Upload folder using huggingface_hub

.gitattributes

@@ -49,3 +49,4 @@ qwen2-gob-plan-115/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2-os-limit118/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2-osplan-119/checkpoint-445/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2-osplan-119/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2-gob-plan-119/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen2-gob-plan-119/README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2-gob-plan119-1epoch
+  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-plan119-1epoch
+
+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-115 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 64
+- 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: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

qwen2-gob-plan-119/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-plan-119/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 476639621545984.0,
+    "train_loss": 0.3024920547110403,
+    "train_runtime": 40928.1916,
+    "train_samples_per_second": 0.915,
+    "train_steps_per_second": 0.029
+}

qwen2-gob-plan-119/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-plan-119/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-plan-119/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-plan-119/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5da6d7ae5386ff79b365d4d14e7910054ed9df0344998278cd1ddc84e502d0
+size 4877660776

qwen2-gob-plan-119/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8e6b88970a82e03235a8d836f6d937d0026c4ef5354e67eacf29fcfba9dade
+size 4932751008

qwen2-gob-plan-119/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee613d5a53e4d8604065315a4aaffeca011848fad09bc084686fa827145a680
+size 4330865200

qwen2-gob-plan-119/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2af827312785f7211f530e7101a94c39de40fdc19b2c542347700c5e9a9903c
+size 1089994880

qwen2-gob-plan-119/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-plan-119/runs/Jan19_02-08-12_hgx003/events.out.tfevents.1768759888.hgx003.2361281.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d5e958293b31e215d3f274ce39ea4f997b062abbdccc7533c04a6fe328a3ae
+size 31220

qwen2-gob-plan-119/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-plan-119/tokenizer.json

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

qwen2-gob-plan-119/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-plan-119/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 476639621545984.0,
+    "train_loss": 0.3024920547110403,
+    "train_runtime": 40928.1916,
+    "train_samples_per_second": 0.915,
+    "train_steps_per_second": 0.029
+}

