Upload folder using huggingface_hub

.gitattributes

@@ -71,3 +71,4 @@ g2_4_plan_cm_oldcode_newcode/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -
 g2_4_plan_cm_oldcode_newcode/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g2_5_plan_newcode/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g2_5_plan_newcode/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+g2_5_plan_newcode/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text

g2_5_plan_newcode/1000M/README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B-Base
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 1000M
+  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. -->
+
+# 1000M
+
+This model is a fine-tuned version of [/lus/flare/projects/MultiModalLLM/model-weights/Qwen/Qwen3-8B-Base](https://huggingface.co//lus/flare/projects/MultiModalLLM/model-weights/Qwen/Qwen3-8B-Base) on the rv5_g2_5_plan_newcode and the instruct_replay datasets.
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 12
+- total_train_batch_size: 12
+- total_eval_batch_size: 96
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: warmup_stable_decay
+- lr_scheduler_warmup_steps: 178
+- training_steps: 11193
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.10.0a0+git449b176
+- Datasets 4.5.0
+- Tokenizers 0.22.2

g2_5_plan_newcode/1000M/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

g2_5_plan_newcode/1000M/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9842595849454802,
+    "total_flos": 4.9965855215861105e+19,
+    "train_loss": 0.06081981670863931,
+    "train_runtime": 11653.1989,
+    "train_samples_per_second": 11.526,
+    "train_steps_per_second": 0.961
+}

g2_5_plan_newcode/1000M/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

g2_5_plan_newcode/1000M/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

g2_5_plan_newcode/1000M/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.6"
+}

g2_5_plan_newcode/1000M/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba67a99bc41ed6cfe5e02e29e5f288db5047e882c89feabbe975a58c4388eb9
+size 4902257696

g2_5_plan_newcode/1000M/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fcb1d96570a3864ab5a6295c212a7f868a6e823a0138ca61dcddd3f6b940ada
+size 4915960368

g2_5_plan_newcode/1000M/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e31af4cbe284f1e9fc78e7f375a74b64d03e93db8645991056071eb383186b
+size 4983068496

g2_5_plan_newcode/1000M/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cadf16cd3833c47f5935037785a8cec41fd746d9249c0961efff465c8bde903
+size 1580230264

g2_5_plan_newcode/1000M/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-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_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "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_norm.weight": "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.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-00001-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_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

g2_5_plan_newcode/1000M/special_tokens_map.json

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

g2_5_plan_newcode/1000M/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

g2_5_plan_newcode/1000M/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": "<|endoftext|>",
+  "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
+}

g2_5_plan_newcode/1000M/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9842595849454802,
+    "total_flos": 4.9965855215861105e+19,
+    "train_loss": 0.06081981670863931,
+    "train_runtime": 11653.1989,
+    "train_samples_per_second": 11.526,
+    "train_steps_per_second": 0.961
+}

