Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: mlfoundations-dev_code-stratos-verified-scaled-0.125_stratos_7b
+  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. -->
+
+# mlfoundations-dev_code-stratos-verified-scaled-0.125_stratos_7b
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/code-stratos-verified-scaled-0.125 dataset.
+
+## 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-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 96
+- total_train_batch_size: 96
+- total_eval_batch_size: 768
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.0.2
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 123848585641984.0,
+    "train_loss": 0.6756999851801456,
+    "train_runtime": 1096.7751,
+    "train_samples_per_second": 6.805,
+    "train_steps_per_second": 0.071
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/marianna/models/Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceda51419eb2769134958364dfa4df321394de767c1208329ef80c7d2a411365
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8cbac780499bbe9d36e73ed4f8e7d6068b00d0d4e64b30a149953ee2957026
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85480790b08a2e48c2e1350ebdb59d9fe563bdbdebfb6dde8f0fdd222b4453c2
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265d8c5c23e7599b7a259c40c1ec4e431e291e314d76aecc81c3db59e187da39
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 123848585641984.0,
+    "train_loss": 0.6756999851801456,
+    "train_runtime": 1096.7751,
+    "train_samples_per_second": 6.805,
+    "train_steps_per_second": 0.071
+}

trainer_log.jsonl

@@ -0,0 +1,79 @@
+{"current_steps": 1, "total_steps": 78, "loss": 1.0526, "lr": 1.25e-06, "epoch": 0.038461538461538464, "percentage": 1.28, "elapsed_time": "0:00:20", "remaining_time": "0:26:18"}
+{"current_steps": 2, "total_steps": 78, "loss": 1.0528, "lr": 2.5e-06, "epoch": 0.07692307692307693, "percentage": 2.56, "elapsed_time": "0:00:34", "remaining_time": "0:21:42"}
+{"current_steps": 3, "total_steps": 78, "loss": 1.0596, "lr": 3.7500000000000005e-06, "epoch": 0.11538461538461539, "percentage": 3.85, "elapsed_time": "0:00:47", "remaining_time": "0:19:43"}
+{"current_steps": 4, "total_steps": 78, "loss": 1.0272, "lr": 5e-06, "epoch": 0.15384615384615385, "percentage": 5.13, "elapsed_time": "0:01:01", "remaining_time": "0:18:54"}
+{"current_steps": 5, "total_steps": 78, "loss": 0.9795, "lr": 6.25e-06, "epoch": 0.19230769230769232, "percentage": 6.41, "elapsed_time": "0:01:14", "remaining_time": "0:18:09"}
+{"current_steps": 6, "total_steps": 78, "loss": 0.94, "lr": 7.500000000000001e-06, "epoch": 0.23076923076923078, "percentage": 7.69, "elapsed_time": "0:01:28", "remaining_time": "0:17:47"}
+{"current_steps": 7, "total_steps": 78, "loss": 0.9473, "lr": 8.750000000000001e-06, "epoch": 0.2692307692307692, "percentage": 8.97, "elapsed_time": "0:01:41", "remaining_time": "0:17:13"}
+{"current_steps": 8, "total_steps": 78, "loss": 0.9536, "lr": 1e-05, "epoch": 0.3076923076923077, "percentage": 10.26, "elapsed_time": "0:01:55", "remaining_time": "0:16:49"}
+{"current_steps": 9, "total_steps": 78, "loss": 0.8806, "lr": 9.994965332706574e-06, "epoch": 0.34615384615384615, "percentage": 11.54, "elapsed_time": "0:02:08", "remaining_time": "0:16:23"}
+{"current_steps": 10, "total_steps": 78, "loss": 0.8694, "lr": 9.979871469976197e-06, "epoch": 0.38461538461538464, "percentage": 12.82, "elapsed_time": "0:02:21", "remaining_time": "0:16:01"}
+{"current_steps": 11, "total_steps": 78, "loss": 0.826, "lr": 9.954748808839675e-06, "epoch": 0.4230769230769231, "percentage": 14.1, "elapsed_time": "0:02:35", "remaining_time": "0:15:45"}
+{"current_steps": 12, "total_steps": 78, "loss": 0.7938, "lr": 9.91964794299315e-06, "epoch": 0.46153846153846156, "percentage": 15.38, "elapsed_time": "0:02:47", "remaining_time": "0:15:19"}
+{"current_steps": 13, "total_steps": 78, "loss": 0.7915, "lr": 9.874639560909118e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:02:59", "remaining_time": "0:14:58"}
+{"current_steps": 14, "total_steps": 78, "loss": 0.7749, "lr": 9.819814303479268e-06, "epoch": 0.5384615384615384, "percentage": 17.95, "elapsed_time": "0:03:14", "remaining_time": "0:14:47"}
