初始化项目，由ModelHub XC社区提供模型

Model: OP12138/qwen3-4b-safechain
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-4B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft-v1
+  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. -->
+
+# sft-v1
+
+This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the safechain 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: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.11.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 2.46059940019431e+18,
+    "train_loss": 0.7171756315231324,
+    "train_runtime": 37151.4848,
+    "train_samples_per_second": 2.153,
+    "train_steps_per_second": 0.135
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.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' }}
+        {{- 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 %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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": 40960,
+  "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": true,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97967d7449c7023989321d7810c1c52a63933213e8900de8ddc120e87f165dce
+size 4990095032

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2417c185f9df505da78dc740a68eab31a525ff6759b7e498e95514458b91ba84
+size 4944309096

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0127d5dc97eaf76a0153d7819f0b3406dbced35307cc44c8cd4d1d775c628674
+size 4996758848

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2610c8961f1f4c819cadf0517e4990db4353f5d3a5e46e5ae1fea76e2481a111
+size 1158754848

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 16089872384
+  },
+  "weight_map": {
+    "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-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-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-00003-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-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_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-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-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-00004-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-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-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_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-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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer_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": "<|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
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 2.46059940019431e+18,
+    "train_loss": 0.7171756315231324,
+    "train_runtime": 37151.4848,
+    "train_samples_per_second": 2.153,
+    "train_steps_per_second": 0.135
+}

trainer_log.jsonl

@@ -0,0 +1,251 @@
+{"current_steps": 20, "total_steps": 5000, "loss": 1.3021, "lr": 3.8e-07, "epoch": 0.008, "percentage": 0.4, "elapsed_time": "0:02:23", "remaining_time": "9:53:33"}
+{"current_steps": 40, "total_steps": 5000, "loss": 1.2112, "lr": 7.8e-07, "epoch": 0.016, "percentage": 0.8, "elapsed_time": "0:04:46", "remaining_time": "9:52:59"}
+{"current_steps": 60, "total_steps": 5000, "loss": 1.0085, "lr": 1.1800000000000001e-06, "epoch": 0.024, "percentage": 1.2, "elapsed_time": "0:07:09", "remaining_time": "9:49:40"}
+{"current_steps": 80, "total_steps": 5000, "loss": 0.9484, "lr": 1.5800000000000001e-06, "epoch": 0.032, "percentage": 1.6, "elapsed_time": "0:09:39", "remaining_time": "9:53:51"}
+{"current_steps": 100, "total_steps": 5000, "loss": 0.9203, "lr": 1.98e-06, "epoch": 0.04, "percentage": 2.0, "elapsed_time": "0:12:20", "remaining_time": "10:04:55"}
+{"current_steps": 120, "total_steps": 5000, "loss": 0.9135, "lr": 2.38e-06, "epoch": 0.048, "percentage": 2.4, "elapsed_time": "0:14:49", "remaining_time": "10:02:35"}
+{"current_steps": 140, "total_steps": 5000, "loss": 0.9045, "lr": 2.7800000000000005e-06, "epoch": 0.056, "percentage": 2.8, "elapsed_time": "0:17:14", "remaining_time": "9:58:15"}
+{"current_steps": 160, "total_steps": 5000, "loss": 0.9032, "lr": 3.1800000000000005e-06, "epoch": 0.064, "percentage": 3.2, "elapsed_time": "0:19:47", "remaining_time": "9:58:51"}
+{"current_steps": 180, "total_steps": 5000, "loss": 0.881, "lr": 3.58e-06, "epoch": 0.072, "percentage": 3.6, "elapsed_time": "0:22:14", "remaining_time": "9:55:32"}
+{"current_steps": 200, "total_steps": 5000, "loss": 0.89, "lr": 3.980000000000001e-06, "epoch": 0.08, "percentage": 4.0, "elapsed_time": "0:24:57", "remaining_time": "9:58:56"}
