Add files using upload-large-folder tool

.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 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-VL-72B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: LongWriter-V-72B
+  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. -->
+
+# LongWriter-V-72B
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct) on the LongWriter-V-22K 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: 7e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 24
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 288
+- total_eval_batch_size: 192
+- optimizer: Use adamw_torch_fused 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
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

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": 2.9815303430079156,
+    "total_flos": 2930651586101248.0,
+    "train_loss": 0.8763364265041966,
+    "train_runtime": 71308.8652,
+    "train_samples_per_second": 0.382,
+    "train_steps_per_second": 0.001
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-VL-72B-Instruct",
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 80,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "intermediate_size": 3456,
+    "model_type": "qwen2_5_vl",
+    "out_hidden_size": 8192,
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2,
+    "torch_dtype": "float32"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81e5ab3118c4496f1c94d266daf47b62242c79d265283a2eb31cbaa31c83c0b8
+size 4687059888

model-00002-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ce78042df532bcc4ada08b83d96ed23a87a18fde1b30d4e425ff30b43181b7
+size 4781670320

model-00003-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2012733c15ca87607d015db00eac9b4db0c2bfc719a79e91e4c12d5f47fa5f
+size 4964101384

model-00004-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c8e5945c532749bf460bd3adf77f483c8590e2e7b4ca1cbc4e31f7c6604089
+size 4781637328

model-00005-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696371e1ab18b60999e3fc94c8ad447359e52b5e26a5b408d51e20a5018e1d28
+size 4781670344

model-00006-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36493707335c9994322baee4be20090f77ab0424f1a6a6fe20b5c5a7d61ac2df
+size 4781670360

model-00007-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3bcac70f866e85713e7f8b4f49f31340d41d6f107b06f2ad89e98cf2b50f25
+size 4964101416

model-00008-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199039a5c0006e7f99fe73434b318a82802d3a7936d00a260f92fcb9c228c577
+size 4781637360

model-00009-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cea902ce5ab1b318ef8cd1cb9fea5e60edc4f809b79849faaaa4408f9c6513c
+size 4781670360

model-00010-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c51ace815a6ae360b44f7d937f64b1a9510937e2b8b6908cf89d957cfc697b
+size 4781670360

model-00011-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508c3ef099bc34ee0f645314548fe834391430aa4ca331309f1dacd0a0d2e30b
+size 4964101416

model-00012-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3115003c723357b4df8df0c98c48319ead8df6694cbc2ad35c4fd0a0f334afb
+size 4781637360

model-00013-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e46568dac1a34eb0c7871d44d6d2513dc891e6befabfbcfa508369c456adcd4
+size 4781670360

model-00014-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36a097f702dbf8824784c3450a8b89d3989c9e9f6a02b25b1b75da9f0f49c18
+size 4781670360

model-00015-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35c0be0344abe69620bc10bab91c81328101a4eaba6e348a074b6235908e8b6
+size 4964101416

model-00016-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c359fc25830d1dfc402ef352745f0cd31688c9510feeedbc03e870e4df11e6f8
+size 4781637360

model-00017-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98c2108b9a73cbf4b10d476dd71852c2cc9cff56e31df27f46484cbf2dd1378
+size 4781670360

model-00018-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba41e128ba3b8b575ba6c096697569507ef7b552df05f3680abf011b6b8886a0
+size 4781670360

model-00019-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3279b010041365d099ec02f105105c8bbf5795387a2a95c4cee50a4673ea1af5
+size 4964101416

model-00020-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b8f4dd9365ea85812ec2945c3a307e2645c395806c46a27f0b5008d4773cf9
+size 4781637360

model-00021-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f5fc543602e0786a433b323d5ee2ab1325d630dda49cfd3432911d7302249d
+size 4781670360

model-00022-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230cf6878b865b373e10c9e8568200025df6b1bcc56c6e763454ae73b14c1477
+size 4781670360

model-00023-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4dd55c0897b05b3b8f6624c5f1385de0a3c089c4adf3fb536536bbe3505735
+size 4964101416

model-00024-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c22c8af78d6cce382dfe7065415132162cadd28682cf506bb2a51975664c204
+size 4781637360

model-00025-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53302054fa02ce90a65508b77e5db3b9256deda991eb1e9c94bd3281e3456c65
+size 4781670360

model-00026-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5939d757f37117f5f5d9f342e2bd0f4848c26b83178553adfccb906131ea4a6a
+size 4781670360

model-00027-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acfac86cd451b51924690e08913f9800193185942bb29b9a2b46d050292781c
+size 4964101416

model-00028-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f80aede64e5bf10c463e1c01ee32c3c4b1fe4904a9c02df0684b51709138906
+size 4781637360

model-00029-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9491e53e718da7923ca0a612a11989a6f7e497a0ffc4a7f84c2c88d7fdce69ee
+size 4781670360

model-00030-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8782c8f6f891389213b25ee719d8c390bd49255d3ce73b7069c3ac7f5119a324
+size 4479675656

model-00031-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00cad5b67ba507a60fad79a3b673407136ce7ffed7b8a5c03d49e0f555263eac
+size 2491416704

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2_5_VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

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": "<|im_end|>",
+    "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 +1,210 @@
+{
+  "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 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 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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9815303430079156,
+    "total_flos": 2930651586101248.0,
+    "train_loss": 0.8763364265041966,
+    "train_runtime": 71308.8652,
+    "train_samples_per_second": 0.382,
+    "train_steps_per_second": 0.001
+}

