Upload folder using huggingface_hub

README.md

@@ -0,0 +1,90 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: RLAIF-V-Dataset
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# RLAIF-V-Dataset
+
+This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the RLAIF-V-Dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4467
+- Rewards/chosen: -3.1988
+- Rewards/rejected: -5.9606
+- Rewards/accuracies: 0.8163
+- Rewards/margins: 2.7618
+- Logps/rejected: -218.4866
+- Logps/chosen: -190.4653
+- Logits/rejected: -2.3732
+- Logits/chosen: -2.4055
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5777        | 0.1709 | 50   | 0.5813          | -0.4541        | -1.0668          | 0.6683             | 0.6127          | -169.5483      | -163.0182    | -2.5153         | -2.5221       |
+| 0.4982        | 0.3419 | 100  | 0.5161          | -0.9806        | -2.1974          | 0.7212             | 1.2168          | -180.8539      | -168.2832    | -2.4606         | -2.4847       |
+| 0.4954        | 0.5128 | 150  | 0.4770          | -1.5352        | -3.2803          | 0.7548             | 1.7451          | -191.6833      | -173.8291    | -2.0991         | -2.1473       |
+| 0.4567        | 0.6838 | 200  | 0.4598          | -1.1951        | -2.8406          | 0.7596             | 1.6455          | -187.2865      | -170.4288    | -2.1090         | -2.1587       |
+| 0.4873        | 0.8547 | 250  | 0.4487          | -1.9205        | -3.6640          | 0.7635             | 1.7435          | -195.5203      | -177.6819    | -2.5457         | -2.5724       |
+| 0.2176        | 1.0256 | 300  | 0.4383          | -1.1991        | -3.1202          | 0.7846             | 1.9211          | -190.0823      | -170.4688    | -2.3130         | -2.3490       |
+| 0.2095        | 1.1966 | 350  | 0.4537          | -2.3545        | -4.8732          | 0.7933             | 2.5188          | -207.6123      | -182.0219    | -2.3656         | -2.3942       |
+| 0.1952        | 1.3675 | 400  | 0.4353          | -1.9722        | -4.1870          | 0.7962             | 2.2148          | -200.7505      | -178.1995    | -2.3058         | -2.3361       |
+| 0.1819        | 1.5385 | 450  | 0.4321          | -2.0466        | -4.4416          | 0.8077             | 2.3950          | -203.2960      | -178.9431    | -2.2282         | -2.2612       |
+| 0.1932        | 1.7094 | 500  | 0.4247          | -1.8597        | -4.1324          | 0.8087             | 2.2727          | -200.2041      | -177.0739    | -2.2659         | -2.2970       |
+| 0.1921        | 1.8803 | 550  | 0.4131          | -2.3219        | -4.8505          | 0.8183             | 2.5286          | -207.3855      | -181.6965    | -2.3691         | -2.3985       |
+| 0.0868        | 2.0513 | 600  | 0.4392          | -2.7792        | -5.2414          | 0.8135             | 2.4623          | -211.2946      | -186.2690    | -2.4330         | -2.4615       |
+| 0.0825        | 2.2222 | 650  | 0.4447          | -3.2209        | -6.0852          | 0.8154             | 2.8642          | -219.7319      | -190.6867    | -2.3962         | -2.4295       |
+| 0.0925        | 2.3932 | 700  | 0.4449          | -3.2092        | -6.0685          | 0.8183             | 2.8593          | -219.5651      | -190.5695    | -2.3854         | -2.4189       |
+| 0.0754        | 2.5641 | 750  | 0.4567          | -3.3570        | -6.0710          | 0.8115             | 2.7141          | -219.5908      | -192.0472    | -2.3789         | -2.4105       |
+| 0.0707        | 2.7350 | 800  | 0.4484          | -3.2447        | -6.0070          | 0.8135             | 2.7622          | -218.9498      | -190.9248    | -2.3739         | -2.4066       |
+| 0.0739        | 2.9060 | 850  | 0.4468          | -3.2032        | -5.9670          | 0.8173             | 2.7638          | -218.5504      | -190.5096    | -2.3732         | -2.4054       |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 2.994871794871795,
+    "eval_logits/chosen": -2.405457019805908,
+    "eval_logits/rejected": -2.3732309341430664,
+    "eval_logps/chosen": -190.46534729003906,
+    "eval_logps/rejected": -218.4866485595703,
+    "eval_loss": 0.4467383623123169,
+    "eval_rewards/accuracies": 0.8163461685180664,
+    "eval_rewards/chosen": -3.198800802230835,
+    "eval_rewards/margins": 2.761833906173706,
+    "eval_rewards/rejected": -5.960635185241699,
+    "eval_runtime": 521.0004,
+    "eval_samples_per_second": 15.958,
+    "eval_steps_per_second": 0.25,
+    "total_flos": 1.0330118169821184e+16,
+    "train_loss": 0.2635330677789436,
+    "train_runtime": 37517.7872,
+    "train_samples_per_second": 5.983,
+    "train_steps_per_second": 0.023
+}

checkpoint-100/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-100/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

checkpoint-100/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4e61641500ca3a512b1c66d6147ffadef201f5b2aec9d1169a1590b6f6dd66
+size 4921618624

checkpoint-100/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0942e81aa791be7ff1069198337d8026df772a84118c26d00985b1443ca5d7c3
+size 4915917672

checkpoint-100/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:313cfd8df887c89098a740b8824f484e126f10aa9ac3fd7eb73c8f4b6208651e
+size 4915917680

checkpoint-100/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b99b5736445aadc42babbfb779d6746af4b285e7d851ebf9e0ed74c128a16b
+size 380134008

checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15133495296
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00004.safetensors",
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