+{"current_steps": 15, "total_steps": 78, "loss": 0.7574, "lr": 9.755282581475769e-06, "epoch": 0.5769230769230769, "percentage": 19.23, "elapsed_time": "0:03:25", "remaining_time": "0:14:23"}
+{"current_steps": 16, "total_steps": 78, "loss": 0.7527, "lr": 9.681174353198687e-06, "epoch": 0.6153846153846154, "percentage": 20.51, "elapsed_time": "0:03:40", "remaining_time": "0:14:14"}
+{"current_steps": 17, "total_steps": 78, "loss": 0.7199, "lr": 9.597638862757255e-06, "epoch": 0.6538461538461539, "percentage": 21.79, "elapsed_time": "0:03:57", "remaining_time": "0:14:10"}
+{"current_steps": 18, "total_steps": 78, "loss": 0.715, "lr": 9.504844339512096e-06, "epoch": 0.6923076923076923, "percentage": 23.08, "elapsed_time": "0:04:13", "remaining_time": "0:14:06"}
+{"current_steps": 19, "total_steps": 78, "loss": 0.6988, "lr": 9.40297765928369e-06, "epoch": 0.7307692307692307, "percentage": 24.36, "elapsed_time": "0:04:28", "remaining_time": "0:13:53"}
+{"current_steps": 20, "total_steps": 78, "loss": 0.7013, "lr": 9.292243968009332e-06, "epoch": 0.7692307692307693, "percentage": 25.64, "elapsed_time": "0:04:42", "remaining_time": "0:13:37"}
+{"current_steps": 21, "total_steps": 78, "loss": 0.691, "lr": 9.172866268606514e-06, "epoch": 0.8076923076923077, "percentage": 26.92, "elapsed_time": "0:04:57", "remaining_time": "0:13:27"}
+{"current_steps": 22, "total_steps": 78, "loss": 0.6967, "lr": 9.045084971874738e-06, "epoch": 0.8461538461538461, "percentage": 28.21, "elapsed_time": "0:05:10", "remaining_time": "0:13:10"}
+{"current_steps": 23, "total_steps": 78, "loss": 0.6837, "lr": 8.90915741234015e-06, "epoch": 0.8846153846153846, "percentage": 29.49, "elapsed_time": "0:05:23", "remaining_time": "0:12:53"}
+{"current_steps": 24, "total_steps": 78, "loss": 0.6789, "lr": 8.765357330018056e-06, "epoch": 0.9230769230769231, "percentage": 30.77, "elapsed_time": "0:05:36", "remaining_time": "0:12:37"}
+{"current_steps": 25, "total_steps": 78, "loss": 0.6895, "lr": 8.613974319136959e-06, "epoch": 0.9615384615384616, "percentage": 32.05, "elapsed_time": "0:05:51", "remaining_time": "0:12:24"}
+{"current_steps": 26, "total_steps": 78, "loss": 0.6846, "lr": 8.455313244934324e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:07", "remaining_time": "0:12:14"}
+{"current_steps": 27, "total_steps": 78, "loss": 0.6554, "lr": 8.289693629698564e-06, "epoch": 1.0384615384615385, "percentage": 34.62, "elapsed_time": "0:06:19", "remaining_time": "0:11:57"}
+{"current_steps": 28, "total_steps": 78, "loss": 0.6586, "lr": 8.117449009293668e-06, "epoch": 1.0769230769230769, "percentage": 35.9, "elapsed_time": "0:06:33", "remaining_time": "0:11:42"}
+{"current_steps": 29, "total_steps": 78, "loss": 0.6569, "lr": 7.938926261462366e-06, "epoch": 1.1153846153846154, "percentage": 37.18, "elapsed_time": "0:06:46", "remaining_time": "0:11:26"}
+{"current_steps": 30, "total_steps": 78, "loss": 0.65, "lr": 7.754484907260513e-06, "epoch": 1.1538461538461537, "percentage": 38.46, "elapsed_time": "0:06:59", "remaining_time": "0:11:10"}
+{"current_steps": 31, "total_steps": 78, "loss": 0.6448, "lr": 7.564496387029532e-06, "epoch": 1.1923076923076923, "percentage": 39.74, "elapsed_time": "0:07:12", "remaining_time": "0:10:55"}
+{"current_steps": 32, "total_steps": 78, "loss": 0.6354, "lr": 7.369343312364994e-06, "epoch": 1.2307692307692308, "percentage": 41.03, "elapsed_time": "0:07:26", "remaining_time": "0:10:42"}
+{"current_steps": 33, "total_steps": 78, "loss": 0.6459, "lr": 7.169418695587791e-06, "epoch": 1.2692307692307692, "percentage": 42.31, "elapsed_time": "0:07:41", "remaining_time": "0:10:29"}
+{"current_steps": 34, "total_steps": 78, "loss": 0.6281, "lr": 6.965125158269619e-06, "epoch": 1.3076923076923077, "percentage": 43.59, "elapsed_time": "0:07:54", "remaining_time": "0:10:13"}
+{"current_steps": 35, "total_steps": 78, "loss": 0.6327, "lr": 6.7568741204067145e-06, "epoch": 1.3461538461538463, "percentage": 44.87, "elapsed_time": "0:08:07", "remaining_time": "0:09:58"}
+{"current_steps": 36, "total_steps": 78, "loss": 0.6331, "lr": 6.545084971874738e-06, "epoch": 1.3846153846153846, "percentage": 46.15, "elapsed_time": "0:08:20", "remaining_time": "0:09:43"}