trainer_log.jsonl

@@ -0,0 +1,94 @@
+{"current_steps": 1, "total_steps": 93, "loss": 1.176, "lr": 7.000000000000001e-07, "epoch": 0.0316622691292876, "percentage": 1.08, "elapsed_time": "0:13:34", "remaining_time": "20:49:11"}
+{"current_steps": 2, "total_steps": 93, "loss": 1.1885, "lr": 1.4000000000000001e-06, "epoch": 0.0633245382585752, "percentage": 2.15, "elapsed_time": "0:26:18", "remaining_time": "19:56:48"}
+{"current_steps": 3, "total_steps": 93, "loss": 1.1853, "lr": 2.1e-06, "epoch": 0.09498680738786279, "percentage": 3.23, "elapsed_time": "0:38:35", "remaining_time": "19:17:53"}
+{"current_steps": 4, "total_steps": 93, "loss": 1.1441, "lr": 2.8000000000000003e-06, "epoch": 0.1266490765171504, "percentage": 4.3, "elapsed_time": "0:51:26", "remaining_time": "19:04:40"}
+{"current_steps": 5, "total_steps": 93, "loss": 1.1434, "lr": 3.5e-06, "epoch": 0.158311345646438, "percentage": 5.38, "elapsed_time": "1:03:46", "remaining_time": "18:42:24"}
+{"current_steps": 6, "total_steps": 93, "loss": 1.1287, "lr": 4.2e-06, "epoch": 0.18997361477572558, "percentage": 6.45, "elapsed_time": "1:16:18", "remaining_time": "18:26:24"}
+{"current_steps": 7, "total_steps": 93, "loss": 1.1233, "lr": 4.9e-06, "epoch": 0.22163588390501318, "percentage": 7.53, "elapsed_time": "1:28:25", "remaining_time": "18:06:23"}
+{"current_steps": 8, "total_steps": 93, "loss": 1.1195, "lr": 5.600000000000001e-06, "epoch": 0.2532981530343008, "percentage": 8.6, "elapsed_time": "1:41:24", "remaining_time": "17:57:23"}
+{"current_steps": 9, "total_steps": 93, "loss": 1.0933, "lr": 6.3e-06, "epoch": 0.2849604221635884, "percentage": 9.68, "elapsed_time": "1:53:50", "remaining_time": "17:42:32"}
+{"current_steps": 10, "total_steps": 93, "loss": 1.1054, "lr": 7e-06, "epoch": 0.316622691292876, "percentage": 10.75, "elapsed_time": "2:06:31", "remaining_time": "17:30:07"}
+{"current_steps": 11, "total_steps": 93, "loss": 1.0968, "lr": 6.99749314185716e-06, "epoch": 0.3482849604221636, "percentage": 11.83, "elapsed_time": "2:18:39", "remaining_time": "17:13:35"}
+{"current_steps": 12, "total_steps": 93, "loss": 1.0736, "lr": 6.989976158478782e-06, "epoch": 0.37994722955145116, "percentage": 12.9, "elapsed_time": "2:31:17", "remaining_time": "17:01:13"}
+{"current_steps": 13, "total_steps": 93, "loss": 1.0864, "lr": 6.977459817871147e-06, "epoch": 0.41160949868073876, "percentage": 13.98, "elapsed_time": "2:44:14", "remaining_time": "16:50:40"}
+{"current_steps": 14, "total_steps": 93, "loss": 1.0507, "lr": 6.959962049571609e-06, "epoch": 0.44327176781002636, "percentage": 15.05, "elapsed_time": "2:56:42", "remaining_time": "16:37:10"}
+{"current_steps": 15, "total_steps": 93, "loss": 1.0483, "lr": 6.937507918964709e-06, "epoch": 0.47493403693931396, "percentage": 16.13, "elapsed_time": "3:08:58", "remaining_time": "16:22:40"}
+{"current_steps": 16, "total_steps": 93, "loss": 1.0232, "lr": 6.9101295913762465e-06, "epoch": 0.5065963060686016, "percentage": 17.2, "elapsed_time": "3:21:33", "remaining_time": "16:09:57"}
+{"current_steps": 17, "total_steps": 93, "loss": 1.0304, "lr": 6.877866285996766e-06, "epoch": 0.5382585751978892, "percentage": 18.28, "elapsed_time": "3:34:19", "remaining_time": "15:58:07"}
+{"current_steps": 18, "total_steps": 93, "loss": 1.0308, "lr": 6.840764219700443e-06, "epoch": 0.5699208443271768, "percentage": 19.35, "elapsed_time": "3:46:55", "remaining_time": "15:45:29"}
+{"current_steps": 19, "total_steps": 93, "loss": 1.0285, "lr": 6.798876540839855e-06, "epoch": 0.6015831134564644, "percentage": 20.43, "elapsed_time": "3:59:37", "remaining_time": "15:33:17"}
+{"current_steps": 20, "total_steps": 93, "loss": 1.0189, "lr": 6.752263253111479e-06, "epoch": 0.633245382585752, "percentage": 21.51, "elapsed_time": "4:12:24", "remaining_time": "15:21:18"}
+{"current_steps": 21, "total_steps": 93, "loss": 1.021, "lr": 6.700991129600976e-06, "epoch": 0.6649076517150396, "percentage": 22.58, "elapsed_time": "4:24:44", "remaining_time": "15:07:42"}
+{"current_steps": 22, "total_steps": 93, "loss": 1.0013, "lr": 6.645133617131388e-06, "epoch": 0.6965699208443272, "percentage": 23.66, "elapsed_time": "4:37:43", "remaining_time": "14:56:16"}
+{"current_steps": 23, "total_steps": 93, "loss": 0.986, "lr": 6.584770731051271e-06, "epoch": 0.7282321899736148, "percentage": 24.73, "elapsed_time": "4:50:59", "remaining_time": "14:45:36"}
+{"current_steps": 24, "total_steps": 93, "loss": 0.9853, "lr": 6.51998894061348e-06, "epoch": 0.7598944591029023, "percentage": 25.81, "elapsed_time": "5:03:38", "remaining_time": "14:32:57"}
+{"current_steps": 25, "total_steps": 93, "loss": 0.9969, "lr": 6.4508810451087956e-06, "epoch": 0.7915567282321899, "percentage": 26.88, "elapsed_time": "5:16:09", "remaining_time": "14:19:56"}
+{"current_steps": 26, "total_steps": 93, "loss": 0.9784, "lr": 6.377546040931835e-06, "epoch": 0.8232189973614775, "percentage": 27.96, "elapsed_time": "5:28:51", "remaining_time": "14:07:27"}