checkpoint-100/preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '`[INST] `' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,365 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3418803418803419,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017094017094017096,
+      "grad_norm": 35.00202204303521,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.7455849647521973,
+      "logits/rejected": -2.7442612648010254,
+      "logps/chosen": -164.2725830078125,
+      "logps/rejected": -170.57113647460938,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.23749999701976776,
+      "rewards/chosen": 0.0026612328365445137,
+      "rewards/margins": -0.001539617427624762,
+      "rewards/rejected": 0.004200850613415241,
+      "step": 5
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "grad_norm": 36.29266486314593,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.709902763366699,
+      "logits/rejected": -2.7155404090881348,
+      "logps/chosen": -171.80032348632812,
+      "logps/rejected": -165.20169067382812,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": 0.012009668163955212,
+      "rewards/margins": 0.0021203968208283186,
+      "rewards/rejected": 0.009889272041618824,
+      "step": 10
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 33.83921269470837,
+      "learning_rate": 9.999177507263144e-07,
+      "logits/chosen": -2.6502068042755127,
+      "logits/rejected": -2.628007411956787,
+      "logps/chosen": -174.082275390625,
+      "logps/rejected": -174.13429260253906,
+      "loss": 0.6698,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.23495244979858398,
+      "rewards/margins": 0.1125468835234642,
+      "rewards/rejected": 0.12240554392337799,
+      "step": 15
+    },
+    {
+      "epoch": 0.06837606837606838,
+      "grad_norm": 34.14427373918799,
+      "learning_rate": 9.996710299650301e-07,
+      "logits/chosen": -2.473665714263916,
+      "logits/rejected": -2.4469008445739746,
+      "logps/chosen": -158.2163848876953,
+      "logps/rejected": -158.0710906982422,
+      "loss": 0.661,
+      "rewards/accuracies": 0.581250011920929,
+      "rewards/chosen": 0.4233472943305969,
+      "rewards/margins": 0.1434161365032196,
+      "rewards/rejected": 0.2799311578273773,
+      "step": 20
+    },
+    {
+      "epoch": 0.08547008547008547,
+      "grad_norm": 33.2696083475879,
+      "learning_rate": 9.992599188865604e-07,
+      "logits/chosen": -2.314507007598877,
+      "logits/rejected": -2.3168132305145264,
+      "logps/chosen": -150.67019653320312,
+      "logps/rejected": -156.8417510986328,
+      "loss": 0.6501,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": 0.4975205063819885,
+      "rewards/margins": 0.15743504464626312,
+      "rewards/rejected": 0.3400854766368866,
+      "step": 25
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 34.42253361988952,
+      "learning_rate": 9.98684552745256e-07,
+      "logits/chosen": -2.243194103240967,
+      "logits/rejected": -2.251340866088867,
+      "logps/chosen": -161.2266845703125,
+      "logps/rejected": -161.32298278808594,
+      "loss": 0.6289,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": 0.4243805408477783,
+      "rewards/margins": 0.2635195851325989,
+      "rewards/rejected": 0.16086098551750183,
+      "step": 30
+    },
+    {
+      "epoch": 0.11965811965811966,
+      "grad_norm": 31.414296706456245,
+      "learning_rate": 9.979451208349055e-07,
+      "logits/chosen": -2.30315899848938,
+      "logits/rejected": -2.289762496948242,
+      "logps/chosen": -171.71713256835938,
+      "logps/rejected": -174.50900268554688,
+      "loss": 0.6296,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.019384615123271942,
+      "rewards/margins": 0.318477988243103,
+      "rewards/rejected": -0.3378625512123108,
+      "step": 35
+    },
+    {
+      "epoch": 0.13675213675213677,
+      "grad_norm": 32.071830655862556,
+      "learning_rate": 9.970418664264595e-07,
+      "logits/chosen": -2.3935599327087402,
+      "logits/rejected": -2.3812546730041504,
+      "logps/chosen": -171.0698699951172,
+      "logps/rejected": -176.58578491210938,
+      "loss": 0.5991,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.26089853048324585,
+      "rewards/margins": 0.5235068202018738,
+      "rewards/rejected": -0.7844053506851196,
+      "step": 40
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 36.19466541168301,
+      "learning_rate": 9.95975086687994e-07,
+      "logits/chosen": -2.4914021492004395,
+      "logits/rejected": -2.4973323345184326,
+      "logps/chosen": -163.68099975585938,
+      "logps/rejected": -167.174072265625,
+      "loss": 0.6141,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2962096929550171,
+      "rewards/margins": 0.4588828682899475,
+      "rewards/rejected": -0.7550925016403198,
+      "step": 45
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 31.16276115760231,
+      "learning_rate": 9.947451325869439e-07,
+      "logits/chosen": -2.5575203895568848,
+      "logits/rejected": -2.557717800140381,
+      "logps/chosen": -172.04318237304688,
+      "logps/rejected": -177.67672729492188,
+      "loss": 0.5777,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.2069791853427887,
+      "rewards/margins": 0.6018465757369995,
+      "rewards/rejected": -0.808825671672821,
+      "step": 50
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "eval_logits/chosen": -2.5221025943756104,
+      "eval_logits/rejected": -2.5152711868286133,
+      "eval_logps/chosen": -163.01820373535156,
+      "eval_logps/rejected": -169.54832458496094,
+      "eval_loss": 0.5812540650367737,
+      "eval_rewards/accuracies": 0.6682692170143127,
+      "eval_rewards/chosen": -0.45408713817596436,
+      "eval_rewards/margins": 0.6127156615257263,
+      "eval_rewards/rejected": -1.0668028593063354,
+      "eval_runtime": 510.3361,
+      "eval_samples_per_second": 16.291,
+      "eval_steps_per_second": 0.255,
+      "step": 50
+    },
+    {
+      "epoch": 0.18803418803418803,
+      "grad_norm": 31.575578721339145,
+      "learning_rate": 9.933524087746347e-07,
+      "logits/chosen": -2.490377426147461,
+      "logits/rejected": -2.4825081825256348,
+      "logps/chosen": -168.06161499023438,
+      "logps/rejected": -175.0494384765625,
+      "loss": 0.5706,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.5060762763023376,
+      "rewards/margins": 0.7589826583862305,
+      "rewards/rejected": -1.2650587558746338,
+      "step": 55
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 30.171745273288415,
+      "learning_rate": 9.917973734531549e-07,
+      "logits/chosen": -2.48228120803833,
+      "logits/rejected": -2.4833157062530518,
+      "logps/chosen": -159.47142028808594,
+      "logps/rejected": -170.63671875,
+      "loss": 0.5753,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.35752761363983154,
+      "rewards/margins": 0.5991309881210327,
+      "rewards/rejected": -0.9566585421562195,
+      "step": 60
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 32.13878319029882,
+      "learning_rate": 9.90080538224607e-07,
+      "logits/chosen": -2.585407018661499,
+      "logits/rejected": -2.5767769813537598,
+      "logps/chosen": -157.43936157226562,
+      "logps/rejected": -166.13589477539062,
+      "loss": 0.566,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.02057185396552086,
+      "rewards/margins": 0.47568243741989136,
+      "rewards/rejected": -0.4962543547153473,
+      "step": 65
+    },
+    {
+      "epoch": 0.23931623931623933,
+      "grad_norm": 29.494674721856043,
+      "learning_rate": 9.882024679227938e-07,
+      "logits/chosen": -2.6504979133605957,
+      "logits/rejected": -2.6398470401763916,
+      "logps/chosen": -178.0801239013672,
+      "logps/rejected": -179.46328735351562,
+      "loss": 0.5444,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.43436694145202637,
+      "rewards/margins": 0.8427752256393433,
+      "rewards/rejected": -1.27714204788208,
+      "step": 70
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 28.856733948308104,
+      "learning_rate": 9.861637804273881e-07,
+      "logits/chosen": -2.660489082336426,
+      "logits/rejected": -2.655539035797119,
+      "logps/chosen": -162.1233673095703,
+      "logps/rejected": -170.16131591796875,
+      "loss": 0.5568,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.4032784402370453,
+      "rewards/margins": 0.6959114074707031,
+      "rewards/rejected": -1.0991899967193604,
+      "step": 75
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 26.646061534818323,
+      "learning_rate": 9.83965146460653e-07,
+      "logits/chosen": -2.6391615867614746,
+      "logits/rejected": -2.628577709197998,
+      "logps/chosen": -168.58099365234375,
+      "logps/rejected": -179.22805786132812,
+      "loss": 0.5448,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.6665827035903931,
+      "rewards/margins": 0.8240470886230469,
+      "rewards/rejected": -1.4906299114227295,
+      "step": 80
+    },
+    {
+      "epoch": 0.2905982905982906,
+      "grad_norm": 36.04159750418885,
+      "learning_rate": 9.816072893667758e-07,
+      "logits/chosen": -2.6322970390319824,
+      "logits/rejected": -2.6053385734558105,
+      "logps/chosen": -174.82640075683594,
+      "logps/rejected": -186.0735626220703,
+      "loss": 0.5579,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.0639268159866333,
+      "rewards/margins": 1.0258175134658813,
+      "rewards/rejected": -2.0897443294525146,
+      "step": 85
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 26.922939193632168,
+      "learning_rate": 9.790909848738904e-07,
+      "logits/chosen": -2.60801362991333,
+      "logits/rejected": -2.6101624965667725,
+      "logps/chosen": -176.20538330078125,
+      "logps/rejected": -184.7812957763672,
+      "loss": 0.5215,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -0.9929834604263306,
+      "rewards/margins": 0.8646324276924133,
+      "rewards/rejected": -1.8576160669326782,
+      "step": 90
+    },
+    {
+      "epoch": 0.3247863247863248,
+      "grad_norm": 30.3564450245371,
+      "learning_rate": 9.764170608388647e-07,
+      "logits/chosen": -2.6054036617279053,
+      "logits/rejected": -2.5733799934387207,
+      "logps/chosen": -168.037109375,
+      "logps/rejected": -174.51144409179688,
+      "loss": 0.5197,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.6652337312698364,
+      "rewards/margins": 1.060430884361267,
+      "rewards/rejected": -1.725664734840393,
+      "step": 95
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 28.936164680674203,
+      "learning_rate": 9.735863969749371e-07,
+      "logits/chosen": -2.5255179405212402,
+      "logits/rejected": -2.4874520301818848,
+      "logps/chosen": -177.73861694335938,
+      "logps/rejected": -189.82369995117188,
+      "loss": 0.4982,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.8511013984680176,
+      "rewards/margins": 1.1354777812957764,
+      "rewards/rejected": -1.986579179763794,
+      "step": 100
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "eval_logits/chosen": -2.484687328338623,
+      "eval_logits/rejected": -2.460559368133545,
+      "eval_logps/chosen": -168.28323364257812,
+      "eval_logps/rejected": -180.8539276123047,
+      "eval_loss": 0.5161151885986328,
+      "eval_rewards/accuracies": 0.7211538553237915,
+      "eval_rewards/chosen": -0.9805887937545776,
+      "eval_rewards/margins": 1.2167747020721436,
+      "eval_rewards/rejected": -2.1973636150360107,
+      "eval_runtime": 510.3447,
+      "eval_samples_per_second": 16.291,
+      "eval_steps_per_second": 0.255,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 876,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1178822762299392.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82da4d1d6d59805e00ef2db173d4cb9ade65e4282b4e4e61c54f617596094735
+size 7096

checkpoint-200/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-200/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

checkpoint-200/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

checkpoint-200/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85bdeae152eb4cca8cac02b6706b33af0655a0b635c892e22a8bd6a44b023d9
+size 4921618624

checkpoint-200/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f58de914594144d3bd2c90d1cb41d994e266dba0de627bb482b74789557892
+size 4915917672

checkpoint-200/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b49609e124188db18d63e9b61616c53239c6b83f6a64624c63cda8d58229d02
+size 4915917680

checkpoint-200/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2c4f63fcc6e551b99e67fd53326309feb2c619ca4b3617ade0bab0fb8ee0d9
+size 380134008

checkpoint-200/model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15133495296
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00004.safetensors",
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

