Upload folder using huggingface_hub

.gitattributes

@@ -55,3 +55,4 @@ llama3-ob-plan-120-ckt-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 llama3-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3-gob-plan-122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2-gob-plan122-2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen2-gob-plan122-2epoch/README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2-gob-plan122-2epoch
+  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. -->
+
+# qwen2-gob-plan122-2epoch
+
+This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct) on the gob-plan-122 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1822
+
+## 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: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.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
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0604        | 2.2321 | 500  | 0.1822          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

qwen2-gob-plan122-2epoch/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
+}

qwen2-gob-plan122-2epoch/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1822352409362793,
+    "eval_runtime": 90.7507,
+    "eval_samples_per_second": 4.165,
+    "eval_steps_per_second": 0.529,
+    "total_flos": 264472544673792.0,
+    "train_loss": 0.197344400354528,
+    "train_runtime": 23654.7664,
+    "train_samples_per_second": 0.909,
+    "train_steps_per_second": 0.028
+}

qwen2-gob-plan122-2epoch/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2-gob-plan122-2epoch/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2-gob-plan122-2epoch/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1822352409362793,
+    "eval_runtime": 90.7507,
+    "eval_samples_per_second": 4.165,
+    "eval_steps_per_second": 0.529
+}

qwen2-gob-plan122-2epoch/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "4.57.1"
+}

qwen2-gob-plan122-2epoch/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3745fa5eb579ecdc4d52dccd50d16bd350b4f6d610016ad4a2f498381ab8be89
+size 4877660776

qwen2-gob-plan122-2epoch/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519e3cac3b3b89f3d75ce60e6c9683e3ed09fd51a93dda38ad59b0d3d3bf5b1f
+size 4932751008

qwen2-gob-plan122-2epoch/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cceb2e0cd1cb13237c2cea6e38cfa143fafe5c0093cfcbd093f7fa1a12208310
+size 4330865200

qwen2-gob-plan122-2epoch/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f280ef0cc2be163f7540bcc69b19a9ea104101b404d5d67afab66be296b5df
+size 1089994880

qwen2-gob-plan122-2epoch/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "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"
+  }
+}

qwen2-gob-plan122-2epoch/runs/Jan22_18-52-35_hgx003/events.out.tfevents.1769079305.hgx003.2819414.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a8bfcdfcbdcf774236388b4a1910007eb75e6b3f8b512b092fe154666839de
+size 20946

qwen2-gob-plan122-2epoch/runs/Jan22_18-52-35_hgx003/events.out.tfevents.1769103077.hgx003.2819414.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540577c45f04032aab33c0d509c31d55131c37269a49b816578d626f23edb878
+size 359

qwen2-gob-plan122-2epoch/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
+  }
+}

qwen2-gob-plan122-2epoch/tokenizer.json

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

qwen2-gob-plan122-2epoch/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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2-gob-plan122-2epoch/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 264472544673792.0,
+    "train_loss": 0.197344400354528,
+    "train_runtime": 23654.7664,
+    "train_samples_per_second": 0.909,
+    "train_steps_per_second": 0.028
+}