+{"current_steps": 27, "total_steps": 93, "loss": 0.9775, "lr": 6.300088979769671e-06, "epoch": 0.8548812664907651, "percentage": 29.03, "elapsed_time": "5:41:14", "remaining_time": "13:54:09"}
+{"current_steps": 28, "total_steps": 93, "loss": 0.9555, "lr": 6.218620818116299e-06, "epoch": 0.8865435356200527, "percentage": 30.11, "elapsed_time": "5:54:29", "remaining_time": "13:42:55"}
+{"current_steps": 29, "total_steps": 93, "loss": 0.9536, "lr": 6.133258258328535e-06, "epoch": 0.9182058047493403, "percentage": 31.18, "elapsed_time": "6:06:42", "remaining_time": "13:29:16"}
+{"current_steps": 30, "total_steps": 93, "loss": 0.9513, "lr": 6.044123581451003e-06, "epoch": 0.9498680738786279, "percentage": 32.26, "elapsed_time": "6:19:12", "remaining_time": "13:16:20"}
+{"current_steps": 31, "total_steps": 93, "loss": 0.9491, "lr": 5.951344472049728e-06, "epoch": 0.9815303430079155, "percentage": 33.33, "elapsed_time": "6:31:52", "remaining_time": "13:03:45"}
+{"current_steps": 32, "total_steps": 93, "loss": 1.2099, "lr": 5.855053835305216e-06, "epoch": 1.0316622691292876, "percentage": 34.41, "elapsed_time": "6:49:02", "remaining_time": "12:59:45"}
+{"current_steps": 33, "total_steps": 93, "loss": 0.8727, "lr": 5.755389606627069e-06, "epoch": 1.0633245382585752, "percentage": 35.48, "elapsed_time": "7:01:59", "remaining_time": "12:47:15"}
+{"current_steps": 34, "total_steps": 93, "loss": 0.8777, "lr": 5.652494554062838e-06, "epoch": 1.0949868073878628, "percentage": 36.56, "elapsed_time": "7:14:20", "remaining_time": "12:33:41"}
+{"current_steps": 35, "total_steps": 93, "loss": 0.8661, "lr": 5.546516073784165e-06, "epoch": 1.1266490765171504, "percentage": 37.63, "elapsed_time": "7:26:39", "remaining_time": "12:20:10"}
+{"current_steps": 36, "total_steps": 93, "loss": 0.8665, "lr": 5.4376059789431955e-06, "epoch": 1.158311345646438, "percentage": 38.71, "elapsed_time": "7:39:28", "remaining_time": "12:07:29"}
+{"current_steps": 37, "total_steps": 93, "loss": 0.8584, "lr": 5.325920282201696e-06, "epoch": 1.1899736147757256, "percentage": 39.78, "elapsed_time": "7:51:50", "remaining_time": "11:54:07"}
+{"current_steps": 38, "total_steps": 93, "loss": 0.8677, "lr": 5.2116189722444164e-06, "epoch": 1.2216358839050132, "percentage": 40.86, "elapsed_time": "8:04:17", "remaining_time": "11:40:56"}
+{"current_steps": 39, "total_steps": 93, "loss": 0.8515, "lr": 5.094865784596845e-06, "epoch": 1.2532981530343008, "percentage": 41.94, "elapsed_time": "8:16:51", "remaining_time": "11:27:57"}
+{"current_steps": 40, "total_steps": 93, "loss": 0.851, "lr": 4.975827967075644e-06, "epoch": 1.2849604221635884, "percentage": 43.01, "elapsed_time": "8:29:45", "remaining_time": "11:15:25"}
+{"current_steps": 41, "total_steps": 93, "loss": 0.8733, "lr": 4.854676040207761e-06, "epoch": 1.316622691292876, "percentage": 44.09, "elapsed_time": "8:42:26", "remaining_time": "11:02:36"}
+{"current_steps": 42, "total_steps": 93, "loss": 0.8698, "lr": 4.731583552961416e-06, "epoch": 1.3482849604221636, "percentage": 45.16, "elapsed_time": "8:54:50", "remaining_time": "10:49:27"}
+{"current_steps": 43, "total_steps": 93, "loss": 0.8464, "lr": 4.606726834138884e-06, "epoch": 1.3799472295514512, "percentage": 46.24, "elapsed_time": "9:07:48", "remaining_time": "10:36:59"}
+{"current_steps": 44, "total_steps": 93, "loss": 0.8465, "lr": 4.480284739787175e-06, "epoch": 1.4116094986807388, "percentage": 47.31, "elapsed_time": "9:19:53", "remaining_time": "10:23:30"}
+{"current_steps": 45, "total_steps": 93, "loss": 0.8415, "lr": 4.352438396988471e-06, "epoch": 1.4432717678100264, "percentage": 48.39, "elapsed_time": "9:32:44", "remaining_time": "10:10:55"}
+{"current_steps": 46, "total_steps": 93, "loss": 0.8089, "lr": 4.223370944397335e-06, "epoch": 1.474934036939314, "percentage": 49.46, "elapsed_time": "9:45:28", "remaining_time": "9:58:12"}
+{"current_steps": 47, "total_steps": 93, "loss": 0.8141, "lr": 4.093267269896339e-06, "epoch": 1.5065963060686016, "percentage": 50.54, "elapsed_time": "9:58:19", "remaining_time": "9:45:35"}
+{"current_steps": 48, "total_steps": 93, "loss": 0.8334, "lr": 3.9623137457459586e-06, "epoch": 1.5382585751978892, "percentage": 51.61, "elapsed_time": "10:11:19", "remaining_time": "9:33:06"}
+{"current_steps": 49, "total_steps": 93, "loss": 0.7996, "lr": 3.83069796160811e-06, "epoch": 1.5699208443271768, "percentage": 52.69, "elapsed_time": "10:23:50", "remaining_time": "9:20:10"}
+{"current_steps": 50, "total_steps": 93, "loss": 0.8206, "lr": 3.6986084558257596e-06, "epoch": 1.6015831134564644, "percentage": 53.76, "elapsed_time": "10:36:31", "remaining_time": "9:07:24"}
+{"current_steps": 51, "total_steps": 93, "loss": 0.8036, "lr": 3.5662344453435665e-06, "epoch": 1.633245382585752, "percentage": 54.84, "elapsed_time": "10:49:08", "remaining_time": "8:54:34"}
+{"current_steps": 52, "total_steps": 93, "loss": 0.849, "lr": 3.4337655546564343e-06, "epoch": 1.6649076517150396, "percentage": 55.91, "elapsed_time": "11:01:16", "remaining_time": "8:41:23"}