+{"current_steps": 220, "total_steps": 5000, "loss": 0.8808, "lr": 4.38e-06, "epoch": 0.088, "percentage": 4.4, "elapsed_time": "0:27:19", "remaining_time": "9:53:42"}
+{"current_steps": 240, "total_steps": 5000, "loss": 0.8928, "lr": 4.78e-06, "epoch": 0.096, "percentage": 4.8, "elapsed_time": "0:29:45", "remaining_time": "9:50:21"}
+{"current_steps": 260, "total_steps": 5000, "loss": 0.8817, "lr": 5.18e-06, "epoch": 0.104, "percentage": 5.2, "elapsed_time": "0:32:13", "remaining_time": "9:47:24"}
+{"current_steps": 280, "total_steps": 5000, "loss": 0.8859, "lr": 5.580000000000001e-06, "epoch": 0.112, "percentage": 5.6, "elapsed_time": "0:34:40", "remaining_time": "9:44:27"}
+{"current_steps": 300, "total_steps": 5000, "loss": 0.8658, "lr": 5.98e-06, "epoch": 0.12, "percentage": 6.0, "elapsed_time": "0:37:10", "remaining_time": "9:42:31"}
+{"current_steps": 320, "total_steps": 5000, "loss": 0.8688, "lr": 6.380000000000001e-06, "epoch": 0.128, "percentage": 6.4, "elapsed_time": "0:39:33", "remaining_time": "9:38:37"}
+{"current_steps": 340, "total_steps": 5000, "loss": 0.8642, "lr": 6.780000000000001e-06, "epoch": 0.136, "percentage": 6.8, "elapsed_time": "0:41:55", "remaining_time": "9:34:39"}
+{"current_steps": 360, "total_steps": 5000, "loss": 0.8694, "lr": 7.180000000000001e-06, "epoch": 0.144, "percentage": 7.2, "elapsed_time": "0:44:20", "remaining_time": "9:31:34"}
+{"current_steps": 380, "total_steps": 5000, "loss": 0.8823, "lr": 7.58e-06, "epoch": 0.152, "percentage": 7.6, "elapsed_time": "0:46:42", "remaining_time": "9:27:48"}
+{"current_steps": 400, "total_steps": 5000, "loss": 0.8616, "lr": 7.980000000000002e-06, "epoch": 0.16, "percentage": 8.0, "elapsed_time": "0:49:14", "remaining_time": "9:26:21"}
+{"current_steps": 420, "total_steps": 5000, "loss": 0.879, "lr": 8.380000000000001e-06, "epoch": 0.168, "percentage": 8.4, "elapsed_time": "0:51:42", "remaining_time": "9:23:48"}
+{"current_steps": 440, "total_steps": 5000, "loss": 0.8707, "lr": 8.78e-06, "epoch": 0.176, "percentage": 8.8, "elapsed_time": "0:54:06", "remaining_time": "9:20:40"}
+{"current_steps": 460, "total_steps": 5000, "loss": 0.8734, "lr": 9.180000000000002e-06, "epoch": 0.184, "percentage": 9.2, "elapsed_time": "0:56:31", "remaining_time": "9:17:51"}
+{"current_steps": 480, "total_steps": 5000, "loss": 0.8724, "lr": 9.58e-06, "epoch": 0.192, "percentage": 9.6, "elapsed_time": "0:58:57", "remaining_time": "9:15:12"}
+{"current_steps": 500, "total_steps": 5000, "loss": 0.8805, "lr": 9.980000000000001e-06, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "1:01:34", "remaining_time": "9:14:13"}
+{"current_steps": 520, "total_steps": 5000, "loss": 0.8781, "lr": 9.999560138895238e-06, "epoch": 0.208, "percentage": 10.4, "elapsed_time": "1:04:06", "remaining_time": "9:12:22"}
+{"current_steps": 540, "total_steps": 5000, "loss": 0.8495, "lr": 9.998146822104943e-06, "epoch": 0.216, "percentage": 10.8, "elapsed_time": "1:06:39", "remaining_time": "9:10:29"}
+{"current_steps": 560, "total_steps": 5000, "loss": 0.8514, "lr": 9.995759106688394e-06, "epoch": 0.224, "percentage": 11.2, "elapsed_time": "1:09:08", "remaining_time": "9:08:11"}
+{"current_steps": 580, "total_steps": 5000, "loss": 0.8619, "lr": 9.992397458135438e-06, "epoch": 0.232, "percentage": 11.6, "elapsed_time": "1:11:36", "remaining_time": "9:05:44"}
+{"current_steps": 600, "total_steps": 5000, "loss": 0.8689, "lr": 9.988062531806127e-06, "epoch": 0.24, "percentage": 12.0, "elapsed_time": "1:14:04", "remaining_time": "9:03:13"}
+{"current_steps": 620, "total_steps": 5000, "loss": 0.8694, "lr": 9.982755172802933e-06, "epoch": 0.248, "percentage": 12.4, "elapsed_time": "1:16:29", "remaining_time": "9:00:23"}
+{"current_steps": 640, "total_steps": 5000, "loss": 0.8604, "lr": 9.976476415806013e-06, "epoch": 0.256, "percentage": 12.8, "elapsed_time": "1:19:01", "remaining_time": "8:58:24"}
+{"current_steps": 660, "total_steps": 5000, "loss": 0.8483, "lr": 9.969227484871485e-06, "epoch": 0.264, "percentage": 13.2, "elapsed_time": "1:21:36", "remaining_time": "8:56:41"}
+{"current_steps": 680, "total_steps": 5000, "loss": 0.8356, "lr": 9.961009793192793e-06, "epoch": 0.272, "percentage": 13.6, "elapsed_time": "1:24:14", "remaining_time": "8:55:09"}
+{"current_steps": 700, "total_steps": 5000, "loss": 0.8524, "lr": 9.951824942825215e-06, "epoch": 0.28, "percentage": 14.0, "elapsed_time": "1:26:43", "remaining_time": "8:52:44"}