qwen2-gob-plan122-2epoch/trainer_log.jsonl

@@ -0,0 +1,69 @@
+{"current_steps": 10, "total_steps": 672, "loss": 2.216, "lr": 1.323529411764706e-06, "epoch": 0.044642857142857144, "percentage": 1.49, "elapsed_time": "0:05:36", "remaining_time": "6:11:24"}
+{"current_steps": 20, "total_steps": 672, "loss": 0.9775, "lr": 2.7941176470588237e-06, "epoch": 0.08928571428571429, "percentage": 2.98, "elapsed_time": "0:11:22", "remaining_time": "6:10:58"}
+{"current_steps": 30, "total_steps": 672, "loss": 0.4809, "lr": 4.264705882352942e-06, "epoch": 0.13392857142857142, "percentage": 4.46, "elapsed_time": "0:17:05", "remaining_time": "6:05:46"}
+{"current_steps": 40, "total_steps": 672, "loss": 0.3737, "lr": 5.735294117647059e-06, "epoch": 0.17857142857142858, "percentage": 5.95, "elapsed_time": "0:22:44", "remaining_time": "5:59:17"}
+{"current_steps": 50, "total_steps": 672, "loss": 0.3288, "lr": 7.205882352941177e-06, "epoch": 0.22321428571428573, "percentage": 7.44, "elapsed_time": "0:28:37", "remaining_time": "5:56:05"}
+{"current_steps": 60, "total_steps": 672, "loss": 0.3049, "lr": 8.676470588235295e-06, "epoch": 0.26785714285714285, "percentage": 8.93, "elapsed_time": "0:34:12", "remaining_time": "5:48:57"}
+{"current_steps": 70, "total_steps": 672, "loss": 0.2994, "lr": 9.999932366027326e-06, "epoch": 0.3125, "percentage": 10.42, "elapsed_time": "0:40:28", "remaining_time": "5:48:01"}
+{"current_steps": 80, "total_steps": 672, "loss": 0.2913, "lr": 9.991818503060027e-06, "epoch": 0.35714285714285715, "percentage": 11.9, "elapsed_time": "0:46:11", "remaining_time": "5:41:50"}
+{"current_steps": 90, "total_steps": 672, "loss": 0.2885, "lr": 9.970202993315836e-06, "epoch": 0.4017857142857143, "percentage": 13.39, "elapsed_time": "0:51:42", "remaining_time": "5:34:24"}
+{"current_steps": 100, "total_steps": 672, "loss": 0.2785, "lr": 9.93514430145593e-06, "epoch": 0.44642857142857145, "percentage": 14.88, "elapsed_time": "0:57:35", "remaining_time": "5:29:27"}
+{"current_steps": 110, "total_steps": 672, "loss": 0.2593, "lr": 9.886737252657483e-06, "epoch": 0.49107142857142855, "percentage": 16.37, "elapsed_time": "1:03:30", "remaining_time": "5:24:28"}
+{"current_steps": 120, "total_steps": 672, "loss": 0.2811, "lr": 9.825112776134763e-06, "epoch": 0.5357142857142857, "percentage": 17.86, "elapsed_time": "1:08:53", "remaining_time": "5:16:56"}
+{"current_steps": 130, "total_steps": 672, "loss": 0.2574, "lr": 9.750437551007677e-06, "epoch": 0.5803571428571429, "percentage": 19.35, "elapsed_time": "1:14:43", "remaining_time": "5:11:31"}
+{"current_steps": 140, "total_steps": 672, "loss": 0.2595, "lr": 9.66291355547556e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "1:20:35", "remaining_time": "5:06:13"}
+{"current_steps": 150, "total_steps": 672, "loss": 0.2644, "lr": 9.562777520515598e-06, "epoch": 0.6696428571428571, "percentage": 22.32, "elapsed_time": "1:26:27", "remaining_time": "5:00:53"}
+{"current_steps": 160, "total_steps": 672, "loss": 0.2437, "lr": 9.450300289583507e-06, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "1:32:08", "remaining_time": "4:54:51"}
+{"current_steps": 170, "total_steps": 672, "loss": 0.2401, "lr": 9.3257860860483e-06, "epoch": 0.7589285714285714, "percentage": 25.3, "elapsed_time": "1:37:53", "remaining_time": "4:49:03"}