+{"current_steps": 53, "total_steps": 93, "loss": 0.7874, "lr": 3.301391544174241e-06, "epoch": 1.6965699208443272, "percentage": 56.99, "elapsed_time": "11:14:32", "remaining_time": "8:29:05"}
+{"current_steps": 54, "total_steps": 93, "loss": 0.8012, "lr": 3.1693020383918907e-06, "epoch": 1.7282321899736148, "percentage": 58.06, "elapsed_time": "11:26:30", "remaining_time": "8:15:48"}
+{"current_steps": 55, "total_steps": 93, "loss": 0.8056, "lr": 3.0376862542540426e-06, "epoch": 1.7598944591029024, "percentage": 59.14, "elapsed_time": "11:38:56", "remaining_time": "8:02:54"}
+{"current_steps": 56, "total_steps": 93, "loss": 0.7769, "lr": 2.9067327301036616e-06, "epoch": 1.79155672823219, "percentage": 60.22, "elapsed_time": "11:51:54", "remaining_time": "7:50:21"}
+{"current_steps": 57, "total_steps": 93, "loss": 0.7984, "lr": 2.7766290556026646e-06, "epoch": 1.8232189973614776, "percentage": 61.29, "elapsed_time": "12:04:14", "remaining_time": "7:37:24"}
+{"current_steps": 58, "total_steps": 93, "loss": 0.7917, "lr": 2.6475616030115286e-06, "epoch": 1.8548812664907652, "percentage": 62.37, "elapsed_time": "12:16:49", "remaining_time": "7:24:37"}
+{"current_steps": 59, "total_steps": 93, "loss": 0.7852, "lr": 2.5197152602128256e-06, "epoch": 1.8865435356200528, "percentage": 63.44, "elapsed_time": "12:29:16", "remaining_time": "7:11:46"}
+{"current_steps": 60, "total_steps": 93, "loss": 0.8023, "lr": 2.393273165861116e-06, "epoch": 1.9182058047493404, "percentage": 64.52, "elapsed_time": "12:41:45", "remaining_time": "6:58:57"}
+{"current_steps": 61, "total_steps": 93, "loss": 0.7616, "lr": 2.2684164470385843e-06, "epoch": 1.949868073878628, "percentage": 65.59, "elapsed_time": "12:54:11", "remaining_time": "6:46:07"}
+{"current_steps": 62, "total_steps": 93, "loss": 0.8165, "lr": 2.14532395979224e-06, "epoch": 1.9815303430079156, "percentage": 66.67, "elapsed_time": "13:07:00", "remaining_time": "6:33:30"}
+{"current_steps": 63, "total_steps": 93, "loss": 1.0035, "lr": 2.0241720329243563e-06, "epoch": 2.0316622691292876, "percentage": 67.74, "elapsed_time": "13:23:43", "remaining_time": "6:22:43"}
+{"current_steps": 64, "total_steps": 93, "loss": 0.7532, "lr": 1.905134215403155e-06, "epoch": 2.063324538258575, "percentage": 68.82, "elapsed_time": "13:36:28", "remaining_time": "6:09:58"}
+{"current_steps": 65, "total_steps": 93, "loss": 0.7628, "lr": 1.7883810277555837e-06, "epoch": 2.094986807387863, "percentage": 69.89, "elapsed_time": "13:49:13", "remaining_time": "5:57:12"}
+{"current_steps": 66, "total_steps": 93, "loss": 0.7511, "lr": 1.6740797177983044e-06, "epoch": 2.1266490765171504, "percentage": 70.97, "elapsed_time": "14:02:02", "remaining_time": "5:44:28"}
+{"current_steps": 67, "total_steps": 93, "loss": 0.7302, "lr": 1.5623940210568042e-06, "epoch": 2.158311345646438, "percentage": 72.04, "elapsed_time": "14:14:39", "remaining_time": "5:31:39"}
+{"current_steps": 68, "total_steps": 93, "loss": 0.7315, "lr": 1.453483926215835e-06, "epoch": 2.1899736147757256, "percentage": 73.12, "elapsed_time": "14:27:20", "remaining_time": "5:18:52"}
+{"current_steps": 69, "total_steps": 93, "loss": 0.7478, "lr": 1.3475054459371625e-06, "epoch": 2.221635883905013, "percentage": 74.19, "elapsed_time": "14:40:00", "remaining_time": "5:06:05"}
+{"current_steps": 70, "total_steps": 93, "loss": 0.7288, "lr": 1.2446103933729302e-06, "epoch": 2.253298153034301, "percentage": 75.27, "elapsed_time": "14:52:39", "remaining_time": "4:53:18"}
+{"current_steps": 71, "total_steps": 93, "loss": 0.7628, "lr": 1.1449461646947839e-06, "epoch": 2.2849604221635884, "percentage": 76.34, "elapsed_time": "15:05:11", "remaining_time": "4:40:28"}
+{"current_steps": 72, "total_steps": 93, "loss": 0.7178, "lr": 1.048655527950273e-06, "epoch": 2.316622691292876, "percentage": 77.42, "elapsed_time": "15:17:33", "remaining_time": "4:27:37"}
+{"current_steps": 73, "total_steps": 93, "loss": 0.7287, "lr": 9.558764185489968e-07, "epoch": 2.3482849604221636, "percentage": 78.49, "elapsed_time": "15:29:54", "remaining_time": "4:14:46"}
+{"current_steps": 74, "total_steps": 93, "loss": 0.7135, "lr": 8.667417416714656e-07, "epoch": 2.379947229551451, "percentage": 79.57, "elapsed_time": "15:42:26", "remaining_time": "4:01:58"}
+{"current_steps": 75, "total_steps": 93, "loss": 0.7242, "lr": 7.813791818837012e-07, "epoch": 2.411609498680739, "percentage": 80.65, "elapsed_time": "15:54:59", "remaining_time": "3:49:11"}
+{"current_steps": 76, "total_steps": 93, "loss": 0.7201, "lr": 6.999110202303293e-07, "epoch": 2.4432717678100264, "percentage": 81.72, "elapsed_time": "16:07:43", "remaining_time": "3:36:27"}
+{"current_steps": 77, "total_steps": 93, "loss": 0.6838, "lr": 6.22453959068165e-07, "epoch": 2.474934036939314, "percentage": 82.8, "elapsed_time": "16:19:57", "remaining_time": "3:23:37"}
+{"current_steps": 78, "total_steps": 93, "loss": 0.717, "lr": 5.491189548912051e-07, "epoch": 2.5065963060686016, "percentage": 83.87, "elapsed_time": "16:32:40", "remaining_time": "3:10:53"}