g2_5_plan_newcode/1000M/trainer_log.jsonl

@@ -0,0 +1,103 @@
+{"current_steps": 10180, "total_steps": 11193, "loss": 0.6757, "lr": 1.999957274187931e-05, "epoch": 0.8951811466760464, "percentage": 90.95, "elapsed_time": "0:00:48", "remaining_time": "0:00:04"}
+{"current_steps": 10190, "total_steps": 11193, "loss": 0.6801, "lr": 1.9991978062682906e-05, "epoch": 0.8960604994723883, "percentage": 91.04, "elapsed_time": "0:02:42", "remaining_time": "0:00:16"}
+{"current_steps": 10200, "total_steps": 11193, "loss": 0.7084, "lr": 1.997489709987378e-05, "epoch": 0.8969398522687302, "percentage": 91.13, "elapsed_time": "0:04:36", "remaining_time": "0:00:26"}
+{"current_steps": 10210, "total_steps": 11193, "loss": 0.6633, "lr": 1.9948346151502135e-05, "epoch": 0.8978192050650721, "percentage": 91.22, "elapsed_time": "0:06:30", "remaining_time": "0:00:37"}
+{"current_steps": 10220, "total_steps": 11193, "loss": 0.6658, "lr": 1.991235055154325e-05, "epoch": 0.898698557861414, "percentage": 91.31, "elapsed_time": "0:08:25", "remaining_time": "0:00:48"}
+{"current_steps": 10230, "total_steps": 11193, "loss": 0.6592, "lr": 1.9866944645724693e-05, "epoch": 0.8995779106577559, "percentage": 91.4, "elapsed_time": "0:10:19", "remaining_time": "0:00:58"}
+{"current_steps": 10240, "total_steps": 11193, "loss": 0.6714, "lr": 1.9812171758754842e-05, "epoch": 0.9004572634540978, "percentage": 91.49, "elapsed_time": "0:12:13", "remaining_time": "0:01:08"}
+{"current_steps": 10250, "total_steps": 11193, "loss": 0.6662, "lr": 1.9748084152983987e-05, "epoch": 0.9013366162504397, "percentage": 91.58, "elapsed_time": "0:14:07", "remaining_time": "0:01:17"}
+{"current_steps": 10260, "total_steps": 11193, "loss": 0.6777, "lr": 1.967474297853744e-05, "epoch": 0.9022159690467816, "percentage": 91.66, "elapsed_time": "0:16:01", "remaining_time": "0:01:27"}
+{"current_steps": 10270, "total_steps": 11193, "loss": 0.6587, "lr": 1.9592218214968256e-05, "epoch": 0.9030953218431235, "percentage": 91.75, "elapsed_time": "0:17:55", "remaining_time": "0:01:36"}
+{"current_steps": 10280, "total_steps": 11193, "loss": 0.703, "lr": 1.9500588604485213e-05, "epoch": 0.9039746746394653, "percentage": 91.84, "elapsed_time": "0:19:49", "remaining_time": "0:01:45"}
+{"current_steps": 10290, "total_steps": 11193, "loss": 0.691, "lr": 1.939994157681979e-05, "epoch": 0.9048540274358072, "percentage": 91.93, "elapsed_time": "0:21:43", "remaining_time": "0:01:54"}
+{"current_steps": 10300, "total_steps": 11193, "loss": 0.6798, "lr": 1.9290373165803803e-05, "epoch": 0.9057333802321491, "percentage": 92.02, "elapsed_time": "0:23:37", "remaining_time": "0:02:02"}
+{"current_steps": 10310, "total_steps": 11193, "loss": 0.6804, "lr": 1.9171987917737328e-05, "epoch": 0.906612733028491, "percentage": 92.11, "elapsed_time": "0:25:31", "remaining_time": "0:02:11"}
+{"current_steps": 10320, "total_steps": 11193, "loss": 0.6834, "lr": 1.9044898791634322e-05, "epoch": 0.9074920858248329, "percentage": 92.2, "elapsed_time": "0:27:25", "remaining_time": "0:02:19"}
+{"current_steps": 10330, "total_steps": 11193, "loss": 0.6969, "lr": 1.8909227051441126e-05, "epoch": 0.9083714386211749, "percentage": 92.29, "elapsed_time": "0:29:19", "remaining_time": "0:02:26"}
+{"current_steps": 10340, "total_steps": 11193, "loss": 0.6927, "lr": 1.8765102150330692e-05, "epoch": 0.9092507914175167, "percentage": 92.38, "elapsed_time": "0:31:13", "remaining_time": "0:02:34"}
