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

checkpoint-440/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vidore/colpaligemma-3b-pt-448-base",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
+  "task_type": "FEATURE_EXTRACTION",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-440/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8666da6b0284045ea1c17797e59524b4de4a5ed7d2759201fc4bd85626f167
+size 157071680

checkpoint-440/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39e4a52f878fc427b72519cdc530ab466e2bb9acf34a36c5eb6bebb7a2f1da0
+size 314278906

checkpoint-440/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b5cbc8e887864e83058da79e5d332e294ed535373e9cfeb42b356d0d721a18
+size 14244

checkpoint-440/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8fe59128df8178ef00a8ffaebdaf30ba991e825e1fa22f8b056695880714384
+size 1064

checkpoint-440/trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4978723404255319,
+  "eval_steps": 100,
+  "global_step": 440,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003404255319148936,
+      "eval_loss": 0.0601724237203598,
+      "eval_model_preparation_time": 0.01,
+      "eval_runtime": 51.9059,
+      "eval_samples_per_second": 5.78,
+      "eval_steps_per_second": 1.445,
+      "step": 1
+    },
+    {
+      "epoch": 0.06808510638297872,
+      "grad_norm": 2.580314874649048,
+      "learning_rate": 1e-05,
+      "loss": 0.1747,
+      "step": 20
+    },
+    {
+      "epoch": 0.13617021276595745,
+      "grad_norm": 0.5411002039909363,
+      "learning_rate": 2e-05,
+      "loss": 0.1839,
+      "step": 40
+    },
+    {
+      "epoch": 0.20425531914893616,
+      "grad_norm": 30.60088539123535,
+      "learning_rate": 3e-05,
+      "loss": 0.097,
+      "step": 60
+    },
+    {
+      "epoch": 0.2723404255319149,
+      "grad_norm": 2.3133761882781982,
+      "learning_rate": 4e-05,
+      "loss": 0.0764,
+      "step": 80
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.25011885166168213,
+      "learning_rate": 5e-05,
+      "loss": 0.0362,
+      "step": 100
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "eval_loss": 0.027220023795962334,
+      "eval_model_preparation_time": 0.01,
+      "eval_runtime": 49.6214,
+      "eval_samples_per_second": 6.046,
+      "eval_steps_per_second": 1.511,
+      "step": 100
+    },
+    {
+      "epoch": 0.4085106382978723,
+      "grad_norm": 0.5348984003067017,
+      "learning_rate": 4.705882352941177e-05,
+      "loss": 0.0442,
+      "step": 120
+    },
+    {
+      "epoch": 0.4765957446808511,
+      "grad_norm": 4.219340801239014,
+      "learning_rate": 4.411764705882353e-05,
+      "loss": 0.1433,
+      "step": 140
+    },
+    {
+      "epoch": 0.5446808510638298,
+      "grad_norm": 22.19352149963379,
+      "learning_rate": 4.11764705882353e-05,
+      "loss": 0.1843,
+      "step": 160
+    },
+    {
+      "epoch": 0.6127659574468085,
+      "grad_norm": 0.669491171836853,
+      "learning_rate": 3.8235294117647055e-05,
+      "loss": 0.1255,
+      "step": 180
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.036889929324388504,
+      "learning_rate": 3.529411764705883e-05,
+      "loss": 0.0197,
+      "step": 200
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "eval_loss": 0.041773486882448196,
+      "eval_model_preparation_time": 0.01,
+      "eval_runtime": 52.4089,
+      "eval_samples_per_second": 5.724,
+      "eval_steps_per_second": 1.431,
+      "step": 200
+    },
+    {
+      "epoch": 0.7489361702127659,
+      "grad_norm": 0.3701242506504059,
+      "learning_rate": 3.235294117647059e-05,
+      "loss": 0.0883,
+      "step": 220
+    },
+    {
+      "epoch": 0.8170212765957446,
+      "grad_norm": 0.824481189250946,
+      "learning_rate": 2.9411764705882354e-05,
+      "loss": 0.244,
+      "step": 240
+    },
+    {
+      "epoch": 0.8851063829787233,
+      "grad_norm": 5.7761688232421875,
+      "learning_rate": 2.647058823529412e-05,
+      "loss": 0.0375,
+      "step": 260
+    },
+    {
+      "epoch": 0.9531914893617022,
+      "grad_norm": 0.16368351876735687,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 0.1261,
+      "step": 280
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 8.153935432434082,
+      "learning_rate": 2.058823529411765e-05,
+      "loss": 0.028,
+      "step": 300
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "eval_loss": 0.02839539758861065,
+      "eval_model_preparation_time": 0.01,
+      "eval_runtime": 50.358,
+      "eval_samples_per_second": 5.957,
+      "eval_steps_per_second": 1.489,
+      "step": 300
+    },
+    {
+      "epoch": 1.0893617021276596,
+      "grad_norm": 0.06095070391893387,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.0511,
+      "step": 320
+    },
+    {
+      "epoch": 1.1574468085106382,
+      "grad_norm": 1.101495623588562,
+      "learning_rate": 1.4705882352941177e-05,
+      "loss": 0.114,
+      "step": 340
+    },
+    {
+      "epoch": 1.225531914893617,
+      "grad_norm": 3.808842182159424,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.0372,
+      "step": 360
+    },
+    {
+      "epoch": 1.2936170212765958,
+      "grad_norm": 0.17184576392173767,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.0036,
+      "step": 380
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.2895020842552185,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.021,
+      "step": 400
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "eval_loss": 0.026183338835835457,
+      "eval_model_preparation_time": 0.01,
+      "eval_runtime": 51.031,
+      "eval_samples_per_second": 5.879,
+      "eval_steps_per_second": 1.47,
+      "step": 400
+    },
+    {
+      "epoch": 1.4297872340425533,
+      "grad_norm": 0.05526858940720558,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.0129,
+      "step": 420
+    },
+    {
+      "epoch": 1.4978723404255319,
+      "grad_norm": 0.009605285711586475,
+      "learning_rate": 0.0,
+      "loss": 0.0078,
+      "step": 440
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0598129422848e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-440/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5668e8926daf62fb26b5a894878b46e35e59853aaea424c82a6a53e27924382c
+size 5240

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 1024,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "ColPaliProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff84f53c290d0348c4e206da6094ef781cf8c0e482fec8b268a996b32257cfd
+size 34600975