+{"current_steps": 720, "total_steps": 5000, "loss": 0.8541, "lr": 9.94167472437353e-06, "epoch": 0.288, "percentage": 14.4, "elapsed_time": "1:29:13", "remaining_time": "8:50:25"}
+{"current_steps": 740, "total_steps": 5000, "loss": 0.8303, "lr": 9.930561116642936e-06, "epoch": 0.296, "percentage": 14.8, "elapsed_time": "1:31:58", "remaining_time": "8:49:29"}
+{"current_steps": 760, "total_steps": 5000, "loss": 0.876, "lr": 9.918486286253279e-06, "epoch": 0.304, "percentage": 15.2, "elapsed_time": "1:34:23", "remaining_time": "8:46:38"}
+{"current_steps": 780, "total_steps": 5000, "loss": 0.8503, "lr": 9.90545258721667e-06, "epoch": 0.312, "percentage": 15.6, "elapsed_time": "1:36:48", "remaining_time": "8:43:46"}
+{"current_steps": 800, "total_steps": 5000, "loss": 0.8481, "lr": 9.891462560478562e-06, "epoch": 0.32, "percentage": 16.0, "elapsed_time": "1:39:13", "remaining_time": "8:40:57"}
+{"current_steps": 820, "total_steps": 5000, "loss": 0.837, "lr": 9.876518933422385e-06, "epoch": 0.328, "percentage": 16.4, "elapsed_time": "1:41:53", "remaining_time": "8:39:25"}
+{"current_steps": 840, "total_steps": 5000, "loss": 0.8564, "lr": 9.860624619337844e-06, "epoch": 0.336, "percentage": 16.8, "elapsed_time": "1:44:23", "remaining_time": "8:36:59"}
+{"current_steps": 860, "total_steps": 5000, "loss": 0.852, "lr": 9.843782716852963e-06, "epoch": 0.344, "percentage": 17.2, "elapsed_time": "1:46:56", "remaining_time": "8:34:49"}
+{"current_steps": 880, "total_steps": 5000, "loss": 0.8368, "lr": 9.825996509330001e-06, "epoch": 0.352, "percentage": 17.6, "elapsed_time": "1:49:15", "remaining_time": "8:31:31"}
+{"current_steps": 900, "total_steps": 5000, "loss": 0.842, "lr": 9.807269464225355e-06, "epoch": 0.36, "percentage": 18.0, "elapsed_time": "1:51:37", "remaining_time": "8:28:29"}
+{"current_steps": 920, "total_steps": 5000, "loss": 0.8434, "lr": 9.787605232413575e-06, "epoch": 0.368, "percentage": 18.4, "elapsed_time": "1:54:09", "remaining_time": "8:26:14"}
+{"current_steps": 940, "total_steps": 5000, "loss": 0.8458, "lr": 9.767007647475618e-06, "epoch": 0.376, "percentage": 18.8, "elapsed_time": "1:56:29", "remaining_time": "8:23:08"}
+{"current_steps": 960, "total_steps": 5000, "loss": 0.8429, "lr": 9.745480724951473e-06, "epoch": 0.384, "percentage": 19.2, "elapsed_time": "1:58:54", "remaining_time": "8:20:24"}
+{"current_steps": 980, "total_steps": 5000, "loss": 0.827, "lr": 9.723028661557345e-06, "epoch": 0.392, "percentage": 19.6, "elapsed_time": "2:01:35", "remaining_time": "8:18:45"}
+{"current_steps": 1000, "total_steps": 5000, "loss": 0.8311, "lr": 9.699655834367479e-06, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "2:03:58", "remaining_time": "8:15:53"}
+{"current_steps": 1020, "total_steps": 5000, "loss": 0.8218, "lr": 9.675366799960842e-06, "epoch": 0.408, "percentage": 20.4, "elapsed_time": "2:06:57", "remaining_time": "8:15:21"}
+{"current_steps": 1040, "total_steps": 5000, "loss": 0.832, "lr": 9.650166293532822e-06, "epoch": 0.416, "percentage": 20.8, "elapsed_time": "2:09:23", "remaining_time": "8:12:41"}
+{"current_steps": 1060, "total_steps": 5000, "loss": 0.8501, "lr": 9.624059227972077e-06, "epoch": 0.424, "percentage": 21.2, "elapsed_time": "2:11:49", "remaining_time": "8:10:01"}
+{"current_steps": 1080, "total_steps": 5000, "loss": 0.8258, "lr": 9.597050692902765e-06, "epoch": 0.432, "percentage": 21.6, "elapsed_time": "2:14:12", "remaining_time": "8:07:08"}
+{"current_steps": 1100, "total_steps": 5000, "loss": 0.8516, "lr": 9.569145953692316e-06, "epoch": 0.44, "percentage": 22.0, "elapsed_time": "2:16:38", "remaining_time": "8:04:26"}
+{"current_steps": 1120, "total_steps": 5000, "loss": 0.8351, "lr": 9.540350450424927e-06, "epoch": 0.448, "percentage": 22.4, "elapsed_time": "2:19:05", "remaining_time": "8:01:52"}
+{"current_steps": 1140, "total_steps": 5000, "loss": 0.8346, "lr": 9.510669796841014e-06, "epoch": 0.456, "percentage": 22.8, "elapsed_time": "2:21:26", "remaining_time": "7:58:54"}
+{"current_steps": 1160, "total_steps": 5000, "loss": 0.8399, "lr": 9.480109779242805e-06, "epoch": 0.464, "percentage": 23.2, "elapsed_time": "2:23:55", "remaining_time": "7:56:25"}
+{"current_steps": 1180, "total_steps": 5000, "loss": 0.8477, "lr": 9.448676355366282e-06, "epoch": 0.472, "percentage": 23.6, "elapsed_time": "2:26:22", "remaining_time": "7:53:50"}
+{"current_steps": 1200, "total_steps": 5000, "loss": 0.8382, "lr": 9.41637565321971e-06, "epoch": 0.48, "percentage": 24.0, "elapsed_time": "2:28:45", "remaining_time": "7:51:04"}