+{"current_steps": 10350, "total_steps": 11193, "loss": 0.666, "lr": 1.861266160718297e-05, "epoch": 0.9101301442138586, "percentage": 92.47, "elapsed_time": "0:33:07", "remaining_time": "0:02:41"}
+{"current_steps": 10360, "total_steps": 11193, "loss": 0.7008, "lr": 1.845205087536923e-05, "epoch": 0.9110094970102005, "percentage": 92.56, "elapsed_time": "0:35:02", "remaining_time": "0:02:49"}
+{"current_steps": 10370, "total_steps": 11193, "loss": 0.6948, "lr": 1.8283423203965633e-05, "epoch": 0.9118888498065424, "percentage": 92.65, "elapsed_time": "0:36:56", "remaining_time": "0:02:55"}
+{"current_steps": 10380, "total_steps": 11193, "loss": 0.6815, "lr": 1.810693949152835e-05, "epoch": 0.9127682026028843, "percentage": 92.74, "elapsed_time": "0:38:50", "remaining_time": "0:03:02"}
+{"current_steps": 10390, "total_steps": 11193, "loss": 0.6513, "lr": 1.7922768132569902e-05, "epoch": 0.9136475553992262, "percentage": 92.83, "elapsed_time": "0:40:44", "remaining_time": "0:03:08"}
+{"current_steps": 10400, "total_steps": 11193, "loss": 0.6775, "lr": 1.773108485688302e-05, "epoch": 0.914526908195568, "percentage": 92.92, "elapsed_time": "0:42:39", "remaining_time": "0:03:15"}
+{"current_steps": 10410, "total_steps": 11193, "loss": 0.6602, "lr": 1.7532072561865537e-05, "epoch": 0.9154062609919099, "percentage": 93.0, "elapsed_time": "0:44:33", "remaining_time": "0:03:21"}
+{"current_steps": 10420, "total_steps": 11193, "loss": 0.6912, "lr": 1.732592113800616e-05, "epoch": 0.9162856137882518, "percentage": 93.09, "elapsed_time": "0:46:27", "remaining_time": "0:03:26"}
+{"current_steps": 10430, "total_steps": 11193, "loss": 0.6775, "lr": 1.7112827287697668e-05, "epoch": 0.9171649665845938, "percentage": 93.18, "elapsed_time": "0:48:21", "remaining_time": "0:03:32"}
+{"current_steps": 10440, "total_steps": 11193, "loss": 0.6764, "lr": 1.6892994337550452e-05, "epoch": 0.9180443193809357, "percentage": 93.27, "elapsed_time": "0:50:16", "remaining_time": "0:03:37"}
+{"current_steps": 10450, "total_steps": 11193, "loss": 0.7079, "lr": 1.6666632044385487e-05, "epoch": 0.9189236721772776, "percentage": 93.36, "elapsed_time": "0:52:10", "remaining_time": "0:03:42"}
+{"current_steps": 10460, "total_steps": 11193, "loss": 0.6665, "lr": 1.6433956395091757e-05, "epoch": 0.9198030249736194, "percentage": 93.45, "elapsed_time": "0:54:04", "remaining_time": "0:03:47"}
+{"current_steps": 10470, "total_steps": 11193, "loss": 0.6738, "lr": 1.6195189400539238e-05, "epoch": 0.9206823777699613, "percentage": 93.54, "elapsed_time": "0:55:58", "remaining_time": "0:03:51"}
+{"current_steps": 10480, "total_steps": 11193, "loss": 0.6921, "lr": 1.595055888374398e-05, "epoch": 0.9215617305663032, "percentage": 93.63, "elapsed_time": "0:57:52", "remaining_time": "0:03:56"}
+{"current_steps": 10490, "total_steps": 11193, "loss": 0.6832, "lr": 1.5700298262487434e-05, "epoch": 0.9224410833626451, "percentage": 93.72, "elapsed_time": "0:59:47", "remaining_time": "0:04:00"}
+{"current_steps": 10500, "total_steps": 11193, "loss": 0.6959, "lr": 1.5444646326597467e-05, "epoch": 0.923320436158987, "percentage": 93.81, "elapsed_time": "1:01:41", "remaining_time": "0:04:04"}
+{"current_steps": 10510, "total_steps": 11193, "loss": 0.6737, "lr": 1.5183847010103586e-05, "epoch": 0.9241997889553288, "percentage": 93.9, "elapsed_time": "1:03:35", "remaining_time": "0:04:07"}