+{"current_steps": 79, "total_steps": 93, "loss": 0.7152, "lr": 4.800110593865199e-07, "epoch": 2.538258575197889, "percentage": 84.95, "elapsed_time": "16:45:13", "remaining_time": "2:58:08"}
+{"current_steps": 80, "total_steps": 93, "loss": 0.7368, "lr": 4.15229268948729e-07, "epoch": 2.569920844327177, "percentage": 86.02, "elapsed_time": "16:57:51", "remaining_time": "2:45:24"}
+{"current_steps": 81, "total_steps": 93, "loss": 0.715, "lr": 3.5486638286861297e-07, "epoch": 2.6015831134564644, "percentage": 87.1, "elapsed_time": "17:10:32", "remaining_time": "2:32:40"}
+{"current_steps": 82, "total_steps": 93, "loss": 0.74, "lr": 2.990088703990245e-07, "epoch": 2.633245382585752, "percentage": 88.17, "elapsed_time": "17:22:58", "remaining_time": "2:19:54"}
+{"current_steps": 83, "total_steps": 93, "loss": 0.7142, "lr": 2.4773674688852197e-07, "epoch": 2.6649076517150396, "percentage": 89.25, "elapsed_time": "17:35:02", "remaining_time": "2:07:06"}
+{"current_steps": 84, "total_steps": 93, "loss": 0.7372, "lr": 2.0112345916014578e-07, "epoch": 2.6965699208443272, "percentage": 90.32, "elapsed_time": "17:47:50", "remaining_time": "1:54:24"}
+{"current_steps": 85, "total_steps": 93, "loss": 0.7241, "lr": 1.592357802995572e-07, "epoch": 2.728232189973615, "percentage": 91.4, "elapsed_time": "18:00:32", "remaining_time": "1:41:41"}
+{"current_steps": 86, "total_steps": 93, "loss": 0.7095, "lr": 1.2213371400323352e-07, "epoch": 2.7598944591029024, "percentage": 92.47, "elapsed_time": "18:13:06", "remaining_time": "1:28:58"}
+{"current_steps": 87, "total_steps": 93, "loss": 0.6919, "lr": 8.987040862375339e-08, "epoch": 2.79155672823219, "percentage": 93.55, "elapsed_time": "18:25:37", "remaining_time": "1:16:15"}
+{"current_steps": 88, "total_steps": 93, "loss": 0.7263, "lr": 6.249208103529092e-08, "epoch": 2.8232189973614776, "percentage": 94.62, "elapsed_time": "18:38:21", "remaining_time": "1:03:32"}
+{"current_steps": 89, "total_steps": 93, "loss": 0.7415, "lr": 4.0037950428390144e-08, "epoch": 2.8548812664907652, "percentage": 95.7, "elapsed_time": "18:51:11", "remaining_time": "0:50:50"}
+{"current_steps": 90, "total_steps": 93, "loss": 0.7267, "lr": 2.254018212885278e-08, "epoch": 2.886543535620053, "percentage": 96.77, "elapsed_time": "19:03:54", "remaining_time": "0:38:07"}
+{"current_steps": 91, "total_steps": 93, "loss": 0.7175, "lr": 1.0023841521217825e-08, "epoch": 2.9182058047493404, "percentage": 97.85, "elapsed_time": "19:15:54", "remaining_time": "0:25:24"}
+{"current_steps": 92, "total_steps": 93, "loss": 0.7126, "lr": 2.506858142839852e-09, "epoch": 2.949868073878628, "percentage": 98.92, "elapsed_time": "19:28:41", "remaining_time": "0:12:42"}
+{"current_steps": 93, "total_steps": 93, "loss": 0.7082, "lr": 0.0, "epoch": 2.9815303430079156, "percentage": 100.0, "elapsed_time": "19:41:35", "remaining_time": "0:00:00"}
+{"current_steps": 93, "total_steps": 93, "epoch": 2.9815303430079156, "percentage": 100.0, "elapsed_time": "19:48:27", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,693 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9815303430079156,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0316622691292876,
+      "grad_norm": 2.5990071296691895,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 1.176,
+      "step": 1
+    },
+    {
+      "epoch": 0.0633245382585752,
+      "grad_norm": 2.6270251274108887,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 1.1885,
+      "step": 2
+    },
+    {
+      "epoch": 0.09498680738786279,
+      "grad_norm": 2.6077260971069336,
+      "learning_rate": 2.1e-06,
+      "loss": 1.1853,
+      "step": 3
+    },
+    {
+      "epoch": 0.1266490765171504,
+      "grad_norm": 2.4010000228881836,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.1441,
+      "step": 4
+    },
+    {
+      "epoch": 0.158311345646438,
+      "grad_norm": 1.6012561321258545,
+      "learning_rate": 3.5e-06,
+      "loss": 1.1434,
+      "step": 5
+    },
+    {
+      "epoch": 0.18997361477572558,
+      "grad_norm": 1.4890481233596802,
+      "learning_rate": 4.2e-06,
+      "loss": 1.1287,
+      "step": 6
+    },
+    {
+      "epoch": 0.22163588390501318,
+      "grad_norm": 2.0511271953582764,
+      "learning_rate": 4.9e-06,
+      "loss": 1.1233,
+      "step": 7
+    },
+    {
+      "epoch": 0.2532981530343008,
+      "grad_norm": 1.9991264343261719,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 1.1195,
+      "step": 8
+    },
+    {
+      "epoch": 0.2849604221635884,
+      "grad_norm": 2.4904370307922363,
+      "learning_rate": 6.3e-06,
+      "loss": 1.0933,
+      "step": 9
+    },
+    {
+      "epoch": 0.316622691292876,
+      "grad_norm": 2.41306471824646,
+      "learning_rate": 7e-06,
+      "loss": 1.1054,
+      "step": 10
+    },
+    {
+      "epoch": 0.3482849604221636,
+      "grad_norm": 1.916558861732483,
+      "learning_rate": 6.99749314185716e-06,
+      "loss": 1.0968,
+      "step": 11
+    },
+    {
+      "epoch": 0.37994722955145116,