+{"current_steps": 1220, "total_steps": 5000, "loss": 0.8182, "lr": 9.383213969888972e-06, "epoch": 0.488, "percentage": 24.4, "elapsed_time": "2:31:14", "remaining_time": "7:48:35"}
+{"current_steps": 1240, "total_steps": 5000, "loss": 0.8161, "lr": 9.349197770309942e-06, "epoch": 0.496, "percentage": 24.8, "elapsed_time": "2:33:48", "remaining_time": "7:46:23"}
+{"current_steps": 1260, "total_steps": 5000, "loss": 0.8179, "lr": 9.314333686008125e-06, "epoch": 0.504, "percentage": 25.2, "elapsed_time": "2:36:11", "remaining_time": "7:43:35"}
+{"current_steps": 1280, "total_steps": 5000, "loss": 0.8348, "lr": 9.278628513805838e-06, "epoch": 0.512, "percentage": 25.6, "elapsed_time": "2:38:38", "remaining_time": "7:41:03"}
+{"current_steps": 1300, "total_steps": 5000, "loss": 0.8421, "lr": 9.242089214497146e-06, "epoch": 0.52, "percentage": 26.0, "elapsed_time": "2:41:02", "remaining_time": "7:38:20"}
+{"current_steps": 1320, "total_steps": 5000, "loss": 0.8266, "lr": 9.204722911490847e-06, "epoch": 0.528, "percentage": 26.4, "elapsed_time": "2:43:27", "remaining_time": "7:35:42"}
+{"current_steps": 1340, "total_steps": 5000, "loss": 0.8465, "lr": 9.16653688942175e-06, "epoch": 0.536, "percentage": 26.8, "elapsed_time": "2:45:49", "remaining_time": "7:32:56"}
+{"current_steps": 1360, "total_steps": 5000, "loss": 0.8253, "lr": 9.12753859273052e-06, "epoch": 0.544, "percentage": 27.2, "elapsed_time": "2:48:18", "remaining_time": "7:30:28"}
+{"current_steps": 1380, "total_steps": 5000, "loss": 0.827, "lr": 9.087735624212365e-06, "epoch": 0.552, "percentage": 27.6, "elapsed_time": "2:50:47", "remaining_time": "7:28:01"}
+{"current_steps": 1400, "total_steps": 5000, "loss": 0.83, "lr": 9.047135743534866e-06, "epoch": 0.56, "percentage": 28.0, "elapsed_time": "2:53:24", "remaining_time": "7:25:54"}
+{"current_steps": 1420, "total_steps": 5000, "loss": 0.8083, "lr": 9.005746865725206e-06, "epoch": 0.568, "percentage": 28.4, "elapsed_time": "2:55:49", "remaining_time": "7:23:15"}
+{"current_steps": 1440, "total_steps": 5000, "loss": 0.8223, "lr": 8.963577059627117e-06, "epoch": 0.576, "percentage": 28.8, "elapsed_time": "2:58:10", "remaining_time": "7:20:29"}
+{"current_steps": 1460, "total_steps": 5000, "loss": 0.8317, "lr": 8.920634546327857e-06, "epoch": 0.584, "percentage": 29.2, "elapsed_time": "3:00:35", "remaining_time": "7:17:51"}
+{"current_steps": 1480, "total_steps": 5000, "loss": 0.8232, "lr": 8.87692769755548e-06, "epoch": 0.592, "percentage": 29.6, "elapsed_time": "3:03:10", "remaining_time": "7:15:38"}
+{"current_steps": 1500, "total_steps": 5000, "loss": 0.8322, "lr": 8.83246503404675e-06, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "3:05:43", "remaining_time": "7:13:21"}
+{"current_steps": 1520, "total_steps": 5000, "loss": 0.8306, "lr": 8.78725522388602e-06, "epoch": 0.608, "percentage": 30.4, "elapsed_time": "3:08:07", "remaining_time": "7:10:42"}
+{"current_steps": 1540, "total_steps": 5000, "loss": 0.816, "lr": 8.741307080815357e-06, "epoch": 0.616, "percentage": 30.8, "elapsed_time": "3:10:27", "remaining_time": "7:07:55"}
+{"current_steps": 1560, "total_steps": 5000, "loss": 0.8267, "lr": 8.694629562516295e-06, "epoch": 0.624, "percentage": 31.2, "elapsed_time": "3:12:52", "remaining_time": "7:05:19"}
+{"current_steps": 1580, "total_steps": 5000, "loss": 0.8065, "lr": 8.647231768863513e-06, "epoch": 0.632, "percentage": 31.6, "elapsed_time": "3:15:24", "remaining_time": "7:02:57"}
+{"current_steps": 1600, "total_steps": 5000, "loss": 0.8195, "lr": 8.599122940150795e-06, "epoch": 0.64, "percentage": 32.0, "elapsed_time": "3:17:48", "remaining_time": "7:00:20"}
+{"current_steps": 1620, "total_steps": 5000, "loss": 0.8092, "lr": 8.550312455289624e-06, "epoch": 0.648, "percentage": 32.4, "elapsed_time": "3:20:20", "remaining_time": "6:58:00"}
+{"current_steps": 1640, "total_steps": 5000, "loss": 0.8105, "lr": 8.500809829980734e-06, "epoch": 0.656, "percentage": 32.8, "elapsed_time": "3:22:58", "remaining_time": "6:55:51"}
+{"current_steps": 1660, "total_steps": 5000, "loss": 0.8035, "lr": 8.450624714859016e-06, "epoch": 0.664, "percentage": 33.2, "elapsed_time": "3:25:35", "remaining_time": "6:53:40"}
+{"current_steps": 1680, "total_steps": 5000, "loss": 0.8179, "lr": 8.399766893612096e-06, "epoch": 0.672, "percentage": 33.6, "elapsed_time": "3:28:01", "remaining_time": "6:51:05"}
+{"current_steps": 1700, "total_steps": 5000, "loss": 0.7876, "lr": 8.348246281072998e-06, "epoch": 0.68, "percentage": 34.0, "elapsed_time": "3:30:23", "remaining_time": "6:48:24"}