+{"current_steps": 10520, "total_steps": 11193, "loss": 0.6673, "lr": 1.4918149158483686e-05, "epoch": 0.9250791417516707, "percentage": 93.99, "elapsed_time": "1:05:29", "remaining_time": "0:04:11"}
+{"current_steps": 10530, "total_steps": 11193, "loss": 0.6937, "lr": 1.464780629122452e-05, "epoch": 0.9259584945480127, "percentage": 94.08, "elapsed_time": "1:07:23", "remaining_time": "0:04:14"}
+{"current_steps": 10540, "total_steps": 11193, "loss": 0.6698, "lr": 1.4373076359922374e-05, "epoch": 0.9268378473443546, "percentage": 94.17, "elapsed_time": "1:09:16", "remaining_time": "0:04:17"}
+{"current_steps": 10550, "total_steps": 11193, "loss": 0.6853, "lr": 1.4094221502154774e-05, "epoch": 0.9277172001406965, "percentage": 94.26, "elapsed_time": "1:11:10", "remaining_time": "0:04:20"}
+{"current_steps": 10560, "total_steps": 11193, "loss": 0.6832, "lr": 1.3811507791358113e-05, "epoch": 0.9285965529370384, "percentage": 94.34, "elapsed_time": "1:13:04", "remaining_time": "0:04:22"}
+{"current_steps": 10570, "total_steps": 11193, "loss": 0.6571, "lr": 1.3525204982949753e-05, "epoch": 0.9294759057333802, "percentage": 94.43, "elapsed_time": "1:14:58", "remaining_time": "0:04:25"}
+{"current_steps": 10580, "total_steps": 11193, "loss": 0.684, "lr": 1.3235586256936996e-05, "epoch": 0.9303552585297221, "percentage": 94.52, "elapsed_time": "1:16:53", "remaining_time": "0:04:27"}
+{"current_steps": 10590, "total_steps": 11193, "loss": 0.6581, "lr": 1.294292795725836e-05, "epoch": 0.931234611326064, "percentage": 94.61, "elapsed_time": "1:18:47", "remaining_time": "0:04:29"}
+{"current_steps": 10600, "total_steps": 11193, "loss": 0.6663, "lr": 1.2647509328105978e-05, "epoch": 0.9321139641224059, "percentage": 94.7, "elapsed_time": "1:20:42", "remaining_time": "0:04:30"}
+{"current_steps": 10610, "total_steps": 11193, "loss": 0.6661, "lr": 1.2349612247480686e-05, "epoch": 0.9329933169187478, "percentage": 94.79, "elapsed_time": "1:22:36", "remaining_time": "0:04:32"}
+{"current_steps": 10620, "total_steps": 11193, "loss": 0.6817, "lr": 1.2049520958234e-05, "epoch": 0.9338726697150896, "percentage": 94.88, "elapsed_time": "1:24:31", "remaining_time": "0:04:33"}
+{"current_steps": 10630, "total_steps": 11193, "loss": 0.6696, "lr": 1.1747521796853638e-05, "epoch": 0.9347520225114316, "percentage": 94.97, "elapsed_time": "1:26:25", "remaining_time": "0:04:34"}
+{"current_steps": 10640, "total_steps": 11193, "loss": 0.6632, "lr": 1.1443902920251395e-05, "epoch": 0.9356313753077735, "percentage": 95.06, "elapsed_time": "1:28:20", "remaining_time": "0:04:35"}
+{"current_steps": 10650, "total_steps": 11193, "loss": 0.6577, "lr": 1.1138954030814009e-05, "epoch": 0.9365107281041154, "percentage": 95.15, "elapsed_time": "1:30:14", "remaining_time": "0:04:36"}
+{"current_steps": 10660, "total_steps": 11193, "loss": 0.6532, "lr": 1.0832966099979388e-05, "epoch": 0.9373900809004573, "percentage": 95.24, "elapsed_time": "1:32:09", "remaining_time": "0:04:36"}
+{"current_steps": 10670, "total_steps": 11193, "loss": 0.6769, "lr": 1.0526231090601969e-05, "epoch": 0.9382694336967992, "percentage": 95.33, "elapsed_time": "1:34:03", "remaining_time": "0:04:36"}
+{"current_steps": 10680, "total_steps": 11193, "loss": 0.6694, "lr": 1.0219041678372106e-05, "epoch": 0.939148786493141, "percentage": 95.42, "elapsed_time": "1:35:57", "remaining_time": "0:04:36"}
+{"current_steps": 10690, "total_steps": 11193, "loss": 0.6593, "lr": 9.911690972555268e-06, "epoch": 0.9400281392894829, "percentage": 95.51, "elapsed_time": "1:37:51", "remaining_time": "0:04:36"}