+{"current_steps": 180, "total_steps": 672, "loss": 0.2442, "lr": 9.189571690342555e-06, "epoch": 0.8035714285714286, "percentage": 26.79, "elapsed_time": "1:43:29", "remaining_time": "4:42:51"}
+{"current_steps": 190, "total_steps": 672, "loss": 0.227, "lr": 9.042025529053825e-06, "epoch": 0.8482142857142857, "percentage": 28.27, "elapsed_time": "1:48:53", "remaining_time": "4:36:13"}
+{"current_steps": 200, "total_steps": 672, "loss": 0.2362, "lr": 8.883546678420918e-06, "epoch": 0.8928571428571429, "percentage": 29.76, "elapsed_time": "1:54:18", "remaining_time": "4:29:45"}
+{"current_steps": 210, "total_steps": 672, "loss": 0.2666, "lr": 8.714563784930384e-06, "epoch": 0.9375, "percentage": 31.25, "elapsed_time": "2:00:01", "remaining_time": "4:24:04"}
+{"current_steps": 220, "total_steps": 672, "loss": 0.2146, "lr": 8.535533905932739e-06, "epoch": 0.9821428571428571, "percentage": 32.74, "elapsed_time": "2:05:44", "remaining_time": "4:18:19"}
+{"current_steps": 230, "total_steps": 672, "loss": 0.1899, "lr": 8.346941273414231e-06, "epoch": 1.0267857142857142, "percentage": 34.23, "elapsed_time": "2:11:12", "remaining_time": "4:12:08"}
+{"current_steps": 240, "total_steps": 672, "loss": 0.1549, "lr": 8.149295984267892e-06, "epoch": 1.0714285714285714, "percentage": 35.71, "elapsed_time": "2:16:48", "remaining_time": "4:06:14"}
+{"current_steps": 250, "total_steps": 672, "loss": 0.1555, "lr": 7.943132620606342e-06, "epoch": 1.1160714285714286, "percentage": 37.2, "elapsed_time": "2:22:32", "remaining_time": "4:00:36"}
+{"current_steps": 260, "total_steps": 672, "loss": 0.1761, "lr": 7.729008803848062e-06, "epoch": 1.1607142857142858, "percentage": 38.69, "elapsed_time": "2:28:07", "remaining_time": "3:54:43"}
+{"current_steps": 270, "total_steps": 672, "loss": 0.1516, "lr": 7.507503686488007e-06, "epoch": 1.2053571428571428, "percentage": 40.18, "elapsed_time": "2:33:47", "remaining_time": "3:48:58"}
+{"current_steps": 280, "total_steps": 672, "loss": 0.1503, "lr": 7.279216385631903e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "2:39:32", "remaining_time": "3:43:21"}
+{"current_steps": 290, "total_steps": 672, "loss": 0.1458, "lr": 7.044764362531181e-06, "epoch": 1.2946428571428572, "percentage": 43.15, "elapsed_time": "2:45:07", "remaining_time": "3:37:30"}
+{"current_steps": 300, "total_steps": 672, "loss": 0.1397, "lr": 6.804781752501474e-06, "epoch": 1.3392857142857144, "percentage": 44.64, "elapsed_time": "2:50:39", "remaining_time": "3:31:36"}
+{"current_steps": 310, "total_steps": 672, "loss": 0.1363, "lr": 6.559917649741869e-06, "epoch": 1.3839285714285714, "percentage": 46.13, "elapsed_time": "2:56:41", "remaining_time": "3:26:20"}
+{"current_steps": 320, "total_steps": 672, "loss": 0.1388, "lr": 6.310834351694023e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "3:02:13", "remaining_time": "3:20:26"}
+{"current_steps": 330, "total_steps": 672, "loss": 0.1435, "lr": 6.058205567689759e-06, "epoch": 1.4732142857142856, "percentage": 49.11, "elapsed_time": "3:08:15", "remaining_time": "3:15:05"}
+{"current_steps": 340, "total_steps": 672, "loss": 0.1364, "lr": 5.8027145967322764e-06, "epoch": 1.5178571428571428, "percentage": 50.6, "elapsed_time": "3:14:02", "remaining_time": "3:09:28"}