+{"current_steps": 1720, "total_steps": 5000, "loss": 0.8193, "lr": 8.296072921287217e-06, "epoch": 0.688, "percentage": 34.4, "elapsed_time": "3:32:43", "remaining_time": "6:45:39"}
+{"current_steps": 1740, "total_steps": 5000, "loss": 0.8192, "lr": 8.243256985554622e-06, "epoch": 0.696, "percentage": 34.8, "elapsed_time": "3:35:08", "remaining_time": "6:43:05"}
+{"current_steps": 1760, "total_steps": 5000, "loss": 0.8128, "lr": 8.189808770446528e-06, "epoch": 0.704, "percentage": 35.2, "elapsed_time": "3:37:42", "remaining_time": "6:40:47"}
+{"current_steps": 1780, "total_steps": 5000, "loss": 0.8118, "lr": 8.135738695798377e-06, "epoch": 0.712, "percentage": 35.6, "elapsed_time": "3:40:11", "remaining_time": "6:38:19"}
+{"current_steps": 1800, "total_steps": 5000, "loss": 0.8081, "lr": 8.081057302678352e-06, "epoch": 0.72, "percentage": 36.0, "elapsed_time": "3:42:54", "remaining_time": "6:36:17"}
+{"current_steps": 1820, "total_steps": 5000, "loss": 0.8222, "lr": 8.02577525133239e-06, "epoch": 0.728, "percentage": 36.4, "elapsed_time": "3:45:16", "remaining_time": "6:33:36"}
+{"current_steps": 1840, "total_steps": 5000, "loss": 0.8263, "lr": 7.969903319105935e-06, "epoch": 0.736, "percentage": 36.8, "elapsed_time": "3:47:39", "remaining_time": "6:30:58"}
+{"current_steps": 1860, "total_steps": 5000, "loss": 0.8154, "lr": 7.913452398342882e-06, "epoch": 0.744, "percentage": 37.2, "elapsed_time": "3:50:07", "remaining_time": "6:28:28"}
+{"current_steps": 1880, "total_steps": 5000, "loss": 0.8073, "lr": 7.856433494262078e-06, "epoch": 0.752, "percentage": 37.6, "elapsed_time": "3:52:34", "remaining_time": "6:25:58"}
+{"current_steps": 1900, "total_steps": 5000, "loss": 0.8127, "lr": 7.798857722811857e-06, "epoch": 0.76, "percentage": 38.0, "elapsed_time": "3:54:56", "remaining_time": "6:23:19"}
+{"current_steps": 1920, "total_steps": 5000, "loss": 0.7946, "lr": 7.740736308502939e-06, "epoch": 0.768, "percentage": 38.4, "elapsed_time": "3:57:28", "remaining_time": "6:20:56"}
+{"current_steps": 1940, "total_steps": 5000, "loss": 0.8081, "lr": 7.682080582220206e-06, "epoch": 0.776, "percentage": 38.8, "elapsed_time": "3:59:51", "remaining_time": "6:18:19"}
+{"current_steps": 1960, "total_steps": 5000, "loss": 0.7946, "lr": 7.622901979013717e-06, "epoch": 0.784, "percentage": 39.2, "elapsed_time": "4:02:19", "remaining_time": "6:15:51"}
+{"current_steps": 1980, "total_steps": 5000, "loss": 0.8156, "lr": 7.563212035869426e-06, "epoch": 0.792, "percentage": 39.6, "elapsed_time": "4:04:46", "remaining_time": "6:13:21"}
+{"current_steps": 2000, "total_steps": 5000, "loss": 0.8137, "lr": 7.503022389460014e-06, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "4:07:14", "remaining_time": "6:10:52"}
+{"current_steps": 2020, "total_steps": 5000, "loss": 0.8045, "lr": 7.44234477387631e-06, "epoch": 0.808, "percentage": 40.4, "elapsed_time": "4:09:50", "remaining_time": "6:08:34"}
+{"current_steps": 2040, "total_steps": 5000, "loss": 0.7921, "lr": 7.381191018339697e-06, "epoch": 0.816, "percentage": 40.8, "elapsed_time": "4:12:18", "remaining_time": "6:06:05"}
+{"current_steps": 2060, "total_steps": 5000, "loss": 0.7882, "lr": 7.319573044895986e-06, "epoch": 0.824, "percentage": 41.2, "elapsed_time": "4:14:55", "remaining_time": "6:03:49"}
+{"current_steps": 2080, "total_steps": 5000, "loss": 0.8121, "lr": 7.257502866091192e-06, "epoch": 0.832, "percentage": 41.6, "elapsed_time": "4:17:22", "remaining_time": "6:01:19"}
+{"current_steps": 2100, "total_steps": 5000, "loss": 0.8066, "lr": 7.194992582629654e-06, "epoch": 0.84, "percentage": 42.0, "elapsed_time": "4:19:48", "remaining_time": "5:58:47"}
+{"current_steps": 2120, "total_steps": 5000, "loss": 0.7999, "lr": 7.1320543810149945e-06, "epoch": 0.848, "percentage": 42.4, "elapsed_time": "4:22:23", "remaining_time": "5:56:27"}
+{"current_steps": 2140, "total_steps": 5000, "loss": 0.8009, "lr": 7.0687005311743195e-06, "epoch": 0.856, "percentage": 42.8, "elapsed_time": "4:24:54", "remaining_time": "5:54:02"}
+{"current_steps": 2160, "total_steps": 5000, "loss": 0.8059, "lr": 7.0049433840661875e-06, "epoch": 0.864, "percentage": 43.2, "elapsed_time": "4:27:15", "remaining_time": "5:51:24"}
+{"current_steps": 2180, "total_steps": 5000, "loss": 0.8054, "lr": 6.940795369272754e-06, "epoch": 0.872, "percentage": 43.6, "elapsed_time": "4:29:48", "remaining_time": "5:49:00"}
+{"current_steps": 2200, "total_steps": 5000, "loss": 0.7843, "lr": 6.876268992576605e-06, "epoch": 0.88, "percentage": 44.0, "elapsed_time": "4:32:28", "remaining_time": "5:46:46"}