+{"current_steps": 37, "total_steps": 78, "loss": 0.6027, "lr": 6.330184227833376e-06, "epoch": 1.4230769230769231, "percentage": 47.44, "elapsed_time": "0:08:33", "remaining_time": "0:09:28"}
+{"current_steps": 38, "total_steps": 78, "loss": 0.6184, "lr": 6.112604669781572e-06, "epoch": 1.4615384615384617, "percentage": 48.72, "elapsed_time": "0:08:46", "remaining_time": "0:09:13"}
+{"current_steps": 39, "total_steps": 78, "loss": 0.6289, "lr": 5.892784473993184e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:08:59", "remaining_time": "0:08:59"}
+{"current_steps": 40, "total_steps": 78, "loss": 0.613, "lr": 5.671166329088278e-06, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "0:09:12", "remaining_time": "0:08:44"}
+{"current_steps": 41, "total_steps": 78, "loss": 0.6141, "lr": 5.448196544517168e-06, "epoch": 1.5769230769230769, "percentage": 52.56, "elapsed_time": "0:09:24", "remaining_time": "0:08:29"}
+{"current_steps": 42, "total_steps": 78, "loss": 0.6155, "lr": 5.224324151752575e-06, "epoch": 1.6153846153846154, "percentage": 53.85, "elapsed_time": "0:09:38", "remaining_time": "0:08:15"}
+{"current_steps": 43, "total_steps": 78, "loss": 0.6169, "lr": 5e-06, "epoch": 1.6538461538461537, "percentage": 55.13, "elapsed_time": "0:09:54", "remaining_time": "0:08:04"}
+{"current_steps": 44, "total_steps": 78, "loss": 0.6216, "lr": 4.775675848247427e-06, "epoch": 1.6923076923076923, "percentage": 56.41, "elapsed_time": "0:10:07", "remaining_time": "0:07:49"}
+{"current_steps": 45, "total_steps": 78, "loss": 0.611, "lr": 4.551803455482833e-06, "epoch": 1.7307692307692308, "percentage": 57.69, "elapsed_time": "0:10:20", "remaining_time": "0:07:35"}
+{"current_steps": 46, "total_steps": 78, "loss": 0.6072, "lr": 4.3288336709117246e-06, "epoch": 1.7692307692307692, "percentage": 58.97, "elapsed_time": "0:10:35", "remaining_time": "0:07:22"}
+{"current_steps": 47, "total_steps": 78, "loss": 0.5998, "lr": 4.107215526006818e-06, "epoch": 1.8076923076923077, "percentage": 60.26, "elapsed_time": "0:10:47", "remaining_time": "0:07:07"}
+{"current_steps": 48, "total_steps": 78, "loss": 0.6289, "lr": 3.887395330218429e-06, "epoch": 1.8461538461538463, "percentage": 61.54, "elapsed_time": "0:11:01", "remaining_time": "0:06:53"}
+{"current_steps": 49, "total_steps": 78, "loss": 0.6196, "lr": 3.669815772166625e-06, "epoch": 1.8846153846153846, "percentage": 62.82, "elapsed_time": "0:11:14", "remaining_time": "0:06:39"}
+{"current_steps": 50, "total_steps": 78, "loss": 0.6126, "lr": 3.4549150281252635e-06, "epoch": 1.9230769230769231, "percentage": 64.1, "elapsed_time": "0:11:27", "remaining_time": "0:06:24"}
+{"current_steps": 51, "total_steps": 78, "loss": 0.5986, "lr": 3.2431258795932863e-06, "epoch": 1.9615384615384617, "percentage": 65.38, "elapsed_time": "0:11:40", "remaining_time": "0:06:11"}
+{"current_steps": 52, "total_steps": 78, "loss": 0.6136, "lr": 3.0348748417303826e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:11:53", "remaining_time": "0:05:56"}
+{"current_steps": 53, "total_steps": 78, "loss": 0.5742, "lr": 2.83058130441221e-06, "epoch": 2.0384615384615383, "percentage": 67.95, "elapsed_time": "0:12:07", "remaining_time": "0:05:43"}
+{"current_steps": 54, "total_steps": 78, "loss": 0.594, "lr": 2.6306566876350072e-06, "epoch": 2.076923076923077, "percentage": 69.23, "elapsed_time": "0:12:21", "remaining_time": "0:05:29"}
+{"current_steps": 55, "total_steps": 78, "loss": 0.5913, "lr": 2.43550361297047e-06, "epoch": 2.1153846153846154, "percentage": 70.51, "elapsed_time": "0:12:36", "remaining_time": "0:05:16"}
+{"current_steps": 56, "total_steps": 78, "loss": 0.5769, "lr": 2.245515092739488e-06, "epoch": 2.1538461538461537, "percentage": 71.79, "elapsed_time": "0:12:51", "remaining_time": "0:05:03"}
+{"current_steps": 57, "total_steps": 78, "loss": 0.5771, "lr": 2.061073738537635e-06, "epoch": 2.1923076923076925, "percentage": 73.08, "elapsed_time": "0:13:07", "remaining_time": "0:04:50"}
+{"current_steps": 58, "total_steps": 78, "loss": 0.5864, "lr": 1.8825509907063328e-06, "epoch": 2.230769230769231, "percentage": 74.36, "elapsed_time": "0:13:22", "remaining_time": "0:04:36"}