+      "grad_norm": 1.6149336099624634,
+      "learning_rate": 6.989976158478782e-06,
+      "loss": 1.0736,
+      "step": 12
+    },
+    {
+      "epoch": 0.41160949868073876,
+      "grad_norm": 1.5957881212234497,
+      "learning_rate": 6.977459817871147e-06,
+      "loss": 1.0864,
+      "step": 13
+    },
+    {
+      "epoch": 0.44327176781002636,
+      "grad_norm": 1.3141591548919678,
+      "learning_rate": 6.959962049571609e-06,
+      "loss": 1.0507,
+      "step": 14
+    },
+    {
+      "epoch": 0.47493403693931396,
+      "grad_norm": 1.0635184049606323,
+      "learning_rate": 6.937507918964709e-06,
+      "loss": 1.0483,
+      "step": 15
+    },
+    {
+      "epoch": 0.5065963060686016,
+      "grad_norm": 0.8129880428314209,
+      "learning_rate": 6.9101295913762465e-06,
+      "loss": 1.0232,
+      "step": 16
+    },
+    {
+      "epoch": 0.5382585751978892,
+      "grad_norm": 1.096314549446106,
+      "learning_rate": 6.877866285996766e-06,
+      "loss": 1.0304,
+      "step": 17
+    },
+    {
+      "epoch": 0.5699208443271768,
+      "grad_norm": 0.8672236204147339,
+      "learning_rate": 6.840764219700443e-06,
+      "loss": 1.0308,
+      "step": 18
+    },
+    {
+      "epoch": 0.6015831134564644,
+      "grad_norm": 0.9555258750915527,
+      "learning_rate": 6.798876540839855e-06,
+      "loss": 1.0285,
+      "step": 19
+    },
+    {
+      "epoch": 0.633245382585752,
+      "grad_norm": 1.5928786993026733,
+      "learning_rate": 6.752263253111479e-06,
+      "loss": 1.0189,
+      "step": 20
+    },
+    {
+      "epoch": 0.6649076517150396,
+      "grad_norm": 1.2837454080581665,
+      "learning_rate": 6.700991129600976e-06,
+      "loss": 1.021,
+      "step": 21
+    },
+    {
+      "epoch": 0.6965699208443272,
+      "grad_norm": 0.7489935755729675,
+      "learning_rate": 6.645133617131388e-06,
+      "loss": 1.0013,
+      "step": 22
+    },
+    {
+      "epoch": 0.7282321899736148,
+      "grad_norm": 0.729206383228302,
+      "learning_rate": 6.584770731051271e-06,
+      "loss": 0.986,
+      "step": 23
+    },
+    {
+      "epoch": 0.7598944591029023,
+      "grad_norm": 0.8594318628311157,
+      "learning_rate": 6.51998894061348e-06,
+      "loss": 0.9853,
+      "step": 24
+    },
+    {
+      "epoch": 0.7915567282321899,
+      "grad_norm": 0.6937134861946106,
+      "learning_rate": 6.4508810451087956e-06,
+      "loss": 0.9969,
+      "step": 25
+    },
+    {
+      "epoch": 0.8232189973614775,
+      "grad_norm": 0.6618143916130066,
+      "learning_rate": 6.377546040931835e-06,
+      "loss": 0.9784,
+      "step": 26
+    },
+    {
+      "epoch": 0.8548812664907651,
+      "grad_norm": 0.7150548100471497,
+      "learning_rate": 6.300088979769671e-06,
+      "loss": 0.9775,
+      "step": 27
+    },
+    {
+      "epoch": 0.8865435356200527,
+      "grad_norm": 0.8135938048362732,
+      "learning_rate": 6.218620818116299e-06,
+      "loss": 0.9555,
+      "step": 28
+    },
+    {
+      "epoch": 0.9182058047493403,
+      "grad_norm": 0.7386907339096069,
+      "learning_rate": 6.133258258328535e-06,
+      "loss": 0.9536,
+      "step": 29
+    },
+    {
+      "epoch": 0.9498680738786279,
+      "grad_norm": 0.6299906969070435,
+      "learning_rate": 6.044123581451003e-06,
+      "loss": 0.9513,
+      "step": 30
+    },
+    {
+      "epoch": 0.9815303430079155,
+      "grad_norm": 0.6849163174629211,
+      "learning_rate": 5.951344472049728e-06,
+      "loss": 0.9491,
+      "step": 31
+    },
+    {
+      "epoch": 1.0316622691292876,
+      "grad_norm": 0.5353211760520935,
+      "learning_rate": 5.855053835305216e-06,
+      "loss": 1.2099,
+      "step": 32
+    },
+    {
+      "epoch": 1.0633245382585752,
+      "grad_norm": 0.5629773736000061,
+      "learning_rate": 5.755389606627069e-06,
+      "loss": 0.8727,
+      "step": 33
+    },
+    {
+      "epoch": 1.0949868073878628,
+      "grad_norm": 0.5262039303779602,
+      "learning_rate": 5.652494554062838e-06,
+      "loss": 0.8777,
+      "step": 34
+    },
+    {
+      "epoch": 1.1266490765171504,
+      "grad_norm": 0.9279022216796875,
+      "learning_rate": 5.546516073784165e-06,
+      "loss": 0.8661,
+      "step": 35
+    },
+    {
+      "epoch": 1.158311345646438,
+      "grad_norm": 1.0550135374069214,
+      "learning_rate": 5.4376059789431955e-06,
+      "loss": 0.8665,
+      "step": 36
+    },
+    {
+      "epoch": 1.1899736147757256,
+      "grad_norm": 0.4825997054576874,
+      "learning_rate": 5.325920282201696e-06,
+      "loss": 0.8584,
+      "step": 37
+    },
+    {
+      "epoch": 1.2216358839050132,
+      "grad_norm": 0.5052205920219421,
+      "learning_rate": 5.2116189722444164e-06,
+      "loss": 0.8677,
+      "step": 38
+    },
+    {
+      "epoch": 1.2532981530343008,
+      "grad_norm": 0.4654822051525116,
+      "learning_rate": 5.094865784596845e-06,
+      "loss": 0.8515,
+      "step": 39
+    },
+    {
+      "epoch": 1.2849604221635884,
+      "grad_norm": 0.45359933376312256,