+{"current_steps": 2220, "total_steps": 5000, "loss": 0.7797, "lr": 6.811376833522729e-06, "epoch": 0.888, "percentage": 44.4, "elapsed_time": "4:35:07", "remaining_time": "5:44:31"}
+{"current_steps": 2240, "total_steps": 5000, "loss": 0.8049, "lr": 6.746131542966112e-06, "epoch": 0.896, "percentage": 44.8, "elapsed_time": "4:37:38", "remaining_time": "5:42:05"}
+{"current_steps": 2260, "total_steps": 5000, "loss": 0.8001, "lr": 6.680545840605423e-06, "epoch": 0.904, "percentage": 45.2, "elapsed_time": "4:40:07", "remaining_time": "5:39:37"}
+{"current_steps": 2280, "total_steps": 5000, "loss": 0.7969, "lr": 6.614632512503289e-06, "epoch": 0.912, "percentage": 45.6, "elapsed_time": "4:42:31", "remaining_time": "5:37:02"}
+{"current_steps": 2300, "total_steps": 5000, "loss": 0.807, "lr": 6.548404408593622e-06, "epoch": 0.92, "percentage": 46.0, "elapsed_time": "4:44:54", "remaining_time": "5:34:27"}
+{"current_steps": 2320, "total_steps": 5000, "loss": 0.7973, "lr": 6.481874440176506e-06, "epoch": 0.928, "percentage": 46.4, "elapsed_time": "4:47:19", "remaining_time": "5:31:54"}
+{"current_steps": 2340, "total_steps": 5000, "loss": 0.7843, "lr": 6.415055577401101e-06, "epoch": 0.936, "percentage": 46.8, "elapsed_time": "4:49:48", "remaining_time": "5:29:26"}
+{"current_steps": 2360, "total_steps": 5000, "loss": 0.783, "lr": 6.3479608467371055e-06, "epoch": 0.944, "percentage": 47.2, "elapsed_time": "4:52:17", "remaining_time": "5:26:58"}
+{"current_steps": 2380, "total_steps": 5000, "loss": 0.7784, "lr": 6.280603328435199e-06, "epoch": 0.952, "percentage": 47.6, "elapsed_time": "4:54:44", "remaining_time": "5:24:28"}
+{"current_steps": 2400, "total_steps": 5000, "loss": 0.797, "lr": 6.212996153977038e-06, "epoch": 0.96, "percentage": 48.0, "elapsed_time": "4:57:17", "remaining_time": "5:22:03"}
+{"current_steps": 2420, "total_steps": 5000, "loss": 0.7918, "lr": 6.145152503515239e-06, "epoch": 0.968, "percentage": 48.4, "elapsed_time": "4:59:40", "remaining_time": "5:19:29"}
+{"current_steps": 2440, "total_steps": 5000, "loss": 0.7972, "lr": 6.077085603303883e-06, "epoch": 0.976, "percentage": 48.8, "elapsed_time": "5:02:07", "remaining_time": "5:16:58"}
+{"current_steps": 2460, "total_steps": 5000, "loss": 0.7931, "lr": 6.008808723120035e-06, "epoch": 0.984, "percentage": 49.2, "elapsed_time": "5:04:40", "remaining_time": "5:14:35"}
+{"current_steps": 2480, "total_steps": 5000, "loss": 0.7893, "lr": 5.94033517367677e-06, "epoch": 0.992, "percentage": 49.6, "elapsed_time": "5:07:14", "remaining_time": "5:12:11"}
+{"current_steps": 2500, "total_steps": 5000, "loss": 0.7937, "lr": 5.871678304028224e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "5:09:36", "remaining_time": "5:09:36"}
+{"current_steps": 2520, "total_steps": 5000, "loss": 0.6091, "lr": 5.802851498967173e-06, "epoch": 1.008, "percentage": 50.4, "elapsed_time": "5:11:59", "remaining_time": "5:07:01"}
+{"current_steps": 2540, "total_steps": 5000, "loss": 0.6033, "lr": 5.733868176415633e-06, "epoch": 1.016, "percentage": 50.8, "elapsed_time": "5:14:22", "remaining_time": "5:04:28"}
+{"current_steps": 2560, "total_steps": 5000, "loss": 0.6056, "lr": 5.6647417848090225e-06, "epoch": 1.024, "percentage": 51.2, "elapsed_time": "5:16:49", "remaining_time": "5:01:58"}
+{"current_steps": 2580, "total_steps": 5000, "loss": 0.6035, "lr": 5.59548580047435e-06, "epoch": 1.032, "percentage": 51.6, "elapsed_time": "5:19:12", "remaining_time": "4:59:24"}
+{"current_steps": 2600, "total_steps": 5000, "loss": 0.6038, "lr": 5.526113725002984e-06, "epoch": 1.04, "percentage": 52.0, "elapsed_time": "5:21:41", "remaining_time": "4:56:56"}
+{"current_steps": 2620, "total_steps": 5000, "loss": 0.6032, "lr": 5.456639082618489e-06, "epoch": 1.048, "percentage": 52.4, "elapsed_time": "5:24:14", "remaining_time": "4:54:32"}
+{"current_steps": 2640, "total_steps": 5000, "loss": 0.593, "lr": 5.3870754175400595e-06, "epoch": 1.056, "percentage": 52.8, "elapsed_time": "5:26:47", "remaining_time": "4:52:07"}
+{"current_steps": 2660, "total_steps": 5000, "loss": 0.5998, "lr": 5.317436291342031e-06, "epoch": 1.064, "percentage": 53.2, "elapsed_time": "5:29:12", "remaining_time": "4:49:36"}
+{"current_steps": 2680, "total_steps": 5000, "loss": 0.6009, "lr": 5.247735280310041e-06, "epoch": 1.072, "percentage": 53.6, "elapsed_time": "5:31:47", "remaining_time": "4:47:13"}
+{"current_steps": 2700, "total_steps": 5000, "loss": 0.6035, "lr": 5.177985972794293e-06, "epoch": 1.08, "percentage": 54.0, "elapsed_time": "5:34:14", "remaining_time": "4:44:43"}