+{"current_steps": 350, "total_steps": 672, "loss": 0.1354, "lr": 5.545052479339662e-06, "epoch": 1.5625, "percentage": 52.08, "elapsed_time": "3:19:48", "remaining_time": "3:03:49"}
+{"current_steps": 360, "total_steps": 672, "loss": 0.1272, "lr": 5.2859161284494955e-06, "epoch": 1.6071428571428572, "percentage": 53.57, "elapsed_time": "3:25:24", "remaining_time": "2:58:01"}
+{"current_steps": 370, "total_steps": 672, "loss": 0.1257, "lr": 5.026006444439991e-06, "epoch": 1.6517857142857144, "percentage": 55.06, "elapsed_time": "3:31:15", "remaining_time": "2:52:26"}
+{"current_steps": 380, "total_steps": 672, "loss": 0.1283, "lr": 4.766026419366095e-06, "epoch": 1.6964285714285714, "percentage": 56.55, "elapsed_time": "3:37:13", "remaining_time": "2:46:55"}
+{"current_steps": 390, "total_steps": 672, "loss": 0.1306, "lr": 4.506679235538113e-06, "epoch": 1.7410714285714286, "percentage": 58.04, "elapsed_time": "3:42:47", "remaining_time": "2:41:05"}
+{"current_steps": 400, "total_steps": 672, "loss": 0.1259, "lr": 4.248666363585729e-06, "epoch": 1.7857142857142856, "percentage": 59.52, "elapsed_time": "3:48:38", "remaining_time": "2:35:28"}
+{"current_steps": 410, "total_steps": 672, "loss": 0.1286, "lr": 3.992685665151723e-06, "epoch": 1.8303571428571428, "percentage": 61.01, "elapsed_time": "3:54:21", "remaining_time": "2:29:45"}
+{"current_steps": 420, "total_steps": 672, "loss": 0.121, "lr": 3.7394295053470937e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "3:59:56", "remaining_time": "2:23:58"}
+{"current_steps": 430, "total_steps": 672, "loss": 0.1168, "lr": 3.489582880072967e-06, "epoch": 1.9196428571428572, "percentage": 63.99, "elapsed_time": "4:05:33", "remaining_time": "2:18:11"}
+{"current_steps": 440, "total_steps": 672, "loss": 0.1212, "lr": 3.2438215632744054e-06, "epoch": 1.9642857142857144, "percentage": 65.48, "elapsed_time": "4:11:18", "remaining_time": "2:12:30"}
+{"current_steps": 450, "total_steps": 672, "loss": 0.1043, "lr": 3.0028102791373536e-06, "epoch": 2.0089285714285716, "percentage": 66.96, "elapsed_time": "4:17:08", "remaining_time": "2:06:51"}
+{"current_steps": 460, "total_steps": 672, "loss": 0.0588, "lr": 2.7672009041724807e-06, "epoch": 2.0535714285714284, "percentage": 68.45, "elapsed_time": "4:22:59", "remaining_time": "2:01:12"}
+{"current_steps": 470, "total_steps": 672, "loss": 0.0622, "lr": 2.5376307040488324e-06, "epoch": 2.0982142857142856, "percentage": 69.94, "elapsed_time": "4:28:29", "remaining_time": "1:55:23"}
+{"current_steps": 480, "total_steps": 672, "loss": 0.0579, "lr": 2.3147206099462313e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "4:34:13", "remaining_time": "1:49:41"}
+{"current_steps": 490, "total_steps": 672, "loss": 0.0607, "lr": 2.0990735390884787e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "4:39:54", "remaining_time": "1:43:57"}
+{"current_steps": 500, "total_steps": 672, "loss": 0.0604, "lr": 1.891272763999884e-06, "epoch": 2.232142857142857, "percentage": 74.4, "elapsed_time": "4:45:34", "remaining_time": "1:38:14"}
+{"current_steps": 500, "total_steps": 672, "eval_loss": 0.1822352409362793, "epoch": 2.232142857142857, "percentage": 74.4, "elapsed_time": "4:47:06", "remaining_time": "1:38:45"}