qwen2-gob-plan-119/trainer_log.jsonl

@@ -0,0 +1,118 @@
+{"current_steps": 10, "total_steps": 1170, "loss": 2.244, "lr": 7.692307692307694e-07, "epoch": 0.008547008547008548, "percentage": 0.85, "elapsed_time": "0:06:15", "remaining_time": "12:06:41"}
+{"current_steps": 20, "total_steps": 1170, "loss": 1.5517, "lr": 1.623931623931624e-06, "epoch": 0.017094017094017096, "percentage": 1.71, "elapsed_time": "0:12:02", "remaining_time": "11:32:33"}
+{"current_steps": 30, "total_steps": 1170, "loss": 0.8494, "lr": 2.478632478632479e-06, "epoch": 0.02564102564102564, "percentage": 2.56, "elapsed_time": "0:17:58", "remaining_time": "11:22:48"}
+{"current_steps": 40, "total_steps": 1170, "loss": 0.6006, "lr": 3.3333333333333333e-06, "epoch": 0.03418803418803419, "percentage": 3.42, "elapsed_time": "0:23:58", "remaining_time": "11:17:22"}
+{"current_steps": 50, "total_steps": 1170, "loss": 0.5208, "lr": 4.188034188034188e-06, "epoch": 0.042735042735042736, "percentage": 4.27, "elapsed_time": "0:29:56", "remaining_time": "11:10:46"}
+{"current_steps": 60, "total_steps": 1170, "loss": 0.5017, "lr": 5.042735042735043e-06, "epoch": 0.05128205128205128, "percentage": 5.13, "elapsed_time": "0:35:58", "remaining_time": "11:05:27"}
+{"current_steps": 70, "total_steps": 1170, "loss": 0.4581, "lr": 5.897435897435898e-06, "epoch": 0.05982905982905983, "percentage": 5.98, "elapsed_time": "0:41:52", "remaining_time": "10:57:58"}
+{"current_steps": 80, "total_steps": 1170, "loss": 0.4624, "lr": 6.752136752136753e-06, "epoch": 0.06837606837606838, "percentage": 6.84, "elapsed_time": "0:47:43", "remaining_time": "10:50:12"}
+{"current_steps": 90, "total_steps": 1170, "loss": 0.4578, "lr": 7.606837606837607e-06, "epoch": 0.07692307692307693, "percentage": 7.69, "elapsed_time": "0:53:22", "remaining_time": "10:40:27"}
+{"current_steps": 100, "total_steps": 1170, "loss": 0.44, "lr": 8.461538461538462e-06, "epoch": 0.08547008547008547, "percentage": 8.55, "elapsed_time": "0:59:15", "remaining_time": "10:34:03"}
+{"current_steps": 110, "total_steps": 1170, "loss": 0.4455, "lr": 9.316239316239318e-06, "epoch": 0.09401709401709402, "percentage": 9.4, "elapsed_time": "1:04:40", "remaining_time": "10:23:15"}
+{"current_steps": 120, "total_steps": 1170, "loss": 0.4151, "lr": 9.999910989402885e-06, "epoch": 0.10256410256410256, "percentage": 10.26, "elapsed_time": "1:10:33", "remaining_time": "10:17:22"}
+{"current_steps": 130, "total_steps": 1170, "loss": 0.4292, "lr": 9.996795951252427e-06, "epoch": 0.1111111111111111, "percentage": 11.11, "elapsed_time": "1:16:17", "remaining_time": "10:10:19"}
+{"current_steps": 140, "total_steps": 1170, "loss": 0.4081, "lr": 9.989233551893588e-06, "epoch": 0.11965811965811966, "percentage": 11.97, "elapsed_time": "1:21:57", "remaining_time": "10:02:55"}
+{"current_steps": 150, "total_steps": 1170, "loss": 0.4095, "lr": 9.977230522183876e-06, "epoch": 0.1282051282051282, "percentage": 12.82, "elapsed_time": "1:27:47", "remaining_time": "9:56:56"}
+{"current_steps": 160, "total_steps": 1170, "loss": 0.4011, "lr": 9.960797545330936e-06, "epoch": 0.13675213675213677, "percentage": 13.68, "elapsed_time": "1:33:49", "remaining_time": "9:52:15"}
+{"current_steps": 170, "total_steps": 1170, "loss": 0.4169, "lr": 9.939949247384046e-06, "epoch": 0.1452991452991453, "percentage": 14.53, "elapsed_time": "1:39:36", "remaining_time": "9:45:53"}
+{"current_steps": 180, "total_steps": 1170, "loss": 0.3819, "lr": 9.914704184216296e-06, "epoch": 0.15384615384615385, "percentage": 15.38, "elapsed_time": "1:45:17", "remaining_time": "9:39:08"}
+{"current_steps": 190, "total_steps": 1170, "loss": 0.3904, "lr": 9.885084825009085e-06, "epoch": 0.1623931623931624, "percentage": 16.24, "elapsed_time": "1:51:10", "remaining_time": "9:33:28"}
+{"current_steps": 200, "total_steps": 1170, "loss": 0.3788, "lr": 9.851117532253587e-06, "epoch": 0.17094017094017094, "percentage": 17.09, "elapsed_time": "1:56:57", "remaining_time": "9:27:14"}
+{"current_steps": 210, "total_steps": 1170, "loss": 0.372, "lr": 9.81283253828701e-06, "epoch": 0.1794871794871795, "percentage": 17.95, "elapsed_time": "2:02:29", "remaining_time": "9:19:57"}
+{"current_steps": 220, "total_steps": 1170, "loss": 0.3839, "lr": 9.770263918384523e-06, "epoch": 0.18803418803418803, "percentage": 18.8, "elapsed_time": "2:08:12", "remaining_time": "9:13:37"}
+{"current_steps": 230, "total_steps": 1170, "loss": 0.373, "lr": 9.723449560430827e-06, "epoch": 0.19658119658119658, "percentage": 19.66, "elapsed_time": "2:13:58", "remaining_time": "9:07:32"}
+{"current_steps": 240, "total_steps": 1170, "loss": 0.3671, "lr": 9.672431131198306e-06, "epoch": 0.20512820512820512, "percentage": 20.51, "elapsed_time": "2:20:02", "remaining_time": "9:02:40"}
+{"current_steps": 250, "total_steps": 1170, "loss": 0.3782, "lr": 9.617254039261835e-06, "epoch": 0.21367521367521367, "percentage": 21.37, "elapsed_time": "2:25:38", "remaining_time": "8:55:56"}
+{"current_steps": 260, "total_steps": 1170, "loss": 0.356, "lr": 9.557967394583206e-06, "epoch": 0.2222222222222222, "percentage": 22.22, "elapsed_time": "2:31:30", "remaining_time": "8:50:15"}
+{"current_steps": 270, "total_steps": 1170, "loss": 0.3297, "lr": 9.494623964801185e-06, "epoch": 0.23076923076923078, "percentage": 23.08, "elapsed_time": "2:37:25", "remaining_time": "8:44:45"}
+{"current_steps": 280, "total_steps": 1170, "loss": 0.3448, "lr": 9.427280128266049e-06, "epoch": 0.23931623931623933, "percentage": 23.93, "elapsed_time": "2:43:00", "remaining_time": "8:38:08"}
+{"current_steps": 290, "total_steps": 1170, "loss": 0.3355, "lr": 9.355995823860468e-06, "epoch": 0.24786324786324787, "percentage": 24.79, "elapsed_time": "2:48:49", "remaining_time": "8:32:16"}