+{"current_steps": 59, "total_steps": 78, "loss": 0.6019, "lr": 1.7103063703014372e-06, "epoch": 2.269230769230769, "percentage": 75.64, "elapsed_time": "0:13:38", "remaining_time": "0:04:23"}
+{"current_steps": 60, "total_steps": 78, "loss": 0.5635, "lr": 1.544686755065677e-06, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "0:13:51", "remaining_time": "0:04:09"}
+{"current_steps": 61, "total_steps": 78, "loss": 0.5717, "lr": 1.3860256808630429e-06, "epoch": 2.3461538461538463, "percentage": 78.21, "elapsed_time": "0:14:03", "remaining_time": "0:03:55"}
+{"current_steps": 62, "total_steps": 78, "loss": 0.5763, "lr": 1.234642669981946e-06, "epoch": 2.3846153846153846, "percentage": 79.49, "elapsed_time": "0:14:16", "remaining_time": "0:03:41"}
+{"current_steps": 63, "total_steps": 78, "loss": 0.5778, "lr": 1.0908425876598512e-06, "epoch": 2.423076923076923, "percentage": 80.77, "elapsed_time": "0:14:29", "remaining_time": "0:03:26"}
+{"current_steps": 64, "total_steps": 78, "loss": 0.5667, "lr": 9.549150281252633e-07, "epoch": 2.4615384615384617, "percentage": 82.05, "elapsed_time": "0:14:41", "remaining_time": "0:03:12"}
+{"current_steps": 65, "total_steps": 78, "loss": 0.5996, "lr": 8.271337313934869e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:14:55", "remaining_time": "0:02:59"}
+{"current_steps": 66, "total_steps": 78, "loss": 0.5987, "lr": 7.077560319906696e-07, "epoch": 2.5384615384615383, "percentage": 84.62, "elapsed_time": "0:15:08", "remaining_time": "0:02:45"}
+{"current_steps": 67, "total_steps": 78, "loss": 0.5749, "lr": 5.9702234071631e-07, "epoch": 2.5769230769230766, "percentage": 85.9, "elapsed_time": "0:15:21", "remaining_time": "0:02:31"}
+{"current_steps": 68, "total_steps": 78, "loss": 0.5616, "lr": 4.951556604879049e-07, "epoch": 2.6153846153846154, "percentage": 87.18, "elapsed_time": "0:15:34", "remaining_time": "0:02:17"}
+{"current_steps": 69, "total_steps": 78, "loss": 0.5571, "lr": 4.0236113724274716e-07, "epoch": 2.6538461538461537, "percentage": 88.46, "elapsed_time": "0:15:49", "remaining_time": "0:02:03"}
+{"current_steps": 70, "total_steps": 78, "loss": 0.5872, "lr": 3.18825646801314e-07, "epoch": 2.6923076923076925, "percentage": 89.74, "elapsed_time": "0:16:03", "remaining_time": "0:01:50"}
+{"current_steps": 71, "total_steps": 78, "loss": 0.5517, "lr": 2.447174185242324e-07, "epoch": 2.730769230769231, "percentage": 91.03, "elapsed_time": "0:16:16", "remaining_time": "0:01:36"}
+{"current_steps": 72, "total_steps": 78, "loss": 0.577, "lr": 1.801856965207338e-07, "epoch": 2.769230769230769, "percentage": 92.31, "elapsed_time": "0:16:28", "remaining_time": "0:01:22"}
+{"current_steps": 73, "total_steps": 78, "loss": 0.5735, "lr": 1.253604390908819e-07, "epoch": 2.8076923076923075, "percentage": 93.59, "elapsed_time": "0:16:43", "remaining_time": "0:01:08"}
+{"current_steps": 74, "total_steps": 78, "loss": 0.5874, "lr": 8.035205700685167e-08, "epoch": 2.8461538461538463, "percentage": 94.87, "elapsed_time": "0:16:55", "remaining_time": "0:00:54"}
+{"current_steps": 75, "total_steps": 78, "loss": 0.564, "lr": 4.52511911603265e-08, "epoch": 2.8846153846153846, "percentage": 96.15, "elapsed_time": "0:17:10", "remaining_time": "0:00:41"}
+{"current_steps": 76, "total_steps": 78, "loss": 0.5748, "lr": 2.012853002380466e-08, "epoch": 2.9230769230769234, "percentage": 97.44, "elapsed_time": "0:17:22", "remaining_time": "0:00:27"}
+{"current_steps": 77, "total_steps": 78, "loss": 0.5707, "lr": 5.034667293427053e-09, "epoch": 2.9615384615384617, "percentage": 98.72, "elapsed_time": "0:17:37", "remaining_time": "0:00:13"}
+{"current_steps": 78, "total_steps": 78, "loss": 0.5867, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:17:49", "remaining_time": "0:00:00"}
+{"current_steps": 78, "total_steps": 78, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:18:15", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,588 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 7.130930423736572,
+      "learning_rate": 1.25e-06,
+      "loss": 1.0526,
+      "step": 1
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 7.099226951599121,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0528,
+      "step": 2