checkpoint-200/preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '`[INST] `' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,697 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6837606837606838,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017094017094017096,
+      "grad_norm": 35.00202204303521,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.7455849647521973,
+      "logits/rejected": -2.7442612648010254,
+      "logps/chosen": -164.2725830078125,
+      "logps/rejected": -170.57113647460938,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.23749999701976776,
+      "rewards/chosen": 0.0026612328365445137,
+      "rewards/margins": -0.001539617427624762,
+      "rewards/rejected": 0.004200850613415241,
+      "step": 5
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "grad_norm": 36.29266486314593,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.709902763366699,
+      "logits/rejected": -2.7155404090881348,
+      "logps/chosen": -171.80032348632812,
+      "logps/rejected": -165.20169067382812,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": 0.012009668163955212,
+      "rewards/margins": 0.0021203968208283186,
+      "rewards/rejected": 0.009889272041618824,
+      "step": 10
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 33.83921269470837,
+      "learning_rate": 9.999177507263144e-07,
+      "logits/chosen": -2.6502068042755127,
+      "logits/rejected": -2.628007411956787,
+      "logps/chosen": -174.082275390625,
+      "logps/rejected": -174.13429260253906,
+      "loss": 0.6698,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.23495244979858398,
+      "rewards/margins": 0.1125468835234642,
+      "rewards/rejected": 0.12240554392337799,
+      "step": 15
+    },
+    {
+      "epoch": 0.06837606837606838,
+      "grad_norm": 34.14427373918799,
+      "learning_rate": 9.996710299650301e-07,
+      "logits/chosen": -2.473665714263916,
+      "logits/rejected": -2.4469008445739746,
+      "logps/chosen": -158.2163848876953,
+      "logps/rejected": -158.0710906982422,
+      "loss": 0.661,
+      "rewards/accuracies": 0.581250011920929,
+      "rewards/chosen": 0.4233472943305969,
+      "rewards/margins": 0.1434161365032196,
+      "rewards/rejected": 0.2799311578273773,
+      "step": 20
+    },
+    {
+      "epoch": 0.08547008547008547,
+      "grad_norm": 33.2696083475879,
+      "learning_rate": 9.992599188865604e-07,
+      "logits/chosen": -2.314507007598877,
+      "logits/rejected": -2.3168132305145264,
+      "logps/chosen": -150.67019653320312,
+      "logps/rejected": -156.8417510986328,
+      "loss": 0.6501,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": 0.4975205063819885,
+      "rewards/margins": 0.15743504464626312,
+      "rewards/rejected": 0.3400854766368866,
+      "step": 25
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 34.42253361988952,
+      "learning_rate": 9.98684552745256e-07,
+      "logits/chosen": -2.243194103240967,
+      "logits/rejected": -2.251340866088867,
+      "logps/chosen": -161.2266845703125,
+      "logps/rejected": -161.32298278808594,
+      "loss": 0.6289,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": 0.4243805408477783,
+      "rewards/margins": 0.2635195851325989,
+      "rewards/rejected": 0.16086098551750183,
+      "step": 30
+    },
+    {
+      "epoch": 0.11965811965811966,
+      "grad_norm": 31.414296706456245,
+      "learning_rate": 9.979451208349055e-07,
+      "logits/chosen": -2.30315899848938,
+      "logits/rejected": -2.289762496948242,
+      "logps/chosen": -171.71713256835938,
+      "logps/rejected": -174.50900268554688,
+      "loss": 0.6296,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.019384615123271942,
+      "rewards/margins": 0.318477988243103,
+      "rewards/rejected": -0.3378625512123108,
+      "step": 35
+    },
+    {
+      "epoch": 0.13675213675213677,
+      "grad_norm": 32.071830655862556,
+      "learning_rate": 9.970418664264595e-07,
+      "logits/chosen": -2.3935599327087402,
+      "logits/rejected": -2.3812546730041504,
+      "logps/chosen": -171.0698699951172,
+      "logps/rejected": -176.58578491210938,
+      "loss": 0.5991,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.26089853048324585,
+      "rewards/margins": 0.5235068202018738,
+      "rewards/rejected": -0.7844053506851196,
+      "step": 40
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 36.19466541168301,
+      "learning_rate": 9.95975086687994e-07,
+      "logits/chosen": -2.4914021492004395,
+      "logits/rejected": -2.4973323345184326,
+      "logps/chosen": -163.68099975585938,
+      "logps/rejected": -167.174072265625,
+      "loss": 0.6141,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2962096929550171,
+      "rewards/margins": 0.4588828682899475,
+      "rewards/rejected": -0.7550925016403198,
+      "step": 45
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 31.16276115760231,
+      "learning_rate": 9.947451325869439e-07,
+      "logits/chosen": -2.5575203895568848,
+      "logits/rejected": -2.557717800140381,
+      "logps/chosen": -172.04318237304688,
+      "logps/rejected": -177.67672729492188,
+      "loss": 0.5777,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.2069791853427887,
+      "rewards/margins": 0.6018465757369995,
+      "rewards/rejected": -0.808825671672821,
+      "step": 50
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "eval_logits/chosen": -2.5221025943756104,
+      "eval_logits/rejected": -2.5152711868286133,
+      "eval_logps/chosen": -163.01820373535156,
+      "eval_logps/rejected": -169.54832458496094,
+      "eval_loss": 0.5812540650367737,
+      "eval_rewards/accuracies": 0.6682692170143127,
+      "eval_rewards/chosen": -0.45408713817596436,
+      "eval_rewards/margins": 0.6127156615257263,
+      "eval_rewards/rejected": -1.0668028593063354,
+      "eval_runtime": 510.3361,
+      "eval_samples_per_second": 16.291,
+      "eval_steps_per_second": 0.255,
+      "step": 50
+    },
+    {
+      "epoch": 0.18803418803418803,
+      "grad_norm": 31.575578721339145,
+      "learning_rate": 9.933524087746347e-07,
+      "logits/chosen": -2.490377426147461,
+      "logits/rejected": -2.4825081825256348,
+      "logps/chosen": -168.06161499023438,
+      "logps/rejected": -175.0494384765625,
+      "loss": 0.5706,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.5060762763023376,
+      "rewards/margins": 0.7589826583862305,
+      "rewards/rejected": -1.2650587558746338,
+      "step": 55
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 30.171745273288415,
+      "learning_rate": 9.917973734531549e-07,
+      "logits/chosen": -2.48228120803833,
+      "logits/rejected": -2.4833157062530518,
+      "logps/chosen": -159.47142028808594,
+      "logps/rejected": -170.63671875,
+      "loss": 0.5753,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.35752761363983154,
+      "rewards/margins": 0.5991309881210327,
+      "rewards/rejected": -0.9566585421562195,
+      "step": 60
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 32.13878319029882,
+      "learning_rate": 9.90080538224607e-07,
+      "logits/chosen": -2.585407018661499,
+      "logits/rejected": -2.5767769813537598,
+      "logps/chosen": -157.43936157226562,
+      "logps/rejected": -166.13589477539062,
+      "loss": 0.566,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.02057185396552086,
+      "rewards/margins": 0.47568243741989136,
+      "rewards/rejected": -0.4962543547153473,
+      "step": 65
+    },
+    {
+      "epoch": 0.23931623931623933,
+      "grad_norm": 29.494674721856043,
+      "learning_rate": 9.882024679227938e-07,
+      "logits/chosen": -2.6504979133605957,
+      "logits/rejected": -2.6398470401763916,
+      "logps/chosen": -178.0801239013672,
+      "logps/rejected": -179.46328735351562,
+      "loss": 0.5444,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.43436694145202637,
+      "rewards/margins": 0.8427752256393433,
+      "rewards/rejected": -1.27714204788208,
+      "step": 70
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 28.856733948308104,
+      "learning_rate": 9.861637804273881e-07,
+      "logits/chosen": -2.660489082336426,
+      "logits/rejected": -2.655539035797119,
+      "logps/chosen": -162.1233673095703,
+      "logps/rejected": -170.16131591796875,
+      "loss": 0.5568,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.4032784402370453,
+      "rewards/margins": 0.6959114074707031,
+      "rewards/rejected": -1.0991899967193604,
+      "step": 75
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 26.646061534818323,
+      "learning_rate": 9.83965146460653e-07,
+      "logits/chosen": -2.6391615867614746,
+      "logits/rejected": -2.628577709197998,
+      "logps/chosen": -168.58099365234375,
+      "logps/rejected": -179.22805786132812,
+      "loss": 0.5448,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.6665827035903931,
+      "rewards/margins": 0.8240470886230469,
+      "rewards/rejected": -1.4906299114227295,
+      "step": 80
+    },
+    {
+      "epoch": 0.2905982905982906,
+      "grad_norm": 36.04159750418885,
+      "learning_rate": 9.816072893667758e-07,
+      "logits/chosen": -2.6322970390319824,
+      "logits/rejected": -2.6053385734558105,
+      "logps/chosen": -174.82640075683594,
+      "logps/rejected": -186.0735626220703,
+      "loss": 0.5579,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.0639268159866333,
+      "rewards/margins": 1.0258175134658813,
+      "rewards/rejected": -2.0897443294525146,
+      "step": 85
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 26.922939193632168,
+      "learning_rate": 9.790909848738904e-07,
+      "logits/chosen": -2.60801362991333,
+      "logits/rejected": -2.6101624965667725,
+      "logps/chosen": -176.20538330078125,
+      "logps/rejected": -184.7812957763672,
+      "loss": 0.5215,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -0.9929834604263306,
+      "rewards/margins": 0.8646324276924133,
+      "rewards/rejected": -1.8576160669326782,
+      "step": 90
+    },
+    {
+      "epoch": 0.3247863247863248,
+      "grad_norm": 30.3564450245371,
+      "learning_rate": 9.764170608388647e-07,
+      "logits/chosen": -2.6054036617279053,
+      "logits/rejected": -2.5733799934387207,
+      "logps/chosen": -168.037109375,
+      "logps/rejected": -174.51144409179688,
+      "loss": 0.5197,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.6652337312698364,
+      "rewards/margins": 1.060430884361267,
+      "rewards/rejected": -1.725664734840393,
+      "step": 95
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 28.936164680674203,
+      "learning_rate": 9.735863969749371e-07,
+      "logits/chosen": -2.5255179405212402,
+      "logits/rejected": -2.4874520301818848,
+      "logps/chosen": -177.73861694335938,
+      "logps/rejected": -189.82369995117188,
+      "loss": 0.4982,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.8511013984680176,
+      "rewards/margins": 1.1354777812957764,
+      "rewards/rejected": -1.986579179763794,
+      "step": 100
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "eval_logits/chosen": -2.484687328338623,
+      "eval_logits/rejected": -2.460559368133545,
+      "eval_logps/chosen": -168.28323364257812,
+      "eval_logps/rejected": -180.8539276123047,
+      "eval_loss": 0.5161151885986328,
+      "eval_rewards/accuracies": 0.7211538553237915,
+      "eval_rewards/chosen": -0.9805887937545776,
+      "eval_rewards/margins": 1.2167747020721436,
+      "eval_rewards/rejected": -2.1973636150360107,
+      "eval_runtime": 510.3447,
+      "eval_samples_per_second": 16.291,
+      "eval_steps_per_second": 0.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.358974358974359,