+{"current_steps": 2720, "total_steps": 5000, "loss": 0.5954, "lr": 5.1082019665604895e-06, "epoch": 1.088, "percentage": 54.4, "elapsed_time": "5:36:46", "remaining_time": "4:42:17"}
+{"current_steps": 2740, "total_steps": 5000, "loss": 0.6085, "lr": 5.038396866138915e-06, "epoch": 1.096, "percentage": 54.8, "elapsed_time": "5:39:13", "remaining_time": "4:39:48"}
+{"current_steps": 2760, "total_steps": 5000, "loss": 0.5875, "lr": 4.968584280172206e-06, "epoch": 1.104, "percentage": 55.2, "elapsed_time": "5:41:42", "remaining_time": "4:37:19"}
+{"current_steps": 2780, "total_steps": 5000, "loss": 0.599, "lr": 4.898777818762325e-06, "epoch": 1.112, "percentage": 55.6, "elapsed_time": "5:44:08", "remaining_time": "4:34:49"}
+{"current_steps": 2800, "total_steps": 5000, "loss": 0.602, "lr": 4.828991090817238e-06, "epoch": 1.12, "percentage": 56.0, "elapsed_time": "5:46:39", "remaining_time": "4:32:22"}
+{"current_steps": 2820, "total_steps": 5000, "loss": 0.6088, "lr": 4.759237701397831e-06, "epoch": 1.1280000000000001, "percentage": 56.4, "elapsed_time": "5:49:11", "remaining_time": "4:29:56"}
+{"current_steps": 2840, "total_steps": 5000, "loss": 0.5926, "lr": 4.689531249065581e-06, "epoch": 1.1360000000000001, "percentage": 56.8, "elapsed_time": "5:51:47", "remaining_time": "4:27:33"}
+{"current_steps": 2860, "total_steps": 5000, "loss": 0.616, "lr": 4.619885323231484e-06, "epoch": 1.144, "percentage": 57.2, "elapsed_time": "5:54:11", "remaining_time": "4:25:01"}
+{"current_steps": 2880, "total_steps": 5000, "loss": 0.603, "lr": 4.5503135015067815e-06, "epoch": 1.152, "percentage": 57.6, "elapsed_time": "5:56:37", "remaining_time": "4:22:30"}
+{"current_steps": 2900, "total_steps": 5000, "loss": 0.6091, "lr": 4.4808293470559645e-06, "epoch": 1.16, "percentage": 58.0, "elapsed_time": "5:59:01", "remaining_time": "4:19:59"}
+{"current_steps": 2920, "total_steps": 5000, "loss": 0.5878, "lr": 4.4114464059526185e-06, "epoch": 1.168, "percentage": 58.4, "elapsed_time": "6:01:33", "remaining_time": "4:17:32"}
+{"current_steps": 2940, "total_steps": 5000, "loss": 0.6124, "lr": 4.342178204538588e-06, "epoch": 1.176, "percentage": 58.8, "elapsed_time": "6:03:55", "remaining_time": "4:14:59"}
+{"current_steps": 2960, "total_steps": 5000, "loss": 0.6061, "lr": 4.273038246786986e-06, "epoch": 1.184, "percentage": 59.2, "elapsed_time": "6:06:24", "remaining_time": "4:12:31"}
+{"current_steps": 2980, "total_steps": 5000, "loss": 0.5879, "lr": 4.204040011669567e-06, "epoch": 1.192, "percentage": 59.6, "elapsed_time": "6:08:59", "remaining_time": "4:10:07"}
+{"current_steps": 3000, "total_steps": 5000, "loss": 0.6107, "lr": 4.135196950528982e-06, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "6:11:26", "remaining_time": "4:07:37"}
+{"current_steps": 3020, "total_steps": 5000, "loss": 0.5969, "lr": 4.066522484456406e-06, "epoch": 1.208, "percentage": 60.4, "elapsed_time": "6:13:54", "remaining_time": "4:05:09"}
+{"current_steps": 3040, "total_steps": 5000, "loss": 0.6048, "lr": 3.9980300016750696e-06, "epoch": 1.216, "percentage": 60.8, "elapsed_time": "6:16:22", "remaining_time": "4:02:39"}
+{"current_steps": 3060, "total_steps": 5000, "loss": 0.5958, "lr": 3.9297328549302e-06, "epoch": 1.224, "percentage": 61.2, "elapsed_time": "6:18:49", "remaining_time": "4:00:10"}
+{"current_steps": 3080, "total_steps": 5000, "loss": 0.5977, "lr": 3.86164435888588e-06, "epoch": 1.232, "percentage": 61.6, "elapsed_time": "6:21:08", "remaining_time": "3:57:35"}
+{"current_steps": 3100, "total_steps": 5000, "loss": 0.5965, "lr": 3.793777787529325e-06, "epoch": 1.24, "percentage": 62.0, "elapsed_time": "6:23:34", "remaining_time": "3:55:05"}
+{"current_steps": 3120, "total_steps": 5000, "loss": 0.5999, "lr": 3.7261463715830902e-06, "epoch": 1.248, "percentage": 62.4, "elapsed_time": "6:26:06", "remaining_time": "3:52:39"}
+{"current_steps": 3140, "total_steps": 5000, "loss": 0.603, "lr": 3.6587632959257168e-06, "epoch": 1.256, "percentage": 62.8, "elapsed_time": "6:28:35", "remaining_time": "3:50:11"}
+{"current_steps": 3160, "total_steps": 5000, "loss": 0.6023, "lr": 3.5916416970213173e-06, "epoch": 1.264, "percentage": 63.2, "elapsed_time": "6:30:54", "remaining_time": "3:47:36"}
+{"current_steps": 3180, "total_steps": 5000, "loss": 0.5961, "lr": 3.524794660358593e-06, "epoch": 1.272, "percentage": 63.6, "elapsed_time": "6:33:18", "remaining_time": "3:45:06"}
+{"current_steps": 3200, "total_steps": 5000, "loss": 0.6055, "lr": 3.4582352178997937e-06, "epoch": 1.28, "percentage": 64.0, "elapsed_time": "6:35:46", "remaining_time": "3:42:37"}