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 6.989954471588135,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.0596,
+      "step": 3
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 6.319800853729248,
+      "learning_rate": 5e-06,
+      "loss": 1.0272,
+      "step": 4
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 4.596342086791992,
+      "learning_rate": 6.25e-06,
+      "loss": 0.9795,
+      "step": 5
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 2.7473602294921875,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.94,
+      "step": 6
+    },
+    {
+      "epoch": 0.2692307692307692,
+      "grad_norm": 4.620419502258301,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.9473,
+      "step": 7
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 4.805872917175293,
+      "learning_rate": 1e-05,
+      "loss": 0.9536,
+      "step": 8
+    },
+    {
+      "epoch": 0.34615384615384615,
+      "grad_norm": 4.337175369262695,
+      "learning_rate": 9.994965332706574e-06,
+      "loss": 0.8806,
+      "step": 9
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 4.0317535400390625,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.8694,
+      "step": 10
+    },
+    {
+      "epoch": 0.4230769230769231,
+      "grad_norm": 3.0269405841827393,
+      "learning_rate": 9.954748808839675e-06,
+      "loss": 0.826,
+      "step": 11
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 1.9066985845565796,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.7938,
+      "step": 12
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.9084997177124023,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.7915,
+      "step": 13
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 1.7610135078430176,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.7749,
+      "step": 14
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 1.4025635719299316,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.7574,
+      "step": 15
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 1.5101988315582275,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.7527,
+      "step": 16
+    },
+    {
+      "epoch": 0.6538461538461539,
+      "grad_norm": 1.289642572402954,
+      "learning_rate": 9.597638862757255e-06,
+      "loss": 0.7199,
+      "step": 17
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 1.2755658626556396,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.715,
+      "step": 18
+    },
+    {
+      "epoch": 0.7307692307692307,
+      "grad_norm": 1.1986231803894043,
+      "learning_rate": 9.40297765928369e-06,
+      "loss": 0.6988,
+      "step": 19
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.021087408065796,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.7013,
+      "step": 20
+    },
+    {
+      "epoch": 0.8076923076923077,
+      "grad_norm": 0.9690332412719727,
+      "learning_rate": 9.172866268606514e-06,
+      "loss": 0.691,
+      "step": 21
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 1.188096046447754,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.6967,
+      "step": 22
+    },
+    {
+      "epoch": 0.8846153846153846,
+      "grad_norm": 0.9607952833175659,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.6837,
+      "step": 23
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.9638901352882385,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.6789,
+      "step": 24
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 1.052692174911499,
+      "learning_rate": 8.613974319136959e-06,
+      "loss": 0.6895,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6750084757804871,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.6846,
+      "step": 26
+    },
+    {
+      "epoch": 1.0384615384615385,
+      "grad_norm": 0.9357823729515076,
+      "learning_rate": 8.289693629698564e-06,
+      "loss": 0.6554,
+      "step": 27
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 1.2013366222381592,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.6586,
+      "step": 28
+    },
+    {
+      "epoch": 1.1153846153846154,
+      "grad_norm": 0.8335021138191223,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.6569,