+      "learning_rate": 4.975827967075644e-06,
+      "loss": 0.851,
+      "step": 40
+    },
+    {
+      "epoch": 1.316622691292876,
+      "grad_norm": 0.968210756778717,
+      "learning_rate": 4.854676040207761e-06,
+      "loss": 0.8733,
+      "step": 41
+    },
+    {
+      "epoch": 1.3482849604221636,
+      "grad_norm": 0.5169340372085571,
+      "learning_rate": 4.731583552961416e-06,
+      "loss": 0.8698,
+      "step": 42
+    },
+    {
+      "epoch": 1.3799472295514512,
+      "grad_norm": 0.8193064332008362,
+      "learning_rate": 4.606726834138884e-06,
+      "loss": 0.8464,
+      "step": 43
+    },
+    {
+      "epoch": 1.4116094986807388,
+      "grad_norm": 0.589012622833252,
+      "learning_rate": 4.480284739787175e-06,
+      "loss": 0.8465,
+      "step": 44
+    },
+    {
+      "epoch": 1.4432717678100264,
+      "grad_norm": 0.5069411993026733,
+      "learning_rate": 4.352438396988471e-06,
+      "loss": 0.8415,
+      "step": 45
+    },
+    {
+      "epoch": 1.474934036939314,
+      "grad_norm": 0.4803805947303772,
+      "learning_rate": 4.223370944397335e-06,
+      "loss": 0.8089,
+      "step": 46
+    },
+    {
+      "epoch": 1.5065963060686016,
+      "grad_norm": 0.44742244482040405,
+      "learning_rate": 4.093267269896339e-06,
+      "loss": 0.8141,
+      "step": 47
+    },
+    {
+      "epoch": 1.5382585751978892,
+      "grad_norm": 0.5128947496414185,
+      "learning_rate": 3.9623137457459586e-06,
+      "loss": 0.8334,
+      "step": 48
+    },
+    {
+      "epoch": 1.5699208443271768,
+      "grad_norm": 0.43568509817123413,
+      "learning_rate": 3.83069796160811e-06,
+      "loss": 0.7996,
+      "step": 49
+    },
+    {
+      "epoch": 1.6015831134564644,
+      "grad_norm": 0.5734230279922485,
+      "learning_rate": 3.6986084558257596e-06,
+      "loss": 0.8206,
+      "step": 50
+    },
+    {
+      "epoch": 1.633245382585752,
+      "grad_norm": 0.4465356469154358,
+      "learning_rate": 3.5662344453435665e-06,
+      "loss": 0.8036,
+      "step": 51
+    },
+    {
+      "epoch": 1.6649076517150396,
+      "grad_norm": 0.9534016251564026,
+      "learning_rate": 3.4337655546564343e-06,
+      "loss": 0.849,
+      "step": 52
+    },
+    {
+      "epoch": 1.6965699208443272,
+      "grad_norm": 0.5999336838722229,
+      "learning_rate": 3.301391544174241e-06,
+      "loss": 0.7874,
+      "step": 53
+    },
+    {
+      "epoch": 1.7282321899736148,
+      "grad_norm": 0.4919511079788208,
+      "learning_rate": 3.1693020383918907e-06,
+      "loss": 0.8012,
+      "step": 54
+    },
+    {
+      "epoch": 1.7598944591029024,
+      "grad_norm": 0.4128033518791199,
+      "learning_rate": 3.0376862542540426e-06,
+      "loss": 0.8056,
+      "step": 55
+    },
+    {
+      "epoch": 1.79155672823219,
+      "grad_norm": 0.4979248642921448,
+      "learning_rate": 2.9067327301036616e-06,
+      "loss": 0.7769,
+      "step": 56
+    },
+    {
+      "epoch": 1.8232189973614776,
+      "grad_norm": 0.46139153838157654,
+      "learning_rate": 2.7766290556026646e-06,
+      "loss": 0.7984,
+      "step": 57
+    },
+    {
+      "epoch": 1.8548812664907652,
+      "grad_norm": 0.46961304545402527,
+      "learning_rate": 2.6475616030115286e-06,
+      "loss": 0.7917,
+      "step": 58
+    },
+    {
+      "epoch": 1.8865435356200528,
+      "grad_norm": 0.4321727752685547,
+      "learning_rate": 2.5197152602128256e-06,
+      "loss": 0.7852,
+      "step": 59
+    },
+    {
+      "epoch": 1.9182058047493404,
+      "grad_norm": 0.4466552138328552,
+      "learning_rate": 2.393273165861116e-06,
+      "loss": 0.8023,
+      "step": 60
+    },
+    {
+      "epoch": 1.949868073878628,
+      "grad_norm": 0.4448838233947754,
+      "learning_rate": 2.2684164470385843e-06,
+      "loss": 0.7616,
+      "step": 61
+    },
+    {
+      "epoch": 1.9815303430079156,
+      "grad_norm": 0.434826523065567,
+      "learning_rate": 2.14532395979224e-06,
+      "loss": 0.8165,
+      "step": 62
+    },
+    {
+      "epoch": 2.0316622691292876,
+      "grad_norm": 0.6250742673873901,
+      "learning_rate": 2.0241720329243563e-06,
+      "loss": 1.0035,
+      "step": 63
+    },
+    {
+      "epoch": 2.063324538258575,
+      "grad_norm": 0.41192013025283813,
+      "learning_rate": 1.905134215403155e-06,
+      "loss": 0.7532,
+      "step": 64
+    },
+    {
+      "epoch": 2.094986807387863,
+      "grad_norm": 0.4167821407318115,
+      "learning_rate": 1.7883810277555837e-06,
+      "loss": 0.7628,
+      "step": 65
+    },
+    {
+      "epoch": 2.1266490765171504,
+      "grad_norm": 0.4210691452026367,
+      "learning_rate": 1.6740797177983044e-06,
+      "loss": 0.7511,
+      "step": 66
+    },
+    {
+      "epoch": 2.158311345646438,
+      "grad_norm": 0.44451218843460083,
+      "learning_rate": 1.5623940210568042e-06,
+      "loss": 0.7302,
+      "step": 67
+    },
+    {
+      "epoch": 2.1899736147757256,
+      "grad_norm": 0.40137404203414917,