+{"current_steps": 10700, "total_steps": 11193, "loss": 0.6624, "lr": 9.604472236317541e-06, "epoch": 0.9409074920858248, "percentage": 95.6, "elapsed_time": "1:39:46", "remaining_time": "0:04:35"}
+{"current_steps": 10710, "total_steps": 11193, "loss": 0.6967, "lr": 9.297678606904335e-06, "epoch": 0.9417868448821667, "percentage": 95.68, "elapsed_time": "1:41:40", "remaining_time": "0:04:35"}
+{"current_steps": 10720, "total_steps": 11193, "loss": 0.6729, "lr": 8.991602815939155e-06, "epoch": 0.9426661976785086, "percentage": 95.77, "elapsed_time": "1:43:34", "remaining_time": "0:04:34"}
+{"current_steps": 10730, "total_steps": 11193, "loss": 0.6423, "lr": 8.686536910109464e-06, "epoch": 0.9435455504748506, "percentage": 95.86, "elapsed_time": "1:45:28", "remaining_time": "0:04:33"}
+{"current_steps": 10740, "total_steps": 11193, "loss": 0.68, "lr": 8.382771972506084e-06, "epoch": 0.9444249032711924, "percentage": 95.95, "elapsed_time": "1:47:22", "remaining_time": "0:04:31"}
+{"current_steps": 10750, "total_steps": 11193, "loss": 0.6365, "lr": 8.08059784488198e-06, "epoch": 0.9453042560675343, "percentage": 96.04, "elapsed_time": "1:49:16", "remaining_time": "0:04:30"}
+{"current_steps": 10760, "total_steps": 11193, "loss": 0.6686, "lr": 7.780302851095544e-06, "epoch": 0.9461836088638762, "percentage": 96.13, "elapsed_time": "1:51:10", "remaining_time": "0:04:28"}
+{"current_steps": 10770, "total_steps": 11193, "loss": 0.6589, "lr": 7.482173522002166e-06, "epoch": 0.9470629616602181, "percentage": 96.22, "elapsed_time": "1:53:04", "remaining_time": "0:04:26"}
+{"current_steps": 10780, "total_steps": 11193, "loss": 0.6474, "lr": 7.186494322056624e-06, "epoch": 0.94794231445656, "percentage": 96.31, "elapsed_time": "1:54:58", "remaining_time": "0:04:24"}
+{"current_steps": 10790, "total_steps": 11193, "loss": 0.6718, "lr": 6.893547377887183e-06, "epoch": 0.9488216672529018, "percentage": 96.4, "elapsed_time": "1:56:52", "remaining_time": "0:04:21"}
+{"current_steps": 10800, "total_steps": 11193, "loss": 0.6547, "lr": 6.6036122091003365e-06, "epoch": 0.9497010200492437, "percentage": 96.49, "elapsed_time": "1:58:46", "remaining_time": "0:04:19"}
+{"current_steps": 10810, "total_steps": 11193, "loss": 0.6823, "lr": 6.316965461573097e-06, "epoch": 0.9505803728455856, "percentage": 96.58, "elapsed_time": "2:00:40", "remaining_time": "0:04:16"}
+{"current_steps": 10820, "total_steps": 11193, "loss": 0.6569, "lr": 6.0338806434872965e-06, "epoch": 0.9514597256419275, "percentage": 96.67, "elapsed_time": "2:02:53", "remaining_time": "0:04:14"}
+{"current_steps": 10830, "total_steps": 11193, "loss": 0.677, "lr": 5.754627864357749e-06, "epoch": 0.9523390784382695, "percentage": 96.76, "elapsed_time": "2:04:47", "remaining_time": "0:04:10"}
+{"current_steps": 10840, "total_steps": 11193, "loss": 0.6577, "lr": 5.479473577303319e-06, "epoch": 0.9532184312346114, "percentage": 96.85, "elapsed_time": "2:06:41", "remaining_time": "0:04:07"}
+{"current_steps": 10850, "total_steps": 11193, "loss": 0.6368, "lr": 5.208680324806778e-06, "epoch": 0.9540977840309532, "percentage": 96.94, "elapsed_time": "2:08:36", "remaining_time": "0:04:03"}
+{"current_steps": 10860, "total_steps": 11193, "loss": 0.6841, "lr": 4.94250648820606e-06, "epoch": 0.9549771368272951, "percentage": 97.02, "elapsed_time": "2:10:30", "remaining_time": "0:04:00"}