+      "grad_norm": 31.089971589067016,
+      "learning_rate": 9.705999245622956e-07,
+      "logits/chosen": -2.4702706336975098,
+      "logits/rejected": -2.4523651599884033,
+      "logps/chosen": -170.59246826171875,
+      "logps/rejected": -182.99813842773438,
+      "loss": 0.4991,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.8999192118644714,
+      "rewards/margins": 0.8702341318130493,
+      "rewards/rejected": -1.770153284072876,
+      "step": 105
+    },
+    {
+      "epoch": 0.37606837606837606,
+      "grad_norm": 27.339023914835686,
+      "learning_rate": 9.674586261416873e-07,
+      "logits/chosen": -2.4866347312927246,
+      "logits/rejected": -2.4518179893493652,
+      "logps/chosen": -179.46290588378906,
+      "logps/rejected": -188.7920379638672,
+      "loss": 0.5213,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.6938365697860718,
+      "rewards/margins": 1.0765600204467773,
+      "rewards/rejected": -1.7703965902328491,
+      "step": 110
+    },
+    {
+      "epoch": 0.39316239316239315,
+      "grad_norm": 31.312902469600562,
+      "learning_rate": 9.641635351911664e-07,
+      "logits/chosen": -2.4456398487091064,
+      "logits/rejected": -2.426159381866455,
+      "logps/chosen": -170.3855438232422,
+      "logps/rejected": -181.9676513671875,
+      "loss": 0.4823,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.8490931391716003,
+      "rewards/margins": 1.2224478721618652,
+      "rewards/rejected": -2.0715408325195312,
+      "step": 115
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 25.966469642807997,
+      "learning_rate": 9.607157357860821e-07,
+      "logits/chosen": -2.4072113037109375,
+      "logits/rejected": -2.3874144554138184,
+      "logps/chosen": -187.41197204589844,
+      "logps/rejected": -201.69454956054688,
+      "loss": 0.5037,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.0798847675323486,
+      "rewards/margins": 1.3365159034729004,
+      "rewards/rejected": -2.41640043258667,
+      "step": 120
+    },
+    {
+      "epoch": 0.42735042735042733,
+      "grad_norm": 32.18242375190423,
+      "learning_rate": 9.571163622424225e-07,
+      "logits/chosen": -2.2766659259796143,
+      "logits/rejected": -2.252072811126709,
+      "logps/chosen": -174.78514099121094,
+      "logps/rejected": -187.40646362304688,
+      "loss": 0.5019,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -1.5247443914413452,
+      "rewards/margins": 1.2177503108978271,
+      "rewards/rejected": -2.742494821548462,
+      "step": 125
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 30.579550576640443,
+      "learning_rate": 9.533665987436261e-07,
+      "logits/chosen": -2.182610034942627,
+      "logits/rejected": -2.128113269805908,
+      "logps/chosen": -178.1033477783203,
+      "logps/rejected": -197.4458465576172,
+      "loss": 0.4957,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.5623412132263184,
+      "rewards/margins": 1.2608497142791748,
+      "rewards/rejected": -2.823190689086914,
+      "step": 130
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 29.287644373971865,
+      "learning_rate": 9.494676789509899e-07,
+      "logits/chosen": -2.1067867279052734,
+      "logits/rejected": -2.0683400630950928,
+      "logps/chosen": -176.67918395996094,
+      "logps/rejected": -193.65371704101562,
+      "loss": 0.4939,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.1053364276885986,
+      "rewards/margins": 1.3829355239868164,
+      "rewards/rejected": -2.488272190093994,
+      "step": 135
+    },
+    {
+      "epoch": 0.47863247863247865,
+      "grad_norm": 27.563555703636343,
+      "learning_rate": 9.454208855977985e-07,
+      "logits/chosen": -2.0855822563171387,
+      "logits/rejected": -2.013296127319336,
+      "logps/chosen": -178.40390014648438,
+      "logps/rejected": -196.03305053710938,
+      "loss": 0.4715,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.443866491317749,
+      "rewards/margins": 1.600778341293335,
+      "rewards/rejected": -3.044644832611084,
+      "step": 140
+    },
+    {
+      "epoch": 0.49572649572649574,
+      "grad_norm": 30.234814125811326,
+      "learning_rate": 9.41227550067308e-07,
+      "logits/chosen": -2.0734238624572754,
+      "logits/rejected": -2.0634400844573975,
+      "logps/chosen": -179.51080322265625,
+      "logps/rejected": -191.87046813964844,
+      "loss": 0.4798,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.6011661291122437,
+      "rewards/margins": 1.445229172706604,
+      "rewards/rejected": -3.0463955402374268,
+      "step": 145
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 31.371346339775513,
+      "learning_rate": 9.36889051954725e-07,
+      "logits/chosen": -2.127821683883667,
+      "logits/rejected": -2.080082416534424,
+      "logps/chosen": -180.66383361816406,
+      "logps/rejected": -196.1031494140625,
+      "loss": 0.4954,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.6335647106170654,
+      "rewards/margins": 1.5422546863555908,
+      "rewards/rejected": -3.1758196353912354,
+      "step": 150
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "eval_logits/chosen": -2.1472573280334473,
+      "eval_logits/rejected": -2.0990829467773438,
+      "eval_logps/chosen": -173.8290557861328,
+      "eval_logps/rejected": -191.683349609375,
+      "eval_loss": 0.47699737548828125,
+      "eval_rewards/accuracies": 0.754807710647583,
+      "eval_rewards/chosen": -1.5351712703704834,
+      "eval_rewards/margins": 1.7451337575912476,
+      "eval_rewards/rejected": -3.2803049087524414,
+      "eval_runtime": 510.7048,
+      "eval_samples_per_second": 16.279,
+      "eval_steps_per_second": 0.255,
+      "step": 150
+    },
+    {
+      "epoch": 0.5299145299145299,
+      "grad_norm": 27.790777356361556,
+      "learning_rate": 9.324068186133245e-07,
+      "logits/chosen": -2.1372084617614746,
+      "logits/rejected": -2.124948024749756,
+      "logps/chosen": -172.3369598388672,
+      "logps/rejected": -186.5850372314453,
+      "loss": 0.4644,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.3583369255065918,
+      "rewards/margins": 1.7439367771148682,
+      "rewards/rejected": -3.102273464202881,
+      "step": 155
+    },
+    {
+      "epoch": 0.5470085470085471,
+      "grad_norm": 27.612583401785376,
+      "learning_rate": 9.277823246848536e-07,
+      "logits/chosen": -2.2635793685913086,
+      "logits/rejected": -2.2123026847839355,
+      "logps/chosen": -186.25137329101562,
+      "logps/rejected": -196.69564819335938,
+      "loss": 0.4547,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -1.2192834615707397,
+      "rewards/margins": 1.371063470840454,
+      "rewards/rejected": -2.5903468132019043,
+      "step": 160
+    },
+    {
+      "epoch": 0.5641025641025641,
+      "grad_norm": 28.168886287584876,
+      "learning_rate": 9.230170916143793e-07,
+      "logits/chosen": -2.3309006690979004,
+      "logits/rejected": -2.2978808879852295,
+      "logps/chosen": -174.7559814453125,
+      "logps/rejected": -195.68280029296875,
+      "loss": 0.4967,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.0855658054351807,
+      "rewards/margins": 1.6249233484268188,
+      "rewards/rejected": -2.710489273071289,
+      "step": 165
+    },
+    {
+      "epoch": 0.5811965811965812,
+      "grad_norm": 28.93959851544435,
+      "learning_rate": 9.181126871497378e-07,
+      "logits/chosen": -2.376833915710449,
+      "logits/rejected": -2.340681552886963,
+      "logps/chosen": -175.3675537109375,
+      "logps/rejected": -194.9619903564453,
+      "loss": 0.4651,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.9624043703079224,
+      "rewards/margins": 1.7745708227157593,
+      "rewards/rejected": -2.7369751930236816,
+      "step": 170
+    },
+    {
+      "epoch": 0.5982905982905983,
+      "grad_norm": 30.43477724579486,
+      "learning_rate": 9.130707248257491e-07,
+      "logits/chosen": -2.458378553390503,
+      "logits/rejected": -2.4171223640441895,
+      "logps/chosen": -168.79849243164062,
+      "logps/rejected": -178.6556396484375,
+      "loss": 0.4728,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.9254748225212097,
+      "rewards/margins": 1.5751961469650269,
+      "rewards/rejected": -2.500671148300171,
+      "step": 175
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 25.220318056395065,
+      "learning_rate": 9.078928634333698e-07,
+      "logits/chosen": -2.4454641342163086,
+      "logits/rejected": -2.4170265197753906,
+      "logps/chosen": -181.41317749023438,
+      "logps/rejected": -199.88668823242188,
+      "loss": 0.4526,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.84205561876297,
+      "rewards/margins": 1.7803510427474976,
+      "rewards/rejected": -2.622406482696533,
+      "step": 180
+    },
+    {
+      "epoch": 0.6324786324786325,
+      "grad_norm": 29.414031929374275,
+      "learning_rate": 9.025808064739549e-07,
+      "logits/chosen": -2.4103400707244873,
+      "logits/rejected": -2.370731830596924,
+      "logps/chosen": -178.70916748046875,
+      "logps/rejected": -193.0004119873047,
+      "loss": 0.4891,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.174070119857788,
+      "rewards/margins": 1.535239338874817,
+      "rewards/rejected": -2.7093093395233154,
+      "step": 185
+    },
+    {
+      "epoch": 0.6495726495726496,
+      "grad_norm": 26.0372223221703,
+      "learning_rate": 8.971363015988113e-07,
+      "logits/chosen": -2.3428735733032227,
+      "logits/rejected": -2.2986531257629395,
+      "logps/chosen": -173.8651580810547,
+      "logps/rejected": -194.9317626953125,
+      "loss": 0.4643,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -1.1425771713256836,
+      "rewards/margins": 1.611919641494751,
+      "rewards/rejected": -2.7544968128204346,
+      "step": 190
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 33.87434178682573,
+      "learning_rate": 8.91561140034225e-07,
+      "logits/chosen": -2.2664923667907715,
+      "logits/rejected": -2.2088184356689453,
+      "logps/chosen": -172.7240753173828,
+      "logps/rejected": -193.1275177001953,
+      "loss": 0.5029,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.3134868144989014,
+      "rewards/margins": 1.5050963163375854,
+      "rewards/rejected": -2.8185834884643555,
+      "step": 195
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 25.21313391058931,
+      "learning_rate": 8.858571559921537e-07,
+      "logits/chosen": -2.191737174987793,
+      "logits/rejected": -2.1188113689422607,
+      "logps/chosen": -174.46722412109375,
+      "logps/rejected": -188.4197540283203,
+      "loss": 0.4567,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.026064157485962,
+      "rewards/margins": 1.5865710973739624,
+      "rewards/rejected": -2.612635374069214,
+      "step": 200
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "eval_logits/chosen": -2.1586899757385254,
+      "eval_logits/rejected": -2.1090493202209473,
+      "eval_logps/chosen": -170.4287872314453,
+      "eval_logps/rejected": -187.2865447998047,
+      "eval_loss": 0.45979756116867065,
+      "eval_rewards/accuracies": 0.7596153616905212,
+      "eval_rewards/chosen": -1.1951465606689453,
+      "eval_rewards/margins": 1.64547860622406,
+      "eval_rewards/rejected": -2.840625047683716,
+      "eval_runtime": 510.4854,
+      "eval_samples_per_second": 16.286,
+      "eval_steps_per_second": 0.255,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 876,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2358113407598592.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82da4d1d6d59805e00ef2db173d4cb9ade65e4282b4e4e61c54f617596094735
+size 7096

checkpoint-300/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-300/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

checkpoint-300/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

checkpoint-300/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70297b2f6be1d0548a0aafaed2a3ff36d6319b27af81ea08bd15aac18e03f5a
+size 4921618624

checkpoint-300/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83bb1810ae16b294441a3fbf7521cb303b38ee7accf3b23211d88a6cf22bf60a
+size 4915917672

checkpoint-300/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c989a774053947b8856a722d3f4a92a676d56811069d083ec49ed1ac315064
+size 4915917680

checkpoint-300/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76fef1bba1c9489671692dcc6d0c4472674ef612a304ddd8bb5ae73e2d395f0
+size 380134008

checkpoint-300/model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15133495296
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00004.safetensors",
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

checkpoint-300/preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '`[INST] `' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,1029 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0256410256410255,
+  "eval_steps": 50,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017094017094017096,
+      "grad_norm": 35.00202204303521,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.7455849647521973,
+      "logits/rejected": -2.7442612648010254,
+      "logps/chosen": -164.2725830078125,
+      "logps/rejected": -170.57113647460938,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.23749999701976776,
+      "rewards/chosen": 0.0026612328365445137,
+      "rewards/margins": -0.001539617427624762,
+      "rewards/rejected": 0.004200850613415241,
+      "step": 5
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "grad_norm": 36.29266486314593,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.709902763366699,
+      "logits/rejected": -2.7155404090881348,
+      "logps/chosen": -171.80032348632812,
+      "logps/rejected": -165.20169067382812,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": 0.012009668163955212,
+      "rewards/margins": 0.0021203968208283186,
+      "rewards/rejected": 0.009889272041618824,
+      "step": 10
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 33.83921269470837,
+      "learning_rate": 9.999177507263144e-07,
+      "logits/chosen": -2.6502068042755127,
+      "logits/rejected": -2.628007411956787,
+      "logps/chosen": -174.082275390625,
+      "logps/rejected": -174.13429260253906,
+      "loss": 0.6698,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.23495244979858398,
+      "rewards/margins": 0.1125468835234642,
+      "rewards/rejected": 0.12240554392337799,
+      "step": 15
+    },
+    {
+      "epoch": 0.06837606837606838,
+      "grad_norm": 34.14427373918799,
+      "learning_rate": 9.996710299650301e-07,
+      "logits/chosen": -2.473665714263916,
+      "logits/rejected": -2.4469008445739746,
+      "logps/chosen": -158.2163848876953,
+      "logps/rejected": -158.0710906982422,
+      "loss": 0.661,
+      "rewards/accuracies": 0.581250011920929,
+      "rewards/chosen": 0.4233472943305969,
+      "rewards/margins": 0.1434161365032196,
+      "rewards/rejected": 0.2799311578273773,
+      "step": 20
+    },
+    {
+      "epoch": 0.08547008547008547,
+      "grad_norm": 33.2696083475879,
+      "learning_rate": 9.992599188865604e-07,
+      "logits/chosen": -2.314507007598877,
+      "logits/rejected": -2.3168132305145264,
+      "logps/chosen": -150.67019653320312,
+      "logps/rejected": -156.8417510986328,
+      "loss": 0.6501,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": 0.4975205063819885,
+      "rewards/margins": 0.15743504464626312,
+      "rewards/rejected": 0.3400854766368866,
+      "step": 25
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 34.42253361988952,
+      "learning_rate": 9.98684552745256e-07,
+      "logits/chosen": -2.243194103240967,
+      "logits/rejected": -2.251340866088867,
+      "logps/chosen": -161.2266845703125,
+      "logps/rejected": -161.32298278808594,
+      "loss": 0.6289,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": 0.4243805408477783,
+      "rewards/margins": 0.2635195851325989,
+      "rewards/rejected": 0.16086098551750183,
+      "step": 30
+    },
+    {
+      "epoch": 0.11965811965811966,
+      "grad_norm": 31.414296706456245,
+      "learning_rate": 9.979451208349055e-07,
+      "logits/chosen": -2.30315899848938,
+      "logits/rejected": -2.289762496948242,
+      "logps/chosen": -171.71713256835938,
+      "logps/rejected": -174.50900268554688,
+      "loss": 0.6296,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.019384615123271942,
+      "rewards/margins": 0.318477988243103,
+      "rewards/rejected": -0.3378625512123108,
+      "step": 35
+    },
+    {
+      "epoch": 0.13675213675213677,
+      "grad_norm": 32.071830655862556,
+      "learning_rate": 9.970418664264595e-07,
+      "logits/chosen": -2.3935599327087402,
+      "logits/rejected": -2.3812546730041504,
+      "logps/chosen": -171.0698699951172,
+      "logps/rejected": -176.58578491210938,
+      "loss": 0.5991,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.26089853048324585,
+      "rewards/margins": 0.5235068202018738,
+      "rewards/rejected": -0.7844053506851196,
+      "step": 40
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 36.19466541168301,
+      "learning_rate": 9.95975086687994e-07,
+      "logits/chosen": -2.4914021492004395,
+      "logits/rejected": -2.4973323345184326,
+      "logps/chosen": -163.68099975585938,
+      "logps/rejected": -167.174072265625,
+      "loss": 0.6141,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2962096929550171,
+      "rewards/margins": 0.4588828682899475,
+      "rewards/rejected": -0.7550925016403198,
+      "step": 45
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 31.16276115760231,
+      "learning_rate": 9.947451325869439e-07,
+      "logits/chosen": -2.5575203895568848,
+      "logits/rejected": -2.557717800140381,
+      "logps/chosen": -172.04318237304688,
+      "logps/rejected": -177.67672729492188,
+      "loss": 0.5777,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.2069791853427887,
+      "rewards/margins": 0.6018465757369995,
+      "rewards/rejected": -0.808825671672821,
+      "step": 50
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "eval_logits/chosen": -2.5221025943756104,
+      "eval_logits/rejected": -2.5152711868286133,
+      "eval_logps/chosen": -163.01820373535156,
+      "eval_logps/rejected": -169.54832458496094,
+      "eval_loss": 0.5812540650367737,
+      "eval_rewards/accuracies": 0.6682692170143127,
+      "eval_rewards/chosen": -0.45408713817596436,
+      "eval_rewards/margins": 0.6127156615257263,
+      "eval_rewards/rejected": -1.0668028593063354,
+      "eval_runtime": 510.3361,
+      "eval_samples_per_second": 16.291,
+      "eval_steps_per_second": 0.255,
+      "step": 50
+    },
+    {
+      "epoch": 0.18803418803418803,
+      "grad_norm": 31.575578721339145,
+      "learning_rate": 9.933524087746347e-07,
+      "logits/chosen": -2.490377426147461,
+      "logits/rejected": -2.4825081825256348,
+      "logps/chosen": -168.06161499023438,
+      "logps/rejected": -175.0494384765625,
+      "loss": 0.5706,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.5060762763023376,
+      "rewards/margins": 0.7589826583862305,
+      "rewards/rejected": -1.2650587558746338,
+      "step": 55
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 30.171745273288415,
+      "learning_rate": 9.917973734531549e-07,
+      "logits/chosen": -2.48228120803833,
+      "logits/rejected": -2.4833157062530518,
+      "logps/chosen": -159.47142028808594,
+      "logps/rejected": -170.63671875,
+      "loss": 0.5753,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.35752761363983154,
+      "rewards/margins": 0.5991309881210327,
+      "rewards/rejected": -0.9566585421562195,
+      "step": 60
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 32.13878319029882,
+      "learning_rate": 9.90080538224607e-07,
+      "logits/chosen": -2.585407018661499,
+      "logits/rejected": -2.5767769813537598,
+      "logps/chosen": -157.43936157226562,
+      "logps/rejected": -166.13589477539062,
+      "loss": 0.566,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.02057185396552086,
+      "rewards/margins": 0.47568243741989136,
+      "rewards/rejected": -0.4962543547153473,
+      "step": 65
+    },
+    {
+      "epoch": 0.23931623931623933,
+      "grad_norm": 29.494674721856043,
+      "learning_rate": 9.882024679227938e-07,
+      "logits/chosen": -2.6504979133605957,
+      "logits/rejected": -2.6398470401763916,
+      "logps/chosen": -178.0801239013672,
+      "logps/rejected": -179.46328735351562,
+      "loss": 0.5444,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.43436694145202637,
+      "rewards/margins": 0.8427752256393433,
+      "rewards/rejected": -1.27714204788208,