+{"current_steps": 300, "total_steps": 1170, "loss": 0.3381, "lr": 9.280834497651334e-06, "epoch": 0.2564102564102564, "percentage": 25.64, "elapsed_time": "2:54:17", "remaining_time": "8:25:25"}
+{"current_steps": 310, "total_steps": 1170, "loss": 0.3401, "lr": 9.201863046420065e-06, "epoch": 0.26495726495726496, "percentage": 26.5, "elapsed_time": "3:00:03", "remaining_time": "8:19:30"}
+{"current_steps": 320, "total_steps": 1170, "loss": 0.3246, "lr": 9.119151758121627e-06, "epoch": 0.27350427350427353, "percentage": 27.35, "elapsed_time": "3:05:53", "remaining_time": "8:13:47"}
+{"current_steps": 330, "total_steps": 1170, "loss": 0.3372, "lr": 9.032774249325247e-06, "epoch": 0.28205128205128205, "percentage": 28.21, "elapsed_time": "3:11:42", "remaining_time": "8:07:59"}
+{"current_steps": 340, "total_steps": 1170, "loss": 0.3168, "lr": 8.942807399692543e-06, "epoch": 0.2905982905982906, "percentage": 29.06, "elapsed_time": "3:17:21", "remaining_time": "8:01:46"}
+{"current_steps": 350, "total_steps": 1170, "loss": 0.3281, "lr": 8.849331283551345e-06, "epoch": 0.29914529914529914, "percentage": 29.91, "elapsed_time": "3:23:22", "remaining_time": "7:56:29"}
+{"current_steps": 360, "total_steps": 1170, "loss": 0.3159, "lr": 8.752429098626132e-06, "epoch": 0.3076923076923077, "percentage": 30.77, "elapsed_time": "3:29:18", "remaining_time": "7:50:55"}
+{"current_steps": 370, "total_steps": 1170, "loss": 0.3179, "lr": 8.652187091988516e-06, "epoch": 0.3162393162393162, "percentage": 31.62, "elapsed_time": "3:35:11", "remaining_time": "7:45:16"}
+{"current_steps": 380, "total_steps": 1170, "loss": 0.3061, "lr": 8.548694483293678e-06, "epoch": 0.3247863247863248, "percentage": 32.48, "elapsed_time": "3:41:09", "remaining_time": "7:39:46"}
+{"current_steps": 390, "total_steps": 1170, "loss": 0.3079, "lr": 8.442043385371069e-06, "epoch": 0.3333333333333333, "percentage": 33.33, "elapsed_time": "3:47:07", "remaining_time": "7:34:15"}
+{"current_steps": 400, "total_steps": 1170, "loss": 0.2989, "lr": 8.332328722240072e-06, "epoch": 0.3418803418803419, "percentage": 34.19, "elapsed_time": "3:53:05", "remaining_time": "7:28:41"}
+{"current_steps": 410, "total_steps": 1170, "loss": 0.2892, "lr": 8.219648144623584e-06, "epoch": 0.3504273504273504, "percentage": 35.04, "elapsed_time": "3:59:02", "remaining_time": "7:23:06"}
+{"current_steps": 420, "total_steps": 1170, "loss": 0.3011, "lr": 8.10410194303471e-06, "epoch": 0.358974358974359, "percentage": 35.9, "elapsed_time": "4:04:54", "remaining_time": "7:17:20"}
+{"current_steps": 430, "total_steps": 1170, "loss": 0.2886, "lr": 7.985792958513932e-06, "epoch": 0.36752136752136755, "percentage": 36.75, "elapsed_time": "4:10:13", "remaining_time": "7:10:36"}
+{"current_steps": 440, "total_steps": 1170, "loss": 0.2973, "lr": 7.864826491096214e-06, "epoch": 0.37606837606837606, "percentage": 37.61, "elapsed_time": "4:16:08", "remaining_time": "7:04:58"}
+{"current_steps": 450, "total_steps": 1170, "loss": 0.2865, "lr": 7.741310206089474e-06, "epoch": 0.38461538461538464, "percentage": 38.46, "elapsed_time": "4:21:53", "remaining_time": "6:59:01"}
+{"current_steps": 460, "total_steps": 1170, "loss": 0.2721, "lr": 7.615354038247889e-06, "epoch": 0.39316239316239315, "percentage": 39.32, "elapsed_time": "4:27:42", "remaining_time": "6:53:12"}
+{"current_steps": 470, "total_steps": 1170, "loss": 0.2675, "lr": 7.48707009392526e-06, "epoch": 0.4017094017094017, "percentage": 40.17, "elapsed_time": "4:33:36", "remaining_time": "6:47:30"}
+{"current_steps": 480, "total_steps": 1170, "loss": 0.2714, "lr": 7.356572551295604e-06, "epoch": 0.41025641025641024, "percentage": 41.03, "elapsed_time": "4:39:24", "remaining_time": "6:41:39"}
+{"current_steps": 490, "total_steps": 1170, "loss": 0.2799, "lr": 7.223977558729707e-06, "epoch": 0.4188034188034188, "percentage": 41.88, "elapsed_time": "4:45:01", "remaining_time": "6:35:32"}
+{"current_steps": 500, "total_steps": 1170, "loss": 0.265, "lr": 7.089403131418126e-06, "epoch": 0.42735042735042733, "percentage": 42.74, "elapsed_time": "4:51:13", "remaining_time": "6:30:14"}
+{"current_steps": 510, "total_steps": 1170, "loss": 0.2756, "lr": 6.952969046332642e-06, "epoch": 0.4358974358974359, "percentage": 43.59, "elapsed_time": "4:57:18", "remaining_time": "6:24:44"}
+{"current_steps": 520, "total_steps": 1170, "loss": 0.4513, "lr": 6.814796735619664e-06, "epoch": 0.4444444444444444, "percentage": 44.44, "elapsed_time": "5:03:12", "remaining_time": "6:19:00"}
+{"current_steps": 530, "total_steps": 1170, "loss": 0.277, "lr": 6.675009178520435e-06, "epoch": 0.452991452991453, "percentage": 45.3, "elapsed_time": "5:09:04", "remaining_time": "6:13:13"}
+{"current_steps": 540, "total_steps": 1170, "loss": 0.2665, "lr": 6.5337307919142766e-06, "epoch": 0.46153846153846156, "percentage": 46.15, "elapsed_time": "5:14:49", "remaining_time": "6:07:17"}
+{"current_steps": 550, "total_steps": 1170, "loss": 0.2607, "lr": 6.391087319582264e-06, "epoch": 0.4700854700854701, "percentage": 47.01, "elapsed_time": "5:20:20", "remaining_time": "6:01:06"}
+{"current_steps": 560, "total_steps": 1170, "loss": 0.2548, "lr": 6.247205720289907e-06, "epoch": 0.47863247863247865, "percentage": 47.86, "elapsed_time": "5:26:17", "remaining_time": "5:55:25"}
+{"current_steps": 570, "total_steps": 1170, "loss": 0.2603, "lr": 6.102214054788444e-06, "epoch": 0.48717948717948717, "percentage": 48.72, "elapsed_time": "5:32:03", "remaining_time": "5:49:31"}
+{"current_steps": 580, "total_steps": 1170, "loss": 0.2496, "lr": 5.956241371835312e-06, "epoch": 0.49572649572649574, "percentage": 49.57, "elapsed_time": "5:37:37", "remaining_time": "5:43:26"}
+{"current_steps": 590, "total_steps": 1170, "loss": 0.2557, "lr": 5.809417593335266e-06, "epoch": 0.5042735042735043, "percentage": 50.43, "elapsed_time": "5:43:20", "remaining_time": "5:37:31"}