+      "learning_rate": 1.453483926215835e-06,
+      "loss": 0.7315,
+      "step": 68
+    },
+    {
+      "epoch": 2.221635883905013,
+      "grad_norm": 0.6961039900779724,
+      "learning_rate": 1.3475054459371625e-06,
+      "loss": 0.7478,
+      "step": 69
+    },
+    {
+      "epoch": 2.253298153034301,
+      "grad_norm": 0.37633243203163147,
+      "learning_rate": 1.2446103933729302e-06,
+      "loss": 0.7288,
+      "step": 70
+    },
+    {
+      "epoch": 2.2849604221635884,
+      "grad_norm": 0.43067774176597595,
+      "learning_rate": 1.1449461646947839e-06,
+      "loss": 0.7628,
+      "step": 71
+    },
+    {
+      "epoch": 2.316622691292876,
+      "grad_norm": 0.3962654769420624,
+      "learning_rate": 1.048655527950273e-06,
+      "loss": 0.7178,
+      "step": 72
+    },
+    {
+      "epoch": 2.3482849604221636,
+      "grad_norm": 0.9008962512016296,
+      "learning_rate": 9.558764185489968e-07,
+      "loss": 0.7287,
+      "step": 73
+    },
+    {
+      "epoch": 2.379947229551451,
+      "grad_norm": 0.4029214084148407,
+      "learning_rate": 8.667417416714656e-07,
+      "loss": 0.7135,
+      "step": 74
+    },
+    {
+      "epoch": 2.411609498680739,
+      "grad_norm": 0.37933027744293213,
+      "learning_rate": 7.813791818837012e-07,
+      "loss": 0.7242,
+      "step": 75
+    },
+    {
+      "epoch": 2.4432717678100264,
+      "grad_norm": 0.4242548644542694,
+      "learning_rate": 6.999110202303293e-07,
+      "loss": 0.7201,
+      "step": 76
+    },
+    {
+      "epoch": 2.474934036939314,
+      "grad_norm": 0.5838273167610168,
+      "learning_rate": 6.22453959068165e-07,
+      "loss": 0.6838,
+      "step": 77
+    },
+    {
+      "epoch": 2.5065963060686016,
+      "grad_norm": 0.3837423026561737,
+      "learning_rate": 5.491189548912051e-07,
+      "loss": 0.717,
+      "step": 78
+    },
+    {
+      "epoch": 2.538258575197889,
+      "grad_norm": 1.0475167036056519,
+      "learning_rate": 4.800110593865199e-07,
+      "loss": 0.7152,
+      "step": 79
+    },
+    {
+      "epoch": 2.569920844327177,
+      "grad_norm": 0.4407210946083069,
+      "learning_rate": 4.15229268948729e-07,
+      "loss": 0.7368,
+      "step": 80
+    },
+    {
+      "epoch": 2.6015831134564644,
+      "grad_norm": 0.39730748534202576,
+      "learning_rate": 3.5486638286861297e-07,
+      "loss": 0.715,
+      "step": 81
+    },
+    {
+      "epoch": 2.633245382585752,
+      "grad_norm": 0.5303342938423157,
+      "learning_rate": 2.990088703990245e-07,
+      "loss": 0.74,
+      "step": 82
+    },
+    {
+      "epoch": 2.6649076517150396,
+      "grad_norm": 0.6698248386383057,
+      "learning_rate": 2.4773674688852197e-07,
+      "loss": 0.7142,
+      "step": 83
+    },
+    {
+      "epoch": 2.6965699208443272,
+      "grad_norm": 0.43907734751701355,
+      "learning_rate": 2.0112345916014578e-07,
+      "loss": 0.7372,
+      "step": 84
+    },
+    {
+      "epoch": 2.728232189973615,
+      "grad_norm": 0.37293171882629395,
+      "learning_rate": 1.592357802995572e-07,
+      "loss": 0.7241,
+      "step": 85
+    },
+    {
+      "epoch": 2.7598944591029024,
+      "grad_norm": 0.394404798746109,
+      "learning_rate": 1.2213371400323352e-07,
+      "loss": 0.7095,
+      "step": 86
+    },
+    {
+      "epoch": 2.79155672823219,
+      "grad_norm": 0.7737839818000793,
+      "learning_rate": 8.987040862375339e-08,
+      "loss": 0.6919,
+      "step": 87
+    },
+    {
+      "epoch": 2.8232189973614776,
+      "grad_norm": 0.3485806882381439,
+      "learning_rate": 6.249208103529092e-08,
+      "loss": 0.7263,
+      "step": 88
+    },
+    {
+      "epoch": 2.8548812664907652,
+      "grad_norm": 0.39798641204833984,
+      "learning_rate": 4.0037950428390144e-08,
+      "loss": 0.7415,
+      "step": 89
+    },
+    {
+      "epoch": 2.886543535620053,
+      "grad_norm": 0.38925713300704956,
+      "learning_rate": 2.254018212885278e-08,
+      "loss": 0.7267,
+      "step": 90
+    },
+    {
+      "epoch": 2.9182058047493404,
+      "grad_norm": 0.361558198928833,
+      "learning_rate": 1.0023841521217825e-08,
+      "loss": 0.7175,
+      "step": 91
+    },
+    {
+      "epoch": 2.949868073878628,
+      "grad_norm": 0.5748413801193237,
+      "learning_rate": 2.506858142839852e-09,
+      "loss": 0.7126,
+      "step": 92
+    },
+    {
+      "epoch": 2.9815303430079156,
+      "grad_norm": 0.3813362717628479,
+      "learning_rate": 0.0,
+      "loss": 0.7082,
+      "step": 93
+    },
+    {
+      "epoch": 2.9815303430079156,
+      "step": 93,
+      "total_flos": 2930651586101248.0,
+      "train_loss": 0.8763364265041966,
+      "train_runtime": 71308.8652,
+      "train_samples_per_second": 0.382,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 93,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2930651586101248.0,
+  "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:ef6081d863ee9dbc07d754037e5cf347c3948eba3092972d4a5dcf75356c1247
+size 7800