+{"current_steps": 510, "total_steps": 672, "loss": 0.0578, "lr": 1.691880334895919e-06, "epoch": 2.2767857142857144, "percentage": 75.89, "elapsed_time": "4:53:46", "remaining_time": "1:33:18"}
+{"current_steps": 520, "total_steps": 672, "loss": 0.0567, "lr": 1.5014355594749859e-06, "epoch": 2.3214285714285716, "percentage": 77.38, "elapsed_time": "4:59:30", "remaining_time": "1:27:32"}
+{"current_steps": 530, "total_steps": 672, "loss": 0.0623, "lr": 1.3204535442231614e-06, "epoch": 2.3660714285714284, "percentage": 78.87, "elapsed_time": "5:05:06", "remaining_time": "1:21:44"}
+{"current_steps": 540, "total_steps": 672, "loss": 0.0521, "lr": 1.1494238011772724e-06, "epoch": 2.4107142857142856, "percentage": 80.36, "elapsed_time": "5:10:51", "remaining_time": "1:15:59"}
+{"current_steps": 550, "total_steps": 672, "loss": 0.0572, "lr": 9.888089239146963e-07, "epoch": 2.455357142857143, "percentage": 81.85, "elapsed_time": "5:16:40", "remaining_time": "1:10:14"}
+{"current_steps": 560, "total_steps": 672, "loss": 0.0548, "lr": 8.390433363510037e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "5:22:25", "remaining_time": "1:04:29"}
+{"current_steps": 570, "total_steps": 672, "loss": 0.0515, "lr": 7.005321177296349e-07, "epoch": 2.544642857142857, "percentage": 84.82, "elapsed_time": "5:28:13", "remaining_time": "0:58:44"}
+{"current_steps": 580, "total_steps": 672, "loss": 0.0531, "lr": 5.736499069817364e-07, "epoch": 2.5892857142857144, "percentage": 86.31, "elapsed_time": "5:33:46", "remaining_time": "0:52:56"}
+{"current_steps": 590, "total_steps": 672, "loss": 0.0523, "lr": 4.587398894195838e-07, "epoch": 2.633928571428571, "percentage": 87.8, "elapsed_time": "5:39:17", "remaining_time": "0:47:09"}
+{"current_steps": 600, "total_steps": 672, "loss": 0.0557, "lr": 3.561128685043397e-07, "epoch": 2.678571428571429, "percentage": 89.29, "elapsed_time": "5:45:08", "remaining_time": "0:41:25"}
+{"current_steps": 610, "total_steps": 672, "loss": 0.0488, "lr": 2.6604642519879766e-07, "epoch": 2.7232142857142856, "percentage": 90.77, "elapsed_time": "5:50:56", "remaining_time": "0:35:40"}
+{"current_steps": 620, "total_steps": 672, "loss": 0.0532, "lr": 1.887841671788382e-07, "epoch": 2.767857142857143, "percentage": 92.26, "elapsed_time": "5:56:53", "remaining_time": "0:29:55"}
+{"current_steps": 630, "total_steps": 672, "loss": 0.054, "lr": 1.2453506993432507e-07, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "6:02:43", "remaining_time": "0:24:10"}
+{"current_steps": 640, "total_steps": 672, "loss": 0.0523, "lr": 7.347291154156222e-08, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "6:08:39", "remaining_time": "0:18:25"}
+{"current_steps": 650, "total_steps": 672, "loss": 0.0493, "lr": 3.573580263615539e-08, "epoch": 2.9017857142857144, "percentage": 96.73, "elapsed_time": "6:14:22", "remaining_time": "0:12:40"}
+{"current_steps": 660, "total_steps": 672, "loss": 0.048, "lr": 1.1425812857557838e-08, "epoch": 2.946428571428571, "percentage": 98.21, "elapsed_time": "6:20:25", "remaining_time": "0:06:55"}
+{"current_steps": 670, "total_steps": 672, "loss": 0.0768, "lr": 6.086947756872574e-10, "epoch": 2.991071428571429, "percentage": 99.7, "elapsed_time": "6:25:53", "remaining_time": "0:01:09"}
+{"current_steps": 672, "total_steps": 672, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:34:14", "remaining_time": "0:00:00"}

qwen2-gob-plan122-2epoch/trainer_state.json

@@ -0,0 +1,520 @@
+{
+  "best_global_step": 500,
+  "best_metric": 0.1822352409362793,
+  "best_model_checkpoint": "saves/qwen2-gob-plan122-2epoch/checkpoint-500",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 672,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044642857142857144,
+      "grad_norm": 30.405736923217773,
+      "learning_rate": 1.323529411764706e-06,
+      "loss": 2.216,
+      "step": 10
+    },
+    {
+      "epoch": 0.08928571428571429,
+      "grad_norm": 6.283041477203369,
+      "learning_rate": 2.7941176470588237e-06,
+      "loss": 0.9775,
+      "step": 20
+    },
+    {
+      "epoch": 0.13392857142857142,
+      "grad_norm": 3.6858878135681152,
+      "learning_rate": 4.264705882352942e-06,
+      "loss": 0.4809,
+      "step": 30
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 3.105330467224121,
+      "learning_rate": 5.735294117647059e-06,
+      "loss": 0.3737,
+      "step": 40
+    },
+    {
+      "epoch": 0.22321428571428573,
+      "grad_norm": 3.1036972999572754,
+      "learning_rate": 7.205882352941177e-06,
+      "loss": 0.3288,
+      "step": 50
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 2.7038118839263916,
+      "learning_rate": 8.676470588235295e-06,
+      "loss": 0.3049,
+      "step": 60
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 2.7672762870788574,
+      "learning_rate": 9.999932366027326e-06,
+      "loss": 0.2994,
+      "step": 70
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 2.8215863704681396,
+      "learning_rate": 9.991818503060027e-06,
+      "loss": 0.2913,
+      "step": 80
+    },
+    {
+      "epoch": 0.4017857142857143,
+      "grad_norm": 2.3533623218536377,
+      "learning_rate": 9.970202993315836e-06,
+      "loss": 0.2885,
+      "step": 90
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "grad_norm": 2.455805540084839,
+      "learning_rate": 9.93514430145593e-06,
+      "loss": 0.2785,
+      "step": 100
+    },
+    {
+      "epoch": 0.49107142857142855,
+      "grad_norm": 2.496835470199585,
+      "learning_rate": 9.886737252657483e-06,
+      "loss": 0.2593,
+      "step": 110
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 2.967664957046509,
+      "learning_rate": 9.825112776134763e-06,
+      "loss": 0.2811,
+      "step": 120
+    },
+    {
+      "epoch": 0.5803571428571429,
+      "grad_norm": 2.4558615684509277,
+      "learning_rate": 9.750437551007677e-06,
+      "loss": 0.2574,
+      "step": 130
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 2.128484010696411,
+      "learning_rate": 9.66291355547556e-06,
+      "loss": 0.2595,
+      "step": 140
+    },
+    {
+      "epoch": 0.6696428571428571,
+      "grad_norm": 2.1013526916503906,
+      "learning_rate": 9.562777520515598e-06,
+      "loss": 0.2644,
+      "step": 150
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.8684916496276855,
+      "learning_rate": 9.450300289583507e-06,
+      "loss": 0.2437,
+      "step": 160
+    },
+    {
+      "epoch": 0.7589285714285714,
+      "grad_norm": 1.9143171310424805,
+      "learning_rate": 9.3257860860483e-06,
+      "loss": 0.2401,
+      "step": 170
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "grad_norm": 2.20692777633667,
+      "learning_rate": 9.189571690342555e-06,
+      "loss": 0.2442,
+      "step": 180
+    },
+    {
+      "epoch": 0.8482142857142857,
+      "grad_norm": 2.018720865249634,
+      "learning_rate": 9.042025529053825e-06,
+      "loss": 0.227,
+      "step": 190
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 1.8927925825119019,
+      "learning_rate": 8.883546678420918e-06,
+      "loss": 0.2362,
+      "step": 200
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 2.034132480621338,
+      "learning_rate": 8.714563784930384e-06,
+      "loss": 0.2666,
+      "step": 210
+    },
+    {
+      "epoch": 0.9821428571428571,
+      "grad_norm": 1.9816973209381104,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.2146,
+      "step": 220
+    },
+    {
+      "epoch": 1.0267857142857142,
+      "grad_norm": 1.770123839378357,
+      "learning_rate": 8.346941273414231e-06,
+      "loss": 0.1899,