+{"current_steps": 600, "total_steps": 1170, "loss": 0.2348, "lr": 5.661873398704344e-06, "epoch": 0.5128205128205128, "percentage": 51.28, "elapsed_time": "5:49:13", "remaining_time": "5:31:46"}
+{"current_steps": 610, "total_steps": 1170, "loss": 0.2381, "lr": 5.5137401085596224e-06, "epoch": 0.5213675213675214, "percentage": 52.14, "elapsed_time": "5:55:02", "remaining_time": "5:25:56"}
+{"current_steps": 620, "total_steps": 1170, "loss": 0.2476, "lr": 5.3651495678382725e-06, "epoch": 0.5299145299145299, "percentage": 52.99, "elapsed_time": "6:00:53", "remaining_time": "5:20:08"}
+{"current_steps": 630, "total_steps": 1170, "loss": 0.227, "lr": 5.216234028449954e-06, "epoch": 0.5384615384615384, "percentage": 53.85, "elapsed_time": "6:06:48", "remaining_time": "5:14:24"}
+{"current_steps": 640, "total_steps": 1170, "loss": 0.2336, "lr": 5.067126031566988e-06, "epoch": 0.5470085470085471, "percentage": 54.7, "elapsed_time": "6:12:47", "remaining_time": "5:08:42"}
+{"current_steps": 650, "total_steps": 1170, "loss": 0.2187, "lr": 4.917958289657053e-06, "epoch": 0.5555555555555556, "percentage": 55.56, "elapsed_time": "6:18:33", "remaining_time": "5:02:51"}
+{"current_steps": 660, "total_steps": 1170, "loss": 0.2307, "lr": 4.768863568363449e-06, "epoch": 0.5641025641025641, "percentage": 56.41, "elapsed_time": "6:24:38", "remaining_time": "4:57:13"}
+{"current_steps": 670, "total_steps": 1170, "loss": 0.2277, "lr": 4.619974568338021e-06, "epoch": 0.5726495726495726, "percentage": 57.26, "elapsed_time": "6:30:24", "remaining_time": "4:51:21"}
+{"current_steps": 680, "total_steps": 1170, "loss": 0.2178, "lr": 4.471423807131921e-06, "epoch": 0.5811965811965812, "percentage": 58.12, "elapsed_time": "6:36:09", "remaining_time": "4:45:27"}
+{"current_steps": 690, "total_steps": 1170, "loss": 0.2163, "lr": 4.323343501249346e-06, "epoch": 0.5897435897435898, "percentage": 58.97, "elapsed_time": "6:41:47", "remaining_time": "4:39:30"}
+{"current_steps": 700, "total_steps": 1170, "loss": 0.2281, "lr": 4.175865448469219e-06, "epoch": 0.5982905982905983, "percentage": 59.83, "elapsed_time": "6:47:25", "remaining_time": "4:33:33"}
+{"current_steps": 710, "total_steps": 1170, "loss": 0.2224, "lr": 4.029120910539553e-06, "epoch": 0.6068376068376068, "percentage": 60.68, "elapsed_time": "6:53:13", "remaining_time": "4:27:43"}
+{"current_steps": 720, "total_steps": 1170, "loss": 0.2213, "lr": 3.883240496348901e-06, "epoch": 0.6153846153846154, "percentage": 61.54, "elapsed_time": "6:58:59", "remaining_time": "4:21:52"}
+{"current_steps": 730, "total_steps": 1170, "loss": 0.2158, "lr": 3.7383540456788915e-06, "epoch": 0.6239316239316239, "percentage": 62.39, "elapsed_time": "7:04:45", "remaining_time": "4:16:01"}
+{"current_steps": 740, "total_steps": 1170, "loss": 0.2104, "lr": 3.5945905136412807e-06, "epoch": 0.6324786324786325, "percentage": 63.25, "elapsed_time": "7:10:26", "remaining_time": "4:10:07"}
+{"current_steps": 750, "total_steps": 1170, "loss": 0.206, "lr": 3.4520778559024215e-06, "epoch": 0.6410256410256411, "percentage": 64.1, "elapsed_time": "7:16:27", "remaining_time": "4:04:25"}
+{"current_steps": 760, "total_steps": 1170, "loss": 0.2053, "lr": 3.310942914797265e-06, "epoch": 0.6495726495726496, "percentage": 64.96, "elapsed_time": "7:22:17", "remaining_time": "3:58:36"}
+{"current_steps": 770, "total_steps": 1170, "loss": 0.2078, "lr": 3.17131130643428e-06, "epoch": 0.6581196581196581, "percentage": 65.81, "elapsed_time": "7:28:30", "remaining_time": "3:52:59"}
+{"current_steps": 780, "total_steps": 1170, "loss": 0.198, "lr": 3.033307308891771e-06, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "7:34:17", "remaining_time": "3:47:08"}
+{"current_steps": 790, "total_steps": 1170, "loss": 0.2151, "lr": 2.8970537516050935e-06, "epoch": 0.6752136752136753, "percentage": 67.52, "elapsed_time": "7:40:03", "remaining_time": "3:41:17"}
+{"current_steps": 800, "total_steps": 1170, "loss": 0.1959, "lr": 2.7626719060432226e-06, "epoch": 0.6837606837606838, "percentage": 68.38, "elapsed_time": "7:45:58", "remaining_time": "3:35:30"}
+{"current_steps": 810, "total_steps": 1170, "loss": 0.183, "lr": 2.6302813777719817e-06, "epoch": 0.6923076923076923, "percentage": 69.23, "elapsed_time": "7:52:07", "remaining_time": "3:29:50"}
+{"current_steps": 820, "total_steps": 1170, "loss": 0.1996, "lr": 2.5000000000000015e-06, "epoch": 0.7008547008547008, "percentage": 70.09, "elapsed_time": "7:58:00", "remaining_time": "3:24:01"}
+{"current_steps": 830, "total_steps": 1170, "loss": 0.1919, "lr": 2.371943728702134e-06, "epoch": 0.7094017094017094, "percentage": 70.94, "elapsed_time": "8:03:51", "remaining_time": "3:18:12"}
+{"current_steps": 840, "total_steps": 1170, "loss": 0.202, "lr": 2.2462265394137045e-06, "epoch": 0.717948717948718, "percentage": 71.79, "elapsed_time": "8:09:33", "remaining_time": "3:12:19"}
+{"current_steps": 850, "total_steps": 1170, "loss": 0.1886, "lr": 2.122960325787432e-06, "epoch": 0.7264957264957265, "percentage": 72.65, "elapsed_time": "8:15:10", "remaining_time": "3:06:24"}
+{"current_steps": 860, "total_steps": 1170, "loss": 0.1772, "lr": 2.002254800003309e-06, "epoch": 0.7350427350427351, "percentage": 73.5, "elapsed_time": "8:20:54", "remaining_time": "3:00:33"}
+{"current_steps": 870, "total_steps": 1170, "loss": 0.1777, "lr": 1.8842173951200877e-06, "epoch": 0.7435897435897436, "percentage": 74.36, "elapsed_time": "8:26:46", "remaining_time": "2:54:44"}
+{"current_steps": 880, "total_steps": 1170, "loss": 0.1846, "lr": 1.7689531694552863e-06, "epoch": 0.7521367521367521, "percentage": 75.21, "elapsed_time": "8:32:41", "remaining_time": "2:48:57"}