+{"current_steps": 10870, "total_steps": 11193, "loss": 0.6711, "lr": 4.681206041155951e-06, "epoch": 0.955856489623637, "percentage": 97.11, "elapsed_time": "2:12:24", "remaining_time": "0:03:56"}
+{"current_steps": 10880, "total_steps": 11193, "loss": 0.6687, "lr": 4.42502830729538e-06, "epoch": 0.9567358424199789, "percentage": 97.2, "elapsed_time": "2:14:19", "remaining_time": "0:03:51"}
+{"current_steps": 10890, "total_steps": 11193, "loss": 0.6626, "lr": 4.174217722351669e-06, "epoch": 0.9576151952163208, "percentage": 97.29, "elapsed_time": "2:16:13", "remaining_time": "0:03:47"}
+{"current_steps": 10900, "total_steps": 11193, "loss": 0.6627, "lr": 3.929013600908575e-06, "epoch": 0.9584945480126627, "percentage": 97.38, "elapsed_time": "2:18:08", "remaining_time": "0:03:42"}
+{"current_steps": 10910, "total_steps": 11193, "loss": 0.6792, "lr": 3.689649908060807e-06, "epoch": 0.9593739008090045, "percentage": 97.47, "elapsed_time": "2:20:02", "remaining_time": "0:03:37"}
+{"current_steps": 10920, "total_steps": 11193, "loss": 0.6594, "lr": 3.4563550361728028e-06, "epoch": 0.9602532536053464, "percentage": 97.56, "elapsed_time": "2:21:57", "remaining_time": "0:03:32"}
+{"current_steps": 10930, "total_steps": 11193, "loss": 0.6821, "lr": 3.2293515869548216e-06, "epoch": 0.9611326064016884, "percentage": 97.65, "elapsed_time": "2:23:51", "remaining_time": "0:03:27"}
+{"current_steps": 10940, "total_steps": 11193, "loss": 0.6479, "lr": 3.0088561590642746e-06, "epoch": 0.9620119591980303, "percentage": 97.74, "elapsed_time": "2:25:46", "remaining_time": "0:03:22"}
+{"current_steps": 10950, "total_steps": 11193, "loss": 0.6547, "lr": 2.795079141434941e-06, "epoch": 0.9628913119943722, "percentage": 97.83, "elapsed_time": "2:27:40", "remaining_time": "0:03:16"}
+{"current_steps": 10960, "total_steps": 11193, "loss": 0.6708, "lr": 2.588224512531299e-06, "epoch": 0.963770664790714, "percentage": 97.92, "elapsed_time": "2:29:35", "remaining_time": "0:03:10"}
+{"current_steps": 10970, "total_steps": 11193, "loss": 0.6579, "lr": 2.388489645719495e-06, "epoch": 0.9646500175870559, "percentage": 98.01, "elapsed_time": "2:31:29", "remaining_time": "0:03:04"}
+{"current_steps": 10980, "total_steps": 11193, "loss": 0.6475, "lr": 2.196065120940663e-06, "epoch": 0.9655293703833978, "percentage": 98.1, "elapsed_time": "2:33:24", "remaining_time": "0:02:58"}
+{"current_steps": 10990, "total_steps": 11193, "loss": 0.6531, "lr": 2.0111345428662808e-06, "epoch": 0.9664087231797397, "percentage": 98.19, "elapsed_time": "2:35:18", "remaining_time": "0:02:52"}
+{"current_steps": 11000, "total_steps": 11193, "loss": 0.6587, "lr": 1.8338743657091102e-06, "epoch": 0.9672880759760816, "percentage": 98.28, "elapsed_time": "2:37:13", "remaining_time": "0:02:45"}
+{"current_steps": 11010, "total_steps": 11193, "loss": 0.6686, "lr": 1.6644537248568113e-06, "epoch": 0.9681674287724235, "percentage": 98.37, "elapsed_time": "2:39:07", "remaining_time": "0:02:38"}
+{"current_steps": 11020, "total_steps": 11193, "loss": 0.6693, "lr": 1.503034275488951e-06, "epoch": 0.9690467815687653, "percentage": 98.45, "elapsed_time": "2:41:02", "remaining_time": "0:02:31"}
+{"current_steps": 11030, "total_steps": 11193, "loss": 0.6651, "lr": 1.3497700383313495e-06, "epoch": 0.9699261343651073, "percentage": 98.54, "elapsed_time": "2:42:56", "remaining_time": "0:02:24"}