+      "step": 230
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 1.89414644241333,
+      "learning_rate": 8.149295984267892e-06,
+      "loss": 0.1549,
+      "step": 240
+    },
+    {
+      "epoch": 1.1160714285714286,
+      "grad_norm": 1.9606295824050903,
+      "learning_rate": 7.943132620606342e-06,
+      "loss": 0.1555,
+      "step": 250
+    },
+    {
+      "epoch": 1.1607142857142858,
+      "grad_norm": 1.8488701581954956,
+      "learning_rate": 7.729008803848062e-06,
+      "loss": 0.1761,
+      "step": 260
+    },
+    {
+      "epoch": 1.2053571428571428,
+      "grad_norm": 1.7967876195907593,
+      "learning_rate": 7.507503686488007e-06,
+      "loss": 0.1516,
+      "step": 270
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.314888000488281,
+      "learning_rate": 7.279216385631903e-06,
+      "loss": 0.1503,
+      "step": 280
+    },
+    {
+      "epoch": 1.2946428571428572,
+      "grad_norm": 1.6510639190673828,
+      "learning_rate": 7.044764362531181e-06,
+      "loss": 0.1458,
+      "step": 290
+    },
+    {
+      "epoch": 1.3392857142857144,
+      "grad_norm": 1.658790111541748,
+      "learning_rate": 6.804781752501474e-06,
+      "loss": 0.1397,
+      "step": 300
+    },
+    {
+      "epoch": 1.3839285714285714,
+      "grad_norm": 1.4212795495986938,
+      "learning_rate": 6.559917649741869e-06,
+      "loss": 0.1363,
+      "step": 310
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.4153637886047363,
+      "learning_rate": 6.310834351694023e-06,
+      "loss": 0.1388,
+      "step": 320
+    },
+    {
+      "epoch": 1.4732142857142856,
+      "grad_norm": 1.750765323638916,
+      "learning_rate": 6.058205567689759e-06,
+      "loss": 0.1435,
+      "step": 330
+    },
+    {
+      "epoch": 1.5178571428571428,
+      "grad_norm": 1.6805425882339478,
+      "learning_rate": 5.8027145967322764e-06,
+      "loss": 0.1364,
+      "step": 340
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 1.2894501686096191,
+      "learning_rate": 5.545052479339662e-06,
+      "loss": 0.1354,
+      "step": 350
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 1.6628329753875732,
+      "learning_rate": 5.2859161284494955e-06,
+      "loss": 0.1272,
+      "step": 360
+    },
+    {
+      "epoch": 1.6517857142857144,
+      "grad_norm": 1.5841708183288574,
+      "learning_rate": 5.026006444439991e-06,
+      "loss": 0.1257,
+      "step": 370
+    },
+    {
+      "epoch": 1.6964285714285714,
+      "grad_norm": 1.3237268924713135,
+      "learning_rate": 4.766026419366095e-06,
+      "loss": 0.1283,
+      "step": 380
+    },
+    {
+      "epoch": 1.7410714285714286,
+      "grad_norm": 1.4074996709823608,
+      "learning_rate": 4.506679235538113e-06,
+      "loss": 0.1306,
+      "step": 390
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 1.6902159452438354,
+      "learning_rate": 4.248666363585729e-06,
+      "loss": 0.1259,
+      "step": 400
+    },
+    {
+      "epoch": 1.8303571428571428,
+      "grad_norm": 1.5233656167984009,
+      "learning_rate": 3.992685665151723e-06,
+      "loss": 0.1286,
+      "step": 410
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.3293139934539795,
+      "learning_rate": 3.7394295053470937e-06,
+      "loss": 0.121,
+      "step": 420
+    },
+    {
+      "epoch": 1.9196428571428572,
+      "grad_norm": 1.2937629222869873,
+      "learning_rate": 3.489582880072967e-06,
+      "loss": 0.1168,
+      "step": 430
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 1.271576166152954,
+      "learning_rate": 3.2438215632744054e-06,
+      "loss": 0.1212,
+      "step": 440
+    },
+    {
+      "epoch": 2.0089285714285716,
+      "grad_norm": 1.1020175218582153,
+      "learning_rate": 3.0028102791373536e-06,
+      "loss": 0.1043,
+      "step": 450
+    },
+    {
+      "epoch": 2.0535714285714284,
+      "grad_norm": 1.1888649463653564,
+      "learning_rate": 2.7672009041724807e-06,
+      "loss": 0.0588,
+      "step": 460
+    },
+    {
+      "epoch": 2.0982142857142856,
+      "grad_norm": 1.4099218845367432,
+      "learning_rate": 2.5376307040488324e-06,
+      "loss": 0.0622,
+      "step": 470