+{"current_steps": 890, "total_steps": 1170, "loss": 0.1908, "lr": 1.6565647130788064e-06, "epoch": 0.7606837606837606, "percentage": 76.07, "elapsed_time": "8:38:29", "remaining_time": "2:43:07"}
+{"current_steps": 900, "total_steps": 1170, "loss": 0.2054, "lr": 1.5471520565034121e-06, "epoch": 0.7692307692307693, "percentage": 76.92, "elapsed_time": "8:44:20", "remaining_time": "2:37:18"}
+{"current_steps": 910, "total_steps": 1170, "loss": 0.1792, "lr": 1.4408125816532981e-06, "epoch": 0.7777777777777778, "percentage": 77.78, "elapsed_time": "8:50:06", "remaining_time": "2:31:27"}
+{"current_steps": 920, "total_steps": 1170, "loss": 0.1852, "lr": 1.337640935190041e-06, "epoch": 0.7863247863247863, "percentage": 78.63, "elapsed_time": "8:56:14", "remaining_time": "2:25:42"}
+{"current_steps": 930, "total_steps": 1170, "loss": 0.1785, "lr": 1.2377289442730406e-06, "epoch": 0.7948717948717948, "percentage": 79.49, "elapsed_time": "9:02:07", "remaining_time": "2:19:54"}
+{"current_steps": 940, "total_steps": 1170, "loss": 0.1793, "lr": 1.141165534829425e-06, "epoch": 0.8034188034188035, "percentage": 80.34, "elapsed_time": "9:07:48", "remaining_time": "2:14:02"}
+{"current_steps": 950, "total_steps": 1170, "loss": 0.163, "lr": 1.0480366524062041e-06, "epoch": 0.811965811965812, "percentage": 81.2, "elapsed_time": "9:13:38", "remaining_time": "2:08:12"}
+{"current_steps": 960, "total_steps": 1170, "loss": 0.1663, "lr": 9.584251856750592e-07, "epoch": 0.8205128205128205, "percentage": 82.05, "elapsed_time": "9:19:35", "remaining_time": "2:02:24"}
+{"current_steps": 970, "total_steps": 1170, "loss": 0.1774, "lr": 8.724108926579e-07, "epoch": 0.8290598290598291, "percentage": 82.91, "elapsed_time": "9:25:32", "remaining_time": "1:56:36"}
+{"current_steps": 980, "total_steps": 1170, "loss": 0.1817, "lr": 7.900703297388313e-07, "epoch": 0.8376068376068376, "percentage": 83.76, "elapsed_time": "9:31:01", "remaining_time": "1:50:42"}
+{"current_steps": 990, "total_steps": 1170, "loss": 0.1717, "lr": 7.114767835257081e-07, "epoch": 0.8461538461538461, "percentage": 84.62, "elapsed_time": "9:36:48", "remaining_time": "1:44:52"}
+{"current_steps": 1000, "total_steps": 1170, "loss": 0.1769, "lr": 6.367002056219285e-07, "epoch": 0.8547008547008547, "percentage": 85.47, "elapsed_time": "9:42:35", "remaining_time": "1:39:02"}
+{"current_steps": 1010, "total_steps": 1170, "loss": 0.1658, "lr": 5.658071503665369e-07, "epoch": 0.8632478632478633, "percentage": 86.32, "elapsed_time": "9:48:36", "remaining_time": "1:33:14"}
+{"current_steps": 1020, "total_steps": 1170, "loss": 0.1727, "lr": 4.988607155980202e-07, "epoch": 0.8717948717948718, "percentage": 87.18, "elapsed_time": "9:54:27", "remaining_time": "1:27:25"}
+{"current_steps": 1030, "total_steps": 1170, "loss": 0.1707, "lr": 4.35920486494546e-07, "epoch": 0.8803418803418803, "percentage": 88.03, "elapsed_time": "10:00:09", "remaining_time": "1:21:34"}
+{"current_steps": 1040, "total_steps": 1170, "loss": 0.1684, "lr": 3.7704248254062047e-07, "epoch": 0.8888888888888888, "percentage": 88.89, "elapsed_time": "10:06:17", "remaining_time": "1:15:47"}
+{"current_steps": 1050, "total_steps": 1170, "loss": 0.1642, "lr": 3.222791076673537e-07, "epoch": 0.8974358974358975, "percentage": 89.74, "elapsed_time": "10:11:59", "remaining_time": "1:09:56"}
+{"current_steps": 1060, "total_steps": 1170, "loss": 0.167, "lr": 2.71679103610738e-07, "epoch": 0.905982905982906, "percentage": 90.6, "elapsed_time": "10:17:47", "remaining_time": "1:04:06"}
+{"current_steps": 1070, "total_steps": 1170, "loss": 0.1672, "lr": 2.2528750652941855e-07, "epoch": 0.9145299145299145, "percentage": 91.45, "elapsed_time": "10:23:29", "remaining_time": "0:58:16"}
+{"current_steps": 1080, "total_steps": 1170, "loss": 0.1659, "lr": 1.8314560692059836e-07, "epoch": 0.9230769230769231, "percentage": 92.31, "elapsed_time": "10:29:14", "remaining_time": "0:52:26"}
+{"current_steps": 1090, "total_steps": 1170, "loss": 0.1744, "lr": 1.4529091286973994e-07, "epoch": 0.9316239316239316, "percentage": 93.16, "elapsed_time": "10:35:13", "remaining_time": "0:46:37"}
+{"current_steps": 1100, "total_steps": 1170, "loss": 0.1642, "lr": 1.117571166667658e-07, "epoch": 0.9401709401709402, "percentage": 94.02, "elapsed_time": "10:41:02", "remaining_time": "0:40:47"}
+{"current_steps": 1110, "total_steps": 1170, "loss": 0.1669, "lr": 8.257406481848861e-08, "epoch": 0.9487179487179487, "percentage": 94.87, "elapsed_time": "10:46:57", "remaining_time": "0:34:58"}
+{"current_steps": 1120, "total_steps": 1170, "loss": 0.1621, "lr": 5.776773148394976e-08, "epoch": 0.9572649572649573, "percentage": 95.73, "elapsed_time": "10:52:28", "remaining_time": "0:29:07"}
+{"current_steps": 1130, "total_steps": 1170, "loss": 0.1523, "lr": 3.7360195356309635e-08, "epoch": 0.9658119658119658, "percentage": 96.58, "elapsed_time": "10:58:17", "remaining_time": "0:23:18"}
+{"current_steps": 1140, "total_steps": 1170, "loss": 0.163, "lr": 2.1369620011871263e-08, "epoch": 0.9743589743589743, "percentage": 97.44, "elapsed_time": "11:04:11", "remaining_time": "0:17:28"}
+{"current_steps": 1150, "total_steps": 1170, "loss": 0.1708, "lr": 9.810237743724805e-09, "epoch": 0.9829059829059829, "percentage": 98.29, "elapsed_time": "11:10:02", "remaining_time": "0:11:39"}
+{"current_steps": 1160, "total_steps": 1170, "loss": 0.1581, "lr": 2.6923368943987395e-09, "epoch": 0.9914529914529915, "percentage": 99.15, "elapsed_time": "11:15:52", "remaining_time": "0:05:49"}
+{"current_steps": 1170, "total_steps": 1170, "loss": 0.1548, "lr": 2.225269879696512e-11, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "11:21:48", "remaining_time": "0:00:00"}
+{"current_steps": 1170, "total_steps": 1170, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "11:22:08", "remaining_time": "0:00:00"}