+      "step": 70
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 28.856733948308104,
+      "learning_rate": 9.861637804273881e-07,
+      "logits/chosen": -2.660489082336426,
+      "logits/rejected": -2.655539035797119,
+      "logps/chosen": -162.1233673095703,
+      "logps/rejected": -170.16131591796875,
+      "loss": 0.5568,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.4032784402370453,
+      "rewards/margins": 0.6959114074707031,
+      "rewards/rejected": -1.0991899967193604,
+      "step": 75
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 26.646061534818323,
+      "learning_rate": 9.83965146460653e-07,
+      "logits/chosen": -2.6391615867614746,
+      "logits/rejected": -2.628577709197998,
+      "logps/chosen": -168.58099365234375,
+      "logps/rejected": -179.22805786132812,
+      "loss": 0.5448,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.6665827035903931,
+      "rewards/margins": 0.8240470886230469,
+      "rewards/rejected": -1.4906299114227295,
+      "step": 80
+    },
+    {
+      "epoch": 0.2905982905982906,
+      "grad_norm": 36.04159750418885,
+      "learning_rate": 9.816072893667758e-07,
+      "logits/chosen": -2.6322970390319824,
+      "logits/rejected": -2.6053385734558105,
+      "logps/chosen": -174.82640075683594,
+      "logps/rejected": -186.0735626220703,
+      "loss": 0.5579,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.0639268159866333,
+      "rewards/margins": 1.0258175134658813,
+      "rewards/rejected": -2.0897443294525146,
+      "step": 85
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 26.922939193632168,
+      "learning_rate": 9.790909848738904e-07,
+      "logits/chosen": -2.60801362991333,
+      "logits/rejected": -2.6101624965667725,
+      "logps/chosen": -176.20538330078125,
+      "logps/rejected": -184.7812957763672,
+      "loss": 0.5215,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -0.9929834604263306,
+      "rewards/margins": 0.8646324276924133,
+      "rewards/rejected": -1.8576160669326782,
+      "step": 90
+    },
+    {
+      "epoch": 0.3247863247863248,
+      "grad_norm": 30.3564450245371,
+      "learning_rate": 9.764170608388647e-07,
+      "logits/chosen": -2.6054036617279053,
+      "logits/rejected": -2.5733799934387207,
+      "logps/chosen": -168.037109375,
+      "logps/rejected": -174.51144409179688,
+      "loss": 0.5197,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.6652337312698364,
+      "rewards/margins": 1.060430884361267,
+      "rewards/rejected": -1.725664734840393,
+      "step": 95
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 28.936164680674203,
+      "learning_rate": 9.735863969749371e-07,
+      "logits/chosen": -2.5255179405212402,
+      "logits/rejected": -2.4874520301818848,
+      "logps/chosen": -177.73861694335938,
+      "logps/rejected": -189.82369995117188,
+      "loss": 0.4982,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.8511013984680176,
+      "rewards/margins": 1.1354777812957764,
+      "rewards/rejected": -1.986579179763794,
+      "step": 100
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "eval_logits/chosen": -2.484687328338623,
+      "eval_logits/rejected": -2.460559368133545,
+      "eval_logps/chosen": -168.28323364257812,
+      "eval_logps/rejected": -180.8539276123047,
+      "eval_loss": 0.5161151885986328,
+      "eval_rewards/accuracies": 0.7211538553237915,
+      "eval_rewards/chosen": -0.9805887937545776,
+      "eval_rewards/margins": 1.2167747020721436,
+      "eval_rewards/rejected": -2.1973636150360107,
+      "eval_runtime": 510.3447,
+      "eval_samples_per_second": 16.291,
+      "eval_steps_per_second": 0.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.358974358974359,
+      "grad_norm": 31.089971589067016,
+      "learning_rate": 9.705999245622956e-07,
+      "logits/chosen": -2.4702706336975098,
+      "logits/rejected": -2.4523651599884033,
+      "logps/chosen": -170.59246826171875,
+      "logps/rejected": -182.99813842773438,
+      "loss": 0.4991,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.8999192118644714,
+      "rewards/margins": 0.8702341318130493,
+      "rewards/rejected": -1.770153284072876,
+      "step": 105
+    },
+    {
+      "epoch": 0.37606837606837606,
+      "grad_norm": 27.339023914835686,
+      "learning_rate": 9.674586261416873e-07,
+      "logits/chosen": -2.4866347312927246,
+      "logits/rejected": -2.4518179893493652,
+      "logps/chosen": -179.46290588378906,
+      "logps/rejected": -188.7920379638672,
+      "loss": 0.5213,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.6938365697860718,
+      "rewards/margins": 1.0765600204467773,
+      "rewards/rejected": -1.7703965902328491,
+      "step": 110
+    },
+    {
+      "epoch": 0.39316239316239315,
+      "grad_norm": 31.312902469600562,
+      "learning_rate": 9.641635351911664e-07,
+      "logits/chosen": -2.4456398487091064,
+      "logits/rejected": -2.426159381866455,
+      "logps/chosen": -170.3855438232422,
+      "logps/rejected": -181.9676513671875,
+      "loss": 0.4823,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.8490931391716003,
+      "rewards/margins": 1.2224478721618652,
+      "rewards/rejected": -2.0715408325195312,
+      "step": 115
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 25.966469642807997,
+      "learning_rate": 9.607157357860821e-07,
+      "logits/chosen": -2.4072113037109375,
+      "logits/rejected": -2.3874144554138184,
+      "logps/chosen": -187.41197204589844,
+      "logps/rejected": -201.69454956054688,
+      "loss": 0.5037,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.0798847675323486,
+      "rewards/margins": 1.3365159034729004,
+      "rewards/rejected": -2.41640043258667,
+      "step": 120
+    },
+    {
+      "epoch": 0.42735042735042733,
+      "grad_norm": 32.18242375190423,
+      "learning_rate": 9.571163622424225e-07,
+      "logits/chosen": -2.2766659259796143,
+      "logits/rejected": -2.252072811126709,
+      "logps/chosen": -174.78514099121094,
+      "logps/rejected": -187.40646362304688,
+      "loss": 0.5019,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -1.5247443914413452,
+      "rewards/margins": 1.2177503108978271,
+      "rewards/rejected": -2.742494821548462,
+      "step": 125
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 30.579550576640443,
+      "learning_rate": 9.533665987436261e-07,
+      "logits/chosen": -2.182610034942627,
+      "logits/rejected": -2.128113269805908,
+      "logps/chosen": -178.1033477783203,
+      "logps/rejected": -197.4458465576172,
+      "loss": 0.4957,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.5623412132263184,
+      "rewards/margins": 1.2608497142791748,
+      "rewards/rejected": -2.823190689086914,
+      "step": 130
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 29.287644373971865,
+      "learning_rate": 9.494676789509899e-07,
+      "logits/chosen": -2.1067867279052734,
+      "logits/rejected": -2.0683400630950928,
+      "logps/chosen": -176.67918395996094,
+      "logps/rejected": -193.65371704101562,
+      "loss": 0.4939,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.1053364276885986,
+      "rewards/margins": 1.3829355239868164,
+      "rewards/rejected": -2.488272190093994,
+      "step": 135
+    },
+    {
+      "epoch": 0.47863247863247865,
+      "grad_norm": 27.563555703636343,
+      "learning_rate": 9.454208855977985e-07,
+      "logits/chosen": -2.0855822563171387,
+      "logits/rejected": -2.013296127319336,
+      "logps/chosen": -178.40390014648438,
+      "logps/rejected": -196.03305053710938,
+      "loss": 0.4715,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.443866491317749,
+      "rewards/margins": 1.600778341293335,
+      "rewards/rejected": -3.044644832611084,
+      "step": 140
+    },
+    {
+      "epoch": 0.49572649572649574,
+      "grad_norm": 30.234814125811326,
+      "learning_rate": 9.41227550067308e-07,
+      "logits/chosen": -2.0734238624572754,
+      "logits/rejected": -2.0634400844573975,
+      "logps/chosen": -179.51080322265625,
+      "logps/rejected": -191.87046813964844,
+      "loss": 0.4798,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.6011661291122437,
+      "rewards/margins": 1.445229172706604,
+      "rewards/rejected": -3.0463955402374268,
+      "step": 145
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 31.371346339775513,
+      "learning_rate": 9.36889051954725e-07,
+      "logits/chosen": -2.127821683883667,
+      "logits/rejected": -2.080082416534424,
+      "logps/chosen": -180.66383361816406,
+      "logps/rejected": -196.1031494140625,
+      "loss": 0.4954,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.6335647106170654,
+      "rewards/margins": 1.5422546863555908,
+      "rewards/rejected": -3.1758196353912354,
+      "step": 150
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "eval_logits/chosen": -2.1472573280334473,
+      "eval_logits/rejected": -2.0990829467773438,
+      "eval_logps/chosen": -173.8290557861328,