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 1.123796820640564,
+      "learning_rate": 2.3147206099462313e-06,
+      "loss": 0.0579,
+      "step": 480
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 1.0837132930755615,
+      "learning_rate": 2.0990735390884787e-06,
+      "loss": 0.0607,
+      "step": 490
+    },
+    {
+      "epoch": 2.232142857142857,
+      "grad_norm": 1.1556771993637085,
+      "learning_rate": 1.891272763999884e-06,
+      "loss": 0.0604,
+      "step": 500
+    },
+    {
+      "epoch": 2.232142857142857,
+      "eval_loss": 0.1822352409362793,
+      "eval_runtime": 91.1926,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 0.526,
+      "step": 500
+    },
+    {
+      "epoch": 2.2767857142857144,
+      "grad_norm": 1.1324012279510498,
+      "learning_rate": 1.691880334895919e-06,
+      "loss": 0.0578,
+      "step": 510
+    },
+    {
+      "epoch": 2.3214285714285716,
+      "grad_norm": 1.1425533294677734,
+      "learning_rate": 1.5014355594749859e-06,
+      "loss": 0.0567,
+      "step": 520
+    },
+    {
+      "epoch": 2.3660714285714284,
+      "grad_norm": 1.3793491125106812,
+      "learning_rate": 1.3204535442231614e-06,
+      "loss": 0.0623,
+      "step": 530
+    },
+    {
+      "epoch": 2.4107142857142856,
+      "grad_norm": 1.0486314296722412,
+      "learning_rate": 1.1494238011772724e-06,
+      "loss": 0.0521,
+      "step": 540
+    },
+    {
+      "epoch": 2.455357142857143,
+      "grad_norm": 1.1928539276123047,
+      "learning_rate": 9.888089239146963e-07,
+      "loss": 0.0572,
+      "step": 550
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.33969247341156,
+      "learning_rate": 8.390433363510037e-07,
+      "loss": 0.0548,
+      "step": 560
+    },
+    {
+      "epoch": 2.544642857142857,
+      "grad_norm": 1.2450653314590454,
+      "learning_rate": 7.005321177296349e-07,
+      "loss": 0.0515,
+      "step": 570
+    },
+    {
+      "epoch": 2.5892857142857144,
+      "grad_norm": 1.1788525581359863,
+      "learning_rate": 5.736499069817364e-07,
+      "loss": 0.0531,
+      "step": 580
+    },
+    {
+      "epoch": 2.633928571428571,
+      "grad_norm": 1.2610106468200684,
+      "learning_rate": 4.587398894195838e-07,
+      "loss": 0.0523,
+      "step": 590
+    },
+    {
+      "epoch": 2.678571428571429,
+      "grad_norm": 1.305772066116333,
+      "learning_rate": 3.561128685043397e-07,
+      "loss": 0.0557,
+      "step": 600
+    },
+    {
+      "epoch": 2.7232142857142856,
+      "grad_norm": 1.0677855014801025,
+      "learning_rate": 2.6604642519879766e-07,
+      "loss": 0.0488,
+      "step": 610
+    },
+    {
+      "epoch": 2.767857142857143,
+      "grad_norm": 1.0048575401306152,
+      "learning_rate": 1.887841671788382e-07,
+      "loss": 0.0532,
+      "step": 620
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 1.2265655994415283,
+      "learning_rate": 1.2453506993432507e-07,
+      "loss": 0.054,
+      "step": 630
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.270810842514038,
+      "learning_rate": 7.347291154156222e-08,
+      "loss": 0.0523,
+      "step": 640
+    },
+    {
+      "epoch": 2.9017857142857144,
+      "grad_norm": 1.1928095817565918,
+      "learning_rate": 3.573580263615539e-08,
+      "loss": 0.0493,
+      "step": 650
+    },
+    {
+      "epoch": 2.946428571428571,
+      "grad_norm": 1.196356177330017,
+      "learning_rate": 1.1425812857557838e-08,
+      "loss": 0.048,
+      "step": 660
+    },
+    {
+      "epoch": 2.991071428571429,
+      "grad_norm": 1.1472580432891846,
+      "learning_rate": 6.086947756872574e-10,
+      "loss": 0.0768,
+      "step": 670
+    },
+    {
+      "epoch": 3.0,
+      "step": 672,
+      "total_flos": 264472544673792.0,
+      "train_loss": 0.197344400354528,
+      "train_runtime": 23654.7664,
+      "train_samples_per_second": 0.909,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 672,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 264472544673792.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2-gob-plan122-2epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153b349bc06c956fd77538b161455b7504b767202aa6d88f47ddb75f5eaebf66
+size 8401