qwen2-gob-plan-119/trainer_state.json

@@ -0,0 +1,862 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008547008547008548,
+      "grad_norm": 27.4459228515625,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 2.244,
+      "step": 10
+    },
+    {
+      "epoch": 0.017094017094017096,
+      "grad_norm": 10.770344734191895,
+      "learning_rate": 1.623931623931624e-06,
+      "loss": 1.5517,
+      "step": 20
+    },
+    {
+      "epoch": 0.02564102564102564,
+      "grad_norm": 5.093418598175049,
+      "learning_rate": 2.478632478632479e-06,
+      "loss": 0.8494,
+      "step": 30
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "grad_norm": 3.8021461963653564,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6006,
+      "step": 40
+    },
+    {
+      "epoch": 0.042735042735042736,
+      "grad_norm": 3.676161527633667,
+      "learning_rate": 4.188034188034188e-06,
+      "loss": 0.5208,
+      "step": 50
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 3.234729290008545,
+      "learning_rate": 5.042735042735043e-06,
+      "loss": 0.5017,
+      "step": 60
+    },
+    {
+      "epoch": 0.05982905982905983,
+      "grad_norm": 2.8927907943725586,
+      "learning_rate": 5.897435897435898e-06,
+      "loss": 0.4581,
+      "step": 70
+    },
+    {
+      "epoch": 0.06837606837606838,
+      "grad_norm": 2.978990316390991,
+      "learning_rate": 6.752136752136753e-06,
+      "loss": 0.4624,
+      "step": 80
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 2.973573923110962,
+      "learning_rate": 7.606837606837607e-06,
+      "loss": 0.4578,
+      "step": 90
+    },
+    {
+      "epoch": 0.08547008547008547,
+      "grad_norm": 3.0416812896728516,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.44,
+      "step": 100
+    },
+    {
+      "epoch": 0.09401709401709402,
+      "grad_norm": 2.8858296871185303,
+      "learning_rate": 9.316239316239318e-06,
+      "loss": 0.4455,
+      "step": 110
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 2.5339534282684326,
+      "learning_rate": 9.999910989402885e-06,
+      "loss": 0.4151,
+      "step": 120
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 2.9609498977661133,
+      "learning_rate": 9.996795951252427e-06,
+      "loss": 0.4292,
+      "step": 130
+    },
+    {
+      "epoch": 0.11965811965811966,
+      "grad_norm": 2.7929954528808594,
+      "learning_rate": 9.989233551893588e-06,
+      "loss": 0.4081,
+      "step": 140
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 2.295203924179077,
+      "learning_rate": 9.977230522183876e-06,
+      "loss": 0.4095,
+      "step": 150
+    },
+    {
+      "epoch": 0.13675213675213677,
+      "grad_norm": 2.527277946472168,
+      "learning_rate": 9.960797545330936e-06,
+      "loss": 0.4011,
+      "step": 160
+    },
+    {
+      "epoch": 0.1452991452991453,
+      "grad_norm": 2.492537021636963,
+      "learning_rate": 9.939949247384046e-06,
+      "loss": 0.4169,
+      "step": 170
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 2.4258060455322266,
+      "learning_rate": 9.914704184216296e-06,
+      "loss": 0.3819,
+      "step": 180
+    },
+    {
+      "epoch": 0.1623931623931624,
+      "grad_norm": 2.4105043411254883,
+      "learning_rate": 9.885084825009085e-06,
+      "loss": 0.3904,
+      "step": 190
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 2.255687713623047,
+      "learning_rate": 9.851117532253587e-06,
+      "loss": 0.3788,
+      "step": 200
+    },
+    {
+      "epoch": 0.1794871794871795,
+      "grad_norm": 2.3440539836883545,
+      "learning_rate": 9.81283253828701e-06,
+      "loss": 0.372,
+      "step": 210
+    },
+    {
+      "epoch": 0.18803418803418803,
+      "grad_norm": 2.5769221782684326,
+      "learning_rate": 9.770263918384523e-06,
+      "loss": 0.3839,
+      "step": 220
+    },
+    {
+      "epoch": 0.19658119658119658,
+      "grad_norm": 2.2017064094543457,
+      "learning_rate": 9.723449560430827e-06,
+      "loss": 0.373,
+      "step": 230
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 2.215395927429199,
+      "learning_rate": 9.672431131198306e-06,
+      "loss": 0.3671,
+      "step": 240
+    },
+    {
+      "epoch": 0.21367521367521367,
+      "grad_norm": 1.936713695526123,
+      "learning_rate": 9.617254039261835e-06,
+      "loss": 0.3782,
+      "step": 250
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 2.1291184425354004,
+      "learning_rate": 9.557967394583206e-06,
+      "loss": 0.356,
+      "step": 260
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 2.167850971221924,
+      "learning_rate": 9.494623964801185e-06,
+      "loss": 0.3297,
+      "step": 270
+    },
+    {
+      "epoch": 0.23931623931623933,
+      "grad_norm": 1.9700742959976196,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 0.3448,
+      "step": 280
+    },
+    {
+      "epoch": 0.24786324786324787,
+      "grad_norm": 2.0936436653137207,
+      "learning_rate": 9.355995823860468e-06,
+      "loss": 0.3355,
+      "step": 290
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 2.071155071258545,
+      "learning_rate": 9.280834497651334e-06,
+      "loss": 0.3381,
+      "step": 300
+    },
+    {
+      "epoch": 0.26495726495726496,
+      "grad_norm": 2.0431532859802246,
+      "learning_rate": 9.201863046420065e-06,
+      "loss": 0.3401,
+      "step": 310
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 2.1435134410858154,
+      "learning_rate": 9.119151758121627e-06,
+      "loss": 0.3246,
+      "step": 320
+    },
+    {
+      "epoch": 0.28205128205128205,
+      "grad_norm": 1.8832941055297852,
+      "learning_rate": 9.032774249325247e-06,
+      "loss": 0.3372,
+      "step": 330
+    },
+    {
+      "epoch": 0.2905982905982906,
+      "grad_norm": 2.0747435092926025,
+      "learning_rate": 8.942807399692543e-06,
+      "loss": 0.3168,
+      "step": 340
+    },
+    {
+      "epoch": 0.29914529914529914,
+      "grad_norm": 1.8736019134521484,
+      "learning_rate": 8.849331283551345e-06,
+      "loss": 0.3281,
+      "step": 350
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 1.9067050218582153,
+      "learning_rate": 8.752429098626132e-06,
+      "loss": 0.3159,
+      "step": 360
+    },
+    {
+      "epoch": 0.3162393162393162,
+      "grad_norm": 1.7850850820541382,
+      "learning_rate": 8.652187091988516e-06,
+      "loss": 0.3179,
+      "step": 370
+    },
+    {
+      "epoch": 0.3247863247863248,
+      "grad_norm": 2.262554883956909,
+      "learning_rate": 8.548694483293678e-06,
+      "loss": 0.3061,
+      "step": 380
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.0474228858947754,
+      "learning_rate": 8.442043385371069e-06,
+      "loss": 0.3079,
+      "step": 390
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 1.743433952331543,
+      "learning_rate": 8.332328722240072e-06,
+      "loss": 0.2989,