+      "eval_logps/rejected": -191.683349609375,
+      "eval_loss": 0.47699737548828125,
+      "eval_rewards/accuracies": 0.754807710647583,
+      "eval_rewards/chosen": -1.5351712703704834,
+      "eval_rewards/margins": 1.7451337575912476,
+      "eval_rewards/rejected": -3.2803049087524414,
+      "eval_runtime": 510.7048,
+      "eval_samples_per_second": 16.279,
+      "eval_steps_per_second": 0.255,
+      "step": 150
+    },
+    {
+      "epoch": 0.5299145299145299,
+      "grad_norm": 27.790777356361556,
+      "learning_rate": 9.324068186133245e-07,
+      "logits/chosen": -2.1372084617614746,
+      "logits/rejected": -2.124948024749756,
+      "logps/chosen": -172.3369598388672,
+      "logps/rejected": -186.5850372314453,
+      "loss": 0.4644,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.3583369255065918,
+      "rewards/margins": 1.7439367771148682,
+      "rewards/rejected": -3.102273464202881,
+      "step": 155
+    },
+    {
+      "epoch": 0.5470085470085471,
+      "grad_norm": 27.612583401785376,
+      "learning_rate": 9.277823246848536e-07,
+      "logits/chosen": -2.2635793685913086,
+      "logits/rejected": -2.2123026847839355,
+      "logps/chosen": -186.25137329101562,
+      "logps/rejected": -196.69564819335938,
+      "loss": 0.4547,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -1.2192834615707397,
+      "rewards/margins": 1.371063470840454,
+      "rewards/rejected": -2.5903468132019043,
+      "step": 160
+    },
+    {
+      "epoch": 0.5641025641025641,
+      "grad_norm": 28.168886287584876,
+      "learning_rate": 9.230170916143793e-07,
+      "logits/chosen": -2.3309006690979004,
+      "logits/rejected": -2.2978808879852295,
+      "logps/chosen": -174.7559814453125,
+      "logps/rejected": -195.68280029296875,
+      "loss": 0.4967,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.0855658054351807,
+      "rewards/margins": 1.6249233484268188,
+      "rewards/rejected": -2.710489273071289,
+      "step": 165
+    },
+    {
+      "epoch": 0.5811965811965812,
+      "grad_norm": 28.93959851544435,
+      "learning_rate": 9.181126871497378e-07,
+      "logits/chosen": -2.376833915710449,
+      "logits/rejected": -2.340681552886963,
+      "logps/chosen": -175.3675537109375,
+      "logps/rejected": -194.9619903564453,
+      "loss": 0.4651,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.9624043703079224,
+      "rewards/margins": 1.7745708227157593,
+      "rewards/rejected": -2.7369751930236816,
+      "step": 170
+    },
+    {
+      "epoch": 0.5982905982905983,
+      "grad_norm": 30.43477724579486,
+      "learning_rate": 9.130707248257491e-07,
+      "logits/chosen": -2.458378553390503,
+      "logits/rejected": -2.4171223640441895,
+      "logps/chosen": -168.79849243164062,
+      "logps/rejected": -178.6556396484375,
+      "loss": 0.4728,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.9254748225212097,
+      "rewards/margins": 1.5751961469650269,
+      "rewards/rejected": -2.500671148300171,
+      "step": 175
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 25.220318056395065,
+      "learning_rate": 9.078928634333698e-07,
+      "logits/chosen": -2.4454641342163086,
+      "logits/rejected": -2.4170265197753906,
+      "logps/chosen": -181.41317749023438,
+      "logps/rejected": -199.88668823242188,
+      "loss": 0.4526,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.84205561876297,
+      "rewards/margins": 1.7803510427474976,
+      "rewards/rejected": -2.622406482696533,
+      "step": 180
+    },
+    {
+      "epoch": 0.6324786324786325,
+      "grad_norm": 29.414031929374275,
+      "learning_rate": 9.025808064739549e-07,
+      "logits/chosen": -2.4103400707244873,
+      "logits/rejected": -2.370731830596924,
+      "logps/chosen": -178.70916748046875,
+      "logps/rejected": -193.0004119873047,
+      "loss": 0.4891,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.174070119857788,
+      "rewards/margins": 1.535239338874817,
+      "rewards/rejected": -2.7093093395233154,
+      "step": 185
+    },
+    {
+      "epoch": 0.6495726495726496,
+      "grad_norm": 26.0372223221703,
+      "learning_rate": 8.971363015988113e-07,
+      "logits/chosen": -2.3428735733032227,
+      "logits/rejected": -2.2986531257629395,
+      "logps/chosen": -173.8651580810547,
+      "logps/rejected": -194.9317626953125,
+      "loss": 0.4643,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -1.1425771713256836,
+      "rewards/margins": 1.611919641494751,
+      "rewards/rejected": -2.7544968128204346,
+      "step": 190
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 33.87434178682573,
+      "learning_rate": 8.91561140034225e-07,
+      "logits/chosen": -2.2664923667907715,
+      "logits/rejected": -2.2088184356689453,
+      "logps/chosen": -172.7240753173828,
+      "logps/rejected": -193.1275177001953,
+      "loss": 0.5029,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.3134868144989014,
+      "rewards/margins": 1.5050963163375854,
+      "rewards/rejected": -2.8185834884643555,
+      "step": 195
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 25.21313391058931,
+      "learning_rate": 8.858571559921537e-07,
+      "logits/chosen": -2.191737174987793,
+      "logits/rejected": -2.1188113689422607,
+      "logps/chosen": -174.46722412109375,
+      "logps/rejected": -188.4197540283203,
+      "loss": 0.4567,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.026064157485962,
+      "rewards/margins": 1.5865710973739624,
+      "rewards/rejected": -2.612635374069214,
+      "step": 200
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "eval_logits/chosen": -2.1586899757385254,
+      "eval_logits/rejected": -2.1090493202209473,
+      "eval_logps/chosen": -170.4287872314453,
+      "eval_logps/rejected": -187.2865447998047,
+      "eval_loss": 0.45979756116867065,
+      "eval_rewards/accuracies": 0.7596153616905212,
+      "eval_rewards/chosen": -1.1951465606689453,
+      "eval_rewards/margins": 1.64547860622406,
+      "eval_rewards/rejected": -2.840625047683716,
+      "eval_runtime": 510.4854,
+      "eval_samples_per_second": 16.286,
+      "eval_steps_per_second": 0.255,
+      "step": 200
+    },
+    {
+      "epoch": 0.7008547008547008,
+      "grad_norm": 35.24537564842276,
+      "learning_rate": 8.800262260667754e-07,
+      "logits/chosen": -2.1282899379730225,
+      "logits/rejected": -2.0742104053497314,
+      "logps/chosen": -165.1837921142578,
+      "logps/rejected": -182.61190795898438,
+      "loss": 0.4603,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.3638368844985962,
+      "rewards/margins": 1.6600275039672852,
+      "rewards/rejected": -3.023864507675171,
+      "step": 205
+    },
+    {
+      "epoch": 0.717948717948718,
+      "grad_norm": 28.161564325401752,
+      "learning_rate": 8.740702686170954e-07,
+      "logits/chosen": -2.131873369216919,
+      "logits/rejected": -2.0582406520843506,
+      "logps/chosen": -184.79843139648438,
+      "logps/rejected": -201.92471313476562,
+      "loss": 0.4458,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.8222748041152954,
+      "rewards/margins": 1.8169399499893188,
+      "rewards/rejected": -3.639214277267456,
+      "step": 210
+    },
+    {
+      "epoch": 0.7350427350427351,
+      "grad_norm": 27.38246704123344,
+      "learning_rate": 8.679912431358109e-07,
+      "logits/chosen": -2.149195909500122,
+      "logits/rejected": -2.0881500244140625,
+      "logps/chosen": -176.96768188476562,
+      "logps/rejected": -193.83583068847656,
+      "loss": 0.4503,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.8590911626815796,
+      "rewards/margins": 1.9566419124603271,
+      "rewards/rejected": -3.8157334327697754,
+      "step": 215
+    },
+    {
+      "epoch": 0.7521367521367521,
+      "grad_norm": 26.680467589239278,
+      "learning_rate": 8.617911496046445e-07,
+      "logits/chosen": -2.1819872856140137,
+      "logits/rejected": -2.1153197288513184,
+      "logps/chosen": -172.77716064453125,
+      "logps/rejected": -191.78298950195312,
+      "loss": 0.4676,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.7457681894302368,
+      "rewards/margins": 1.8468406200408936,
+      "rewards/rejected": -3.592608690261841,
+      "step": 220
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 27.17086789362823,
+      "learning_rate": 8.554720278363547e-07,
+      "logits/chosen": -2.2397422790527344,
+      "logits/rejected": -2.199204444885254,
+      "logps/chosen": -173.76963806152344,
+      "logps/rejected": -191.92172241210938,
+      "loss": 0.474,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.4509254693984985,
+      "rewards/margins": 1.7614561319351196,
+      "rewards/rejected": -3.212381362915039,
+      "step": 225
+    },
+    {
+      "epoch": 0.7863247863247863,
+      "grad_norm": 34.41944082003437,
+      "learning_rate": 8.490359568036445e-07,
+      "logits/chosen": -2.3623924255371094,
+      "logits/rejected": -2.332777976989746,
+      "logps/chosen": -181.22314453125,