+      "step": 29
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.703048050403595,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.65,
+      "step": 30
+    },
+    {
+      "epoch": 1.1923076923076923,
+      "grad_norm": 0.9962571263313293,
+      "learning_rate": 7.564496387029532e-06,
+      "loss": 0.6448,
+      "step": 31
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.810019314289093,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.6354,
+      "step": 32
+    },
+    {
+      "epoch": 1.2692307692307692,
+      "grad_norm": 0.6070151925086975,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.6459,
+      "step": 33
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.6172223091125488,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.6281,
+      "step": 34
+    },
+    {
+      "epoch": 1.3461538461538463,
+      "grad_norm": 0.671054482460022,
+      "learning_rate": 6.7568741204067145e-06,
+      "loss": 0.6327,
+      "step": 35
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.5767695307731628,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.6331,
+      "step": 36
+    },
+    {
+      "epoch": 1.4230769230769231,
+      "grad_norm": 0.6138707399368286,
+      "learning_rate": 6.330184227833376e-06,
+      "loss": 0.6027,
+      "step": 37
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.5649499297142029,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.6184,
+      "step": 38
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.638535737991333,
+      "learning_rate": 5.892784473993184e-06,
+      "loss": 0.6289,
+      "step": 39
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.6712307333946228,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.613,
+      "step": 40
+    },
+    {
+      "epoch": 1.5769230769230769,
+      "grad_norm": 0.6186216473579407,
+      "learning_rate": 5.448196544517168e-06,
+      "loss": 0.6141,
+      "step": 41
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.4753836691379547,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.6155,
+      "step": 42
+    },
+    {
+      "epoch": 1.6538461538461537,
+      "grad_norm": 0.5167324542999268,
+      "learning_rate": 5e-06,
+      "loss": 0.6169,
+      "step": 43
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.5835758447647095,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.6216,
+      "step": 44
+    },
+    {
+      "epoch": 1.7307692307692308,
+      "grad_norm": 0.564730167388916,
+      "learning_rate": 4.551803455482833e-06,
+      "loss": 0.611,
+      "step": 45
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 0.5620990991592407,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.6072,
+      "step": 46
+    },
+    {
+      "epoch": 1.8076923076923077,
+      "grad_norm": 0.47912776470184326,
+      "learning_rate": 4.107215526006818e-06,
+      "loss": 0.5998,
+      "step": 47
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.4562658369541168,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.6289,
+      "step": 48
+    },
+    {
+      "epoch": 1.8846153846153846,
+      "grad_norm": 0.5224369764328003,
+      "learning_rate": 3.669815772166625e-06,
+      "loss": 0.6196,
+      "step": 49
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.5150539875030518,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.6126,
+      "step": 50
+    },
+    {
+      "epoch": 1.9615384615384617,
+      "grad_norm": 0.4940248727798462,
+      "learning_rate": 3.2431258795932863e-06,
+      "loss": 0.5986,
+      "step": 51
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4971993565559387,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.6136,
+      "step": 52
+    },
+    {
+      "epoch": 2.0384615384615383,
+      "grad_norm": 0.5150362253189087,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.5742,
+      "step": 53
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 0.45559242367744446,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.594,
+      "step": 54
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "grad_norm": 0.4556572437286377,
+      "learning_rate": 2.43550361297047e-06,
+      "loss": 0.5913,
+      "step": 55