+      "step": 400
+    },
+    {
+      "epoch": 0.3504273504273504,
+      "grad_norm": 2.109647274017334,
+      "learning_rate": 8.219648144623584e-06,
+      "loss": 0.2892,
+      "step": 410
+    },
+    {
+      "epoch": 0.358974358974359,
+      "grad_norm": 2.0099992752075195,
+      "learning_rate": 8.10410194303471e-06,
+      "loss": 0.3011,
+      "step": 420
+    },
+    {
+      "epoch": 0.36752136752136755,
+      "grad_norm": 1.9044047594070435,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.2886,
+      "step": 430
+    },
+    {
+      "epoch": 0.37606837606837606,
+      "grad_norm": 1.9169471263885498,
+      "learning_rate": 7.864826491096214e-06,
+      "loss": 0.2973,
+      "step": 440
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 1.8048131465911865,
+      "learning_rate": 7.741310206089474e-06,
+      "loss": 0.2865,
+      "step": 450
+    },
+    {
+      "epoch": 0.39316239316239315,
+      "grad_norm": 1.8077330589294434,
+      "learning_rate": 7.615354038247889e-06,
+      "loss": 0.2721,
+      "step": 460
+    },
+    {
+      "epoch": 0.4017094017094017,
+      "grad_norm": 1.9586660861968994,
+      "learning_rate": 7.48707009392526e-06,
+      "loss": 0.2675,
+      "step": 470
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 1.7881312370300293,
+      "learning_rate": 7.356572551295604e-06,
+      "loss": 0.2714,
+      "step": 480
+    },
+    {
+      "epoch": 0.4188034188034188,
+      "grad_norm": 1.773877501487732,
+      "learning_rate": 7.223977558729707e-06,
+      "loss": 0.2799,
+      "step": 490
+    },
+    {
+      "epoch": 0.42735042735042733,
+      "grad_norm": 1.5951801538467407,
+      "learning_rate": 7.089403131418126e-06,
+      "loss": 0.265,
+      "step": 500
+    },
+    {
+      "epoch": 0.4358974358974359,
+      "grad_norm": 1.6559046506881714,
+      "learning_rate": 6.952969046332642e-06,
+      "loss": 0.2756,
+      "step": 510
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.7863497734069824,
+      "learning_rate": 6.814796735619664e-06,
+      "loss": 0.4513,
+      "step": 520
+    },
+    {
+      "epoch": 0.452991452991453,
+      "grad_norm": 1.632804036140442,
+      "learning_rate": 6.675009178520435e-06,
+      "loss": 0.277,
+      "step": 530
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 1.8557840585708618,
+      "learning_rate": 6.5337307919142766e-06,
+      "loss": 0.2665,
+      "step": 540
+    },
+    {
+      "epoch": 0.4700854700854701,
+      "grad_norm": 1.7625755071640015,
+      "learning_rate": 6.391087319582264e-06,
+      "loss": 0.2607,
+      "step": 550
+    },
+    {
+      "epoch": 0.47863247863247865,
+      "grad_norm": 1.7799347639083862,
+      "learning_rate": 6.247205720289907e-06,
+      "loss": 0.2548,
+      "step": 560
+    },
+    {
+      "epoch": 0.48717948717948717,
+      "grad_norm": 1.62433660030365,
+      "learning_rate": 6.102214054788444e-06,
+      "loss": 0.2603,
+      "step": 570
+    },
+    {
+      "epoch": 0.49572649572649574,
+      "grad_norm": 1.6350067853927612,
+      "learning_rate": 5.956241371835312e-06,
+      "loss": 0.2496,
+      "step": 580
+    },
+    {
+      "epoch": 0.5042735042735043,
+      "grad_norm": 1.648517370223999,
+      "learning_rate": 5.809417593335266e-06,
+      "loss": 0.2557,
+      "step": 590
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 1.7348986864089966,
+      "learning_rate": 5.661873398704344e-06,
+      "loss": 0.2348,
+      "step": 600
+    },
+    {
+      "epoch": 0.5213675213675214,
+      "grad_norm": 1.6275596618652344,
+      "learning_rate": 5.5137401085596224e-06,
+      "loss": 0.2381,
+      "step": 610
+    },
+    {
+      "epoch": 0.5299145299145299,
+      "grad_norm": 1.7754584550857544,
+      "learning_rate": 5.3651495678382725e-06,
+      "loss": 0.2476,
+      "step": 620
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 1.6710491180419922,
+      "learning_rate": 5.216234028449954e-06,
+      "loss": 0.227,
+      "step": 630
+    },
+    {
+      "epoch": 0.5470085470085471,
+      "grad_norm": 1.6521528959274292,
+      "learning_rate": 5.067126031566988e-06,
+      "loss": 0.2336,
+      "step": 640
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.5551559925079346,
+      "learning_rate": 4.917958289657053e-06,
+      "loss": 0.2187,
+      "step": 650
+    },
+    {
+      "epoch": 0.5641025641025641,
+      "grad_norm": 1.523729920387268,
+      "learning_rate": 4.768863568363449e-06,
+      "loss": 0.2307,
+      "step": 660
+    },
+    {
+      "epoch": 0.5726495726495726,
+      "grad_norm": 1.6331489086151123,
+      "learning_rate": 4.619974568338021e-06,
+      "loss": 0.2277,
+      "step": 670
+    },
+    {
+      "epoch": 0.5811965811965812,
+      "grad_norm": 1.7467578649520874,
+      "learning_rate": 4.471423807131921e-06,
+      "loss": 0.2178,
+      "step": 680
+    },
+    {
+      "epoch": 0.5897435897435898,
+      "grad_norm": 1.6113359928131104,
+      "learning_rate": 4.323343501249346e-06,
+      "loss": 0.2163,
+      "step": 690
+    },
+    {
+      "epoch": 0.5982905982905983,
+      "grad_norm": 1.7347848415374756,
+      "learning_rate": 4.175865448469219e-06,
+      "loss": 0.2281,
+      "step": 700
+    },
+    {
+      "epoch": 0.6068376068376068,
+      "grad_norm": 1.6740282773971558,
+      "learning_rate": 4.029120910539553e-06,
+      "loss": 0.2224,
+      "step": 710
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 1.758033275604248,
+      "learning_rate": 3.883240496348901e-06,
+      "loss": 0.2213,
+      "step": 720
+    },
+    {
+      "epoch": 0.6239316239316239,
+      "grad_norm": 1.8379418849945068,
+      "learning_rate": 3.7383540456788915e-06,
+      "loss": 0.2158,
+      "step": 730
+    },
+    {
+      "epoch": 0.6324786324786325,
+      "grad_norm": 1.700239658355713,
+      "learning_rate": 3.5945905136412807e-06,
+      "loss": 0.2104,
+      "step": 740
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 1.6407594680786133,
+      "learning_rate": 3.4520778559024215e-06,
+      "loss": 0.206,
+      "step": 750
+    },
+    {
+      "epoch": 0.6495726495726496,
+      "grad_norm": 1.5347175598144531,
+      "learning_rate": 3.310942914797265e-06,
+      "loss": 0.2053,
+      "step": 760
+    },
+    {
+      "epoch": 0.6581196581196581,
+      "grad_norm": 2.9763214588165283,
+      "learning_rate": 3.17131130643428e-06,
+      "loss": 0.2078,
+      "step": 770
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.5973738431930542,
+      "learning_rate": 3.033307308891771e-06,
+      "loss": 0.198,
+      "step": 780
+    },
+    {
+      "epoch": 0.6752136752136753,
+      "grad_norm": 1.8559173345565796,
+      "learning_rate": 2.8970537516050935e-06,
+      "loss": 0.2151,
+      "step": 790
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 1.450613021850586,
+      "learning_rate": 2.7626719060432226e-06,