+      "logps/rejected": -203.68490600585938,
+      "loss": 0.458,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.3178858757019043,
+      "rewards/margins": 1.6162595748901367,
+      "rewards/rejected": -2.934145450592041,
+      "step": 230
+    },
+    {
+      "epoch": 0.8034188034188035,
+      "grad_norm": 26.240821537730366,
+      "learning_rate": 8.424850539551856e-07,
+      "logits/chosen": -2.457951068878174,
+      "logits/rejected": -2.430043935775757,
+      "logps/chosen": -174.00967407226562,
+      "logps/rejected": -190.4671173095703,
+      "loss": 0.4457,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.3960864543914795,
+      "rewards/margins": 1.7217321395874023,
+      "rewards/rejected": -3.117818593978882,
+      "step": 235
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 23.836616559503103,
+      "learning_rate": 8.358214745189829e-07,
+      "logits/chosen": -2.5360074043273926,
+      "logits/rejected": -2.502570867538452,
+      "logps/chosen": -183.65618896484375,
+      "logps/rejected": -204.5669403076172,
+      "loss": 0.4236,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -1.516182541847229,
+      "rewards/margins": 2.1192710399627686,
+      "rewards/rejected": -3.635453462600708,
+      "step": 240
+    },
+    {
+      "epoch": 0.8376068376068376,
+      "grad_norm": 26.25101678311949,
+      "learning_rate": 8.290474107933114e-07,
+      "logits/chosen": -2.5879926681518555,
+      "logits/rejected": -2.5638298988342285,
+      "logps/chosen": -184.1548614501953,
+      "logps/rejected": -202.95677185058594,
+      "loss": 0.4494,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.7255306243896484,
+      "rewards/margins": 1.9638643264770508,
+      "rewards/rejected": -3.68939471244812,
+      "step": 245
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 28.730820152276525,
+      "learning_rate": 8.221650914254565e-07,
+      "logits/chosen": -2.592283248901367,
+      "logits/rejected": -2.561645984649658,
+      "logps/chosen": -183.74407958984375,
+      "logps/rejected": -195.3282470703125,
+      "loss": 0.4873,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.9939171075820923,
+      "rewards/margins": 1.590651273727417,
+      "rewards/rejected": -3.584568500518799,
+      "step": 250
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "eval_logits/chosen": -2.5724236965179443,
+      "eval_logits/rejected": -2.545708417892456,
+      "eval_logps/chosen": -177.6819305419922,
+      "eval_logps/rejected": -195.5203399658203,
+      "eval_loss": 0.44874703884124756,
+      "eval_rewards/accuracies": 0.7634615302085876,
+      "eval_rewards/chosen": -1.9204591512680054,
+      "eval_rewards/margins": 1.743545413017273,
+      "eval_rewards/rejected": -3.664004325866699,
+      "eval_runtime": 510.735,
+      "eval_samples_per_second": 16.278,
+      "eval_steps_per_second": 0.255,
+      "step": 250
+    },
+    {
+      "epoch": 0.8717948717948718,
+      "grad_norm": 26.28610055865234,
+      "learning_rate": 8.151767806784953e-07,
+      "logits/chosen": -2.5476808547973633,
+      "logits/rejected": -2.5247130393981934,
+      "logps/chosen": -188.99472045898438,
+      "logps/rejected": -200.0706329345703,
+      "loss": 0.4745,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -1.8807718753814697,
+      "rewards/margins": 1.3770544528961182,
+      "rewards/rejected": -3.257826328277588,
+      "step": 255
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 31.895303400766686,
+      "learning_rate": 8.080847776863608e-07,
+      "logits/chosen": -2.523097038269043,
+      "logits/rejected": -2.4968159198760986,
+      "logps/chosen": -187.11276245117188,
+      "logps/rejected": -202.34288024902344,
+      "loss": 0.4478,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.120813250541687,
+      "rewards/margins": 2.0744528770446777,
+      "rewards/rejected": -3.1952662467956543,
+      "step": 260
+    },
+    {
+      "epoch": 0.905982905982906,
+      "grad_norm": 26.320681707210774,
+      "learning_rate": 8.008914156974333e-07,
+      "logits/chosen": -2.462744951248169,
+      "logits/rejected": -2.4353935718536377,
+      "logps/chosen": -173.44297790527344,
+      "logps/rejected": -195.9517822265625,
+      "loss": 0.4374,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -0.8408319354057312,
+      "rewards/margins": 1.7711703777313232,
+      "rewards/rejected": -2.612001895904541,
+      "step": 265
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 26.997987002073426,
+      "learning_rate": 7.935990613069086e-07,
+      "logits/chosen": -2.4033281803131104,
+      "logits/rejected": -2.369520425796509,
+      "logps/chosen": -171.97085571289062,
+      "logps/rejected": -191.66697692871094,
+      "loss": 0.4474,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.8512971997261047,
+      "rewards/margins": 1.844062089920044,
+      "rewards/rejected": -2.695359230041504,
+      "step": 270
+    },
+    {
+      "epoch": 0.9401709401709402,
+      "grad_norm": 27.58725138274707,
+      "learning_rate": 7.862101136781946e-07,
+      "logits/chosen": -2.3467745780944824,
+      "logits/rejected": -2.3106236457824707,
+      "logps/chosen": -171.92318725585938,
+      "logps/rejected": -194.26400756835938,
+      "loss": 0.4207,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -1.4691975116729736,
+      "rewards/margins": 1.7321897745132446,
+      "rewards/rejected": -3.201387405395508,
+      "step": 275
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 28.716376412825436,
+      "learning_rate": 7.78727003753595e-07,
+      "logits/chosen": -2.287221670150757,
+      "logits/rejected": -2.260993480682373,
+      "logps/chosen": -175.48435974121094,
+      "logps/rejected": -199.2796173095703,
+      "loss": 0.4469,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.8219757080078125,
+      "rewards/margins": 2.2368292808532715,
+      "rewards/rejected": -4.058804512023926,
+      "step": 280
+    },
+    {
+      "epoch": 0.9743589743589743,
+      "grad_norm": 22.896854237985796,
+      "learning_rate": 7.711521934545342e-07,
+      "logits/chosen": -2.2684969902038574,
+      "logits/rejected": -2.2303268909454346,
+      "logps/chosen": -187.36607360839844,
+      "logps/rejected": -207.65261840820312,
+      "loss": 0.4153,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.6430988311767578,
+      "rewards/margins": 2.1586105823516846,
+      "rewards/rejected": -3.8017096519470215,
+      "step": 285
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "grad_norm": 27.30975328138857,
+      "learning_rate": 7.63488174871594e-07,
+      "logits/chosen": -2.2886035442352295,
+      "logits/rejected": -2.2276930809020996,
+      "logps/chosen": -183.37933349609375,
+      "logps/rejected": -201.49429321289062,
+      "loss": 0.4079,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -1.3509235382080078,
+      "rewards/margins": 2.130119800567627,
+      "rewards/rejected": -3.481043577194214,
+      "step": 290
+    },
+    {
+      "epoch": 1.0085470085470085,
+      "grad_norm": 20.392666769639558,
+      "learning_rate": 7.557374694446221e-07,
+      "logits/chosen": -2.264070510864258,
+      "logits/rejected": -2.248257637023926,
+      "logps/chosen": -170.48977661132812,
+      "logps/rejected": -192.82720947265625,
+      "loss": 0.3189,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.9297264814376831,
+      "rewards/margins": 2.2484724521636963,
+      "rewards/rejected": -3.1781985759735107,
+      "step": 295
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 16.68267756771692,
+      "learning_rate": 7.479026271331863e-07,
+      "logits/chosen": -2.3048789501190186,
+      "logits/rejected": -2.2495861053466797,
+      "logps/chosen": -170.22055053710938,
+      "logps/rejected": -198.54359436035156,
+      "loss": 0.2176,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -0.4595426619052887,
+      "rewards/margins": 2.989124059677124,
+      "rewards/rejected": -3.44866681098938,
+      "step": 300
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "eval_logits/chosen": -2.3489644527435303,
+      "eval_logits/rejected": -2.3130385875701904,
+      "eval_logps/chosen": -170.4687957763672,
+      "eval_logps/rejected": -190.08233642578125,
+      "eval_loss": 0.4382702112197876,
+      "eval_rewards/accuracies": 0.7846153974533081,
+      "eval_rewards/chosen": -1.1991456747055054,
+      "eval_rewards/margins": 1.9210587739944458,
+      "eval_rewards/rejected": -3.1202046871185303,
+      "eval_runtime": 511.3486,
+      "eval_samples_per_second": 16.259,
+      "eval_steps_per_second": 0.254,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 876,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3537404052897792.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82da4d1d6d59805e00ef2db173d4cb9ade65e4282b4e4e61c54f617596094735
+size 7096

checkpoint-400/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-400/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}