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.504047155380249,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.5769,
+      "step": 56
+    },
+    {
+      "epoch": 2.1923076923076925,
+      "grad_norm": 0.5272749662399292,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.5771,
+      "step": 57
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 0.4603540599346161,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.5864,
+      "step": 58
+    },
+    {
+      "epoch": 2.269230769230769,
+      "grad_norm": 0.3963864743709564,
+      "learning_rate": 1.7103063703014372e-06,
+      "loss": 0.6019,
+      "step": 59
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.43673136830329895,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.5635,
+      "step": 60
+    },
+    {
+      "epoch": 2.3461538461538463,
+      "grad_norm": 0.4128812551498413,
+      "learning_rate": 1.3860256808630429e-06,
+      "loss": 0.5717,
+      "step": 61
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": 0.4299347698688507,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.5763,
+      "step": 62
+    },
+    {
+      "epoch": 2.423076923076923,
+      "grad_norm": 0.4996536374092102,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.5778,
+      "step": 63
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.48068103194236755,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.5667,
+      "step": 64
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.49868765473365784,
+      "learning_rate": 8.271337313934869e-07,
+      "loss": 0.5996,
+      "step": 65
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 0.3790745139122009,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.5987,
+      "step": 66
+    },
+    {
+      "epoch": 2.5769230769230766,
+      "grad_norm": 0.3854691982269287,
+      "learning_rate": 5.9702234071631e-07,
+      "loss": 0.5749,
+      "step": 67
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.41013067960739136,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.5616,
+      "step": 68
+    },
+    {
+      "epoch": 2.6538461538461537,
+      "grad_norm": 0.40195363759994507,
+      "learning_rate": 4.0236113724274716e-07,
+      "loss": 0.5571,
+      "step": 69
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 0.3825042247772217,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.5872,
+      "step": 70
+    },
+    {
+      "epoch": 2.730769230769231,
+      "grad_norm": 0.3998315632343292,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.5517,
+      "step": 71
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.4044024348258972,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.577,
+      "step": 72
+    },
+    {
+      "epoch": 2.8076923076923075,
+      "grad_norm": 0.40848174691200256,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.5735,
+      "step": 73
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "grad_norm": 0.3801068365573883,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.5874,
+      "step": 74
+    },
+    {
+      "epoch": 2.8846153846153846,
+      "grad_norm": 0.43877533078193665,
+      "learning_rate": 4.52511911603265e-08,
+      "loss": 0.564,
+      "step": 75
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.3853648602962494,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.5748,
+      "step": 76
+    },
+    {
+      "epoch": 2.9615384615384617,
+      "grad_norm": 0.3701406717300415,
+      "learning_rate": 5.034667293427053e-09,
+      "loss": 0.5707,
+      "step": 77
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3850381672382355,
+      "learning_rate": 0.0,
+      "loss": 0.5867,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "step": 78,
+      "total_flos": 123848585641984.0,
+      "train_loss": 0.6756999851801456,
+      "train_runtime": 1096.7751,
+      "train_samples_per_second": 6.805,
+      "train_steps_per_second": 0.071
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 78,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 123848585641984.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6c6b5d8416e7d40b441db2fe265f8e2c492d461de43cf375554f9fa1548baa
+size 7672