+      "loss": 0.1959,
+      "step": 800
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 1.7653888463974,
+      "learning_rate": 2.6302813777719817e-06,
+      "loss": 0.183,
+      "step": 810
+    },
+    {
+      "epoch": 0.7008547008547008,
+      "grad_norm": 1.8113172054290771,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1996,
+      "step": 820
+    },
+    {
+      "epoch": 0.7094017094017094,
+      "grad_norm": 1.5475842952728271,
+      "learning_rate": 2.371943728702134e-06,
+      "loss": 0.1919,
+      "step": 830
+    },
+    {
+      "epoch": 0.717948717948718,
+      "grad_norm": 1.4717930555343628,
+      "learning_rate": 2.2462265394137045e-06,
+      "loss": 0.202,
+      "step": 840
+    },
+    {
+      "epoch": 0.7264957264957265,
+      "grad_norm": 1.4109082221984863,
+      "learning_rate": 2.122960325787432e-06,
+      "loss": 0.1886,
+      "step": 850
+    },
+    {
+      "epoch": 0.7350427350427351,
+      "grad_norm": 1.48606276512146,
+      "learning_rate": 2.002254800003309e-06,
+      "loss": 0.1772,
+      "step": 860
+    },
+    {
+      "epoch": 0.7435897435897436,
+      "grad_norm": 1.4984902143478394,
+      "learning_rate": 1.8842173951200877e-06,
+      "loss": 0.1777,
+      "step": 870
+    },
+    {
+      "epoch": 0.7521367521367521,
+      "grad_norm": 1.5217974185943604,
+      "learning_rate": 1.7689531694552863e-06,
+      "loss": 0.1846,
+      "step": 880
+    },
+    {
+      "epoch": 0.7606837606837606,
+      "grad_norm": 1.5059102773666382,
+      "learning_rate": 1.6565647130788064e-06,
+      "loss": 0.1908,
+      "step": 890
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.6452871561050415,
+      "learning_rate": 1.5471520565034121e-06,
+      "loss": 0.2054,
+      "step": 900
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 1.4861767292022705,
+      "learning_rate": 1.4408125816532981e-06,
+      "loss": 0.1792,
+      "step": 910
+    },
+    {
+      "epoch": 0.7863247863247863,
+      "grad_norm": 1.7520594596862793,
+      "learning_rate": 1.337640935190041e-06,
+      "loss": 0.1852,
+      "step": 920
+    },
+    {
+      "epoch": 0.7948717948717948,
+      "grad_norm": 1.570269227027893,
+      "learning_rate": 1.2377289442730406e-06,
+      "loss": 0.1785,
+      "step": 930
+    },
+    {
+      "epoch": 0.8034188034188035,
+      "grad_norm": 1.6048128604888916,
+      "learning_rate": 1.141165534829425e-06,
+      "loss": 0.1793,
+      "step": 940
+    },
+    {
+      "epoch": 0.811965811965812,
+      "grad_norm": 1.5234979391098022,
+      "learning_rate": 1.0480366524062041e-06,
+      "loss": 0.163,
+      "step": 950
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 1.668768286705017,
+      "learning_rate": 9.584251856750592e-07,
+      "loss": 0.1663,
+      "step": 960
+    },
+    {
+      "epoch": 0.8290598290598291,
+      "grad_norm": 1.436938762664795,
+      "learning_rate": 8.724108926579e-07,
+      "loss": 0.1774,
+      "step": 970
+    },
+    {
+      "epoch": 0.8376068376068376,
+      "grad_norm": 1.6603827476501465,
+      "learning_rate": 7.900703297388313e-07,
+      "loss": 0.1817,
+      "step": 980
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 1.733099102973938,
+      "learning_rate": 7.114767835257081e-07,
+      "loss": 0.1717,
+      "step": 990
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 1.586044192314148,
+      "learning_rate": 6.367002056219285e-07,
+      "loss": 0.1769,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8632478632478633,
+      "grad_norm": 1.4413237571716309,
+      "learning_rate": 5.658071503665369e-07,
+      "loss": 0.1658,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8717948717948718,
+      "grad_norm": 1.7140276432037354,
+      "learning_rate": 4.988607155980202e-07,
+      "loss": 0.1727,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8803418803418803,
+      "grad_norm": 1.661085605621338,
+      "learning_rate": 4.35920486494546e-07,
+      "loss": 0.1707,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.455249547958374,
+      "learning_rate": 3.7704248254062047e-07,
+      "loss": 0.1684,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 1.5443419218063354,
+      "learning_rate": 3.222791076673537e-07,
+      "loss": 0.1642,
+      "step": 1050
+    },
+    {
+      "epoch": 0.905982905982906,
+      "grad_norm": 1.521584153175354,
+      "learning_rate": 2.71679103610738e-07,
+      "loss": 0.167,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9145299145299145,
+      "grad_norm": 1.5626137256622314,
+      "learning_rate": 2.2528750652941855e-07,
+      "loss": 0.1672,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 1.4470199346542358,
+      "learning_rate": 1.8314560692059836e-07,
+      "loss": 0.1659,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9316239316239316,
+      "grad_norm": 1.4819871187210083,
+      "learning_rate": 1.4529091286973994e-07,
+      "loss": 0.1744,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9401709401709402,
+      "grad_norm": 1.6093999147415161,
+      "learning_rate": 1.117571166667658e-07,
+      "loss": 0.1642,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9487179487179487,
+      "grad_norm": 1.5020021200180054,
+      "learning_rate": 8.257406481848861e-08,
+      "loss": 0.1669,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 1.4375704526901245,
+      "learning_rate": 5.776773148394976e-08,
+      "loss": 0.1621,
+      "step": 1120
+    },
+    {
+      "epoch": 0.9658119658119658,
+      "grad_norm": 1.3386337757110596,
+      "learning_rate": 3.7360195356309635e-08,
+      "loss": 0.1523,
+      "step": 1130
+    },
+    {
+      "epoch": 0.9743589743589743,
+      "grad_norm": 1.6521068811416626,
+      "learning_rate": 2.1369620011871263e-08,
+      "loss": 0.163,
+      "step": 1140
+    },
+    {
+      "epoch": 0.9829059829059829,
+      "grad_norm": 1.68519127368927,
+      "learning_rate": 9.810237743724805e-09,
+      "loss": 0.1708,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "grad_norm": 1.4955705404281616,
+      "learning_rate": 2.6923368943987395e-09,
+      "loss": 0.1581,
+      "step": 1160
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6666723489761353,
+      "learning_rate": 2.225269879696512e-11,
+      "loss": 0.1548,
+      "step": 1170
+    },
+    {
+      "epoch": 1.0,
+      "step": 1170,
+      "total_flos": 476639621545984.0,
+      "train_loss": 0.3024920547110403,
+      "train_runtime": 40928.1916,
+      "train_samples_per_second": 0.915,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1170,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 476639621545984.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2-gob-plan-119/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce2ccaa8b24fad30f0e5de1e3f4526f59af7aa470b9a2acf1325b97e3591003
+size 8401