+{"current_steps": 11040, "total_steps": 11193, "loss": 0.6508, "lr": 1.2048072526949562e-06, "epoch": 0.9708054871614492, "percentage": 98.63, "elapsed_time": "2:44:50", "remaining_time": "0:02:17"}
+{"current_steps": 11050, "total_steps": 11193, "loss": 0.6499, "lr": 1.0682842369394756e-06, "epoch": 0.9716848399577911, "percentage": 98.72, "elapsed_time": "2:46:44", "remaining_time": "0:02:09"}
+{"current_steps": 11060, "total_steps": 11193, "loss": 0.6548, "lr": 9.403312564948792e-07, "epoch": 0.972564192754133, "percentage": 98.81, "elapsed_time": "2:48:38", "remaining_time": "0:02:01"}
+{"current_steps": 11070, "total_steps": 11193, "loss": 0.6692, "lr": 8.210703995667471e-07, "epoch": 0.9734435455504749, "percentage": 98.9, "elapsed_time": "2:50:32", "remaining_time": "0:01:53"}
+{"current_steps": 11080, "total_steps": 11193, "loss": 0.6301, "lr": 7.106154606440245e-07, "epoch": 0.9743228983468167, "percentage": 98.99, "elapsed_time": "2:52:27", "remaining_time": "0:01:45"}
+{"current_steps": 11090, "total_steps": 11193, "loss": 0.6672, "lr": 6.090718319203393e-07, "epoch": 0.9752022511431586, "percentage": 99.08, "elapsed_time": "2:54:20", "remaining_time": "0:01:37"}
+{"current_steps": 11100, "total_steps": 11193, "loss": 0.673, "lr": 5.165364027325089e-07, "epoch": 0.9760816039395005, "percentage": 99.17, "elapsed_time": "2:56:14", "remaining_time": "0:01:28"}
+{"current_steps": 11110, "total_steps": 11193, "loss": 0.6957, "lr": 4.330974671121585e-07, "epoch": 0.9769609567358424, "percentage": 99.26, "elapsed_time": "2:58:08", "remaining_time": "0:01:19"}
+{"current_steps": 11120, "total_steps": 11193, "loss": 0.6742, "lr": 3.588346395386846e-07, "epoch": 0.9778403095321843, "percentage": 99.35, "elapsed_time": "3:00:02", "remaining_time": "0:01:10"}
+{"current_steps": 11130, "total_steps": 11193, "loss": 0.6281, "lr": 2.938187789739395e-07, "epoch": 0.9787196623285263, "percentage": 99.44, "elapsed_time": "3:01:56", "remaining_time": "0:01:01"}
+{"current_steps": 11140, "total_steps": 11193, "loss": 0.6494, "lr": 2.3811192125110724e-07, "epoch": 0.9795990151248681, "percentage": 99.53, "elapsed_time": "3:03:50", "remaining_time": "0:00:52"}
+{"current_steps": 11150, "total_steps": 11193, "loss": 0.6405, "lr": 1.917672198823177e-07, "epoch": 0.98047836792121, "percentage": 99.62, "elapsed_time": "3:05:44", "remaining_time": "0:00:42"}
+{"current_steps": 11160, "total_steps": 11193, "loss": 0.6662, "lr": 1.5482889534143795e-07, "epoch": 0.9813577207175519, "percentage": 99.71, "elapsed_time": "3:07:38", "remaining_time": "0:00:33"}
+{"current_steps": 11170, "total_steps": 11193, "loss": 0.675, "lr": 1.273321928704694e-07, "epoch": 0.9822370735138938, "percentage": 99.79, "elapsed_time": "3:09:32", "remaining_time": "0:00:23"}
+{"current_steps": 11180, "total_steps": 11193, "loss": 0.6596, "lr": 1.0930334884977866e-07, "epoch": 0.9831164263102357, "percentage": 99.88, "elapsed_time": "3:11:26", "remaining_time": "0:00:13"}
+{"current_steps": 11190, "total_steps": 11193, "loss": 0.6568, "lr": 1.0075956576427487e-07, "epoch": 0.9839957791065775, "percentage": 99.97, "elapsed_time": "3:13:20", "remaining_time": "0:00:03"}
+{"current_steps": 11193, "total_steps": 11193, "epoch": 0.9842595849454802, "percentage": 100.0, "elapsed_time": "3:14:13", "remaining_time": "0:00:00"}

g2_5_plan_newcode/1000M/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b03884b0d3adaca694a8ffc5e16e30fee669df62df05096c31d27de133b8cf
+size 9105