+{"current_steps": 3220, "total_steps": 5000, "loss": 0.5978, "lr": 3.3919763455401016e-06, "epoch": 1.288, "percentage": 64.4, "elapsed_time": "6:38:12", "remaining_time": "3:40:07"}
+{"current_steps": 3240, "total_steps": 5000, "loss": 0.5982, "lr": 3.3260309605779717e-06, "epoch": 1.296, "percentage": 64.8, "elapsed_time": "6:40:39", "remaining_time": "3:37:38"}
+{"current_steps": 3260, "total_steps": 5000, "loss": 0.5912, "lr": 3.260411919196866e-06, "epoch": 1.304, "percentage": 65.2, "elapsed_time": "6:43:03", "remaining_time": "3:35:07"}
+{"current_steps": 3280, "total_steps": 5000, "loss": 0.6008, "lr": 3.195132013958918e-06, "epoch": 1.312, "percentage": 65.6, "elapsed_time": "6:45:23", "remaining_time": "3:32:34"}
+{"current_steps": 3300, "total_steps": 5000, "loss": 0.587, "lr": 3.130203971310999e-06, "epoch": 1.32, "percentage": 66.0, "elapsed_time": "6:47:50", "remaining_time": "3:30:06"}
+{"current_steps": 3320, "total_steps": 5000, "loss": 0.6021, "lr": 3.0656404491036696e-06, "epoch": 1.328, "percentage": 66.4, "elapsed_time": "6:50:16", "remaining_time": "3:27:36"}
+{"current_steps": 3340, "total_steps": 5000, "loss": 0.5959, "lr": 3.001454034123512e-06, "epoch": 1.336, "percentage": 66.8, "elapsed_time": "6:52:45", "remaining_time": "3:25:08"}
+{"current_steps": 3360, "total_steps": 5000, "loss": 0.5882, "lr": 2.9376572396393047e-06, "epoch": 1.3439999999999999, "percentage": 67.2, "elapsed_time": "6:55:14", "remaining_time": "3:22:40"}
+{"current_steps": 3380, "total_steps": 5000, "loss": 0.5898, "lr": 2.874262502962537e-06, "epoch": 1.3519999999999999, "percentage": 67.6, "elapsed_time": "6:57:45", "remaining_time": "3:20:13"}
+{"current_steps": 3400, "total_steps": 5000, "loss": 0.5947, "lr": 2.811282183022736e-06, "epoch": 1.3599999999999999, "percentage": 68.0, "elapsed_time": "7:00:18", "remaining_time": "3:17:47"}
+{"current_steps": 3420, "total_steps": 5000, "loss": 0.5936, "lr": 2.7487285579580635e-06, "epoch": 1.3679999999999999, "percentage": 68.4, "elapsed_time": "7:02:57", "remaining_time": "3:15:24"}
+{"current_steps": 3440, "total_steps": 5000, "loss": 0.5905, "lr": 2.686613822721666e-06, "epoch": 1.376, "percentage": 68.8, "elapsed_time": "7:05:26", "remaining_time": "3:12:56"}
+{"current_steps": 3460, "total_steps": 5000, "loss": 0.5845, "lr": 2.6249500867042523e-06, "epoch": 1.384, "percentage": 69.2, "elapsed_time": "7:07:54", "remaining_time": "3:10:27"}
+{"current_steps": 3480, "total_steps": 5000, "loss": 0.5971, "lr": 2.5637493713733376e-06, "epoch": 1.392, "percentage": 69.6, "elapsed_time": "7:10:22", "remaining_time": "3:07:58"}
+{"current_steps": 3500, "total_steps": 5000, "loss": 0.5861, "lr": 2.5030236079296443e-06, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "7:12:45", "remaining_time": "3:05:28"}
+{"current_steps": 3520, "total_steps": 5000, "loss": 0.6021, "lr": 2.442784634981071e-06, "epoch": 1.408, "percentage": 70.4, "elapsed_time": "7:15:11", "remaining_time": "3:02:58"}
+{"current_steps": 3540, "total_steps": 5000, "loss": 0.6008, "lr": 2.3830441962347528e-06, "epoch": 1.416, "percentage": 70.8, "elapsed_time": "7:17:33", "remaining_time": "3:00:27"}
+{"current_steps": 3560, "total_steps": 5000, "loss": 0.5791, "lr": 2.323813938207593e-06, "epoch": 1.424, "percentage": 71.2, "elapsed_time": "7:20:03", "remaining_time": "2:57:59"}
+{"current_steps": 3580, "total_steps": 5000, "loss": 0.5907, "lr": 2.265105407955752e-06, "epoch": 1.432, "percentage": 71.6, "elapsed_time": "7:22:29", "remaining_time": "2:55:30"}
+{"current_steps": 3600, "total_steps": 5000, "loss": 0.6024, "lr": 2.2069300508235273e-06, "epoch": 1.44, "percentage": 72.0, "elapsed_time": "7:24:54", "remaining_time": "2:53:01"}
+{"current_steps": 3620, "total_steps": 5000, "loss": 0.6016, "lr": 2.14929920821206e-06, "epoch": 1.448, "percentage": 72.4, "elapsed_time": "7:27:24", "remaining_time": "2:50:33"}
+{"current_steps": 3640, "total_steps": 5000, "loss": 0.5918, "lr": 2.0922241153683064e-06, "epoch": 1.456, "percentage": 72.8, "elapsed_time": "7:29:49", "remaining_time": "2:48:03"}
+{"current_steps": 3660, "total_steps": 5000, "loss": 0.5887, "lr": 2.035715899194704e-06, "epoch": 1.464, "percentage": 73.2, "elapsed_time": "7:32:16", "remaining_time": "2:45:35"}
+{"current_steps": 3680, "total_steps": 5000, "loss": 0.5823, "lr": 1.979785576079961e-06, "epoch": 1.472, "percentage": 73.6, "elapsed_time": "7:34:47", "remaining_time": "2:43:07"}
+{"current_steps": 3700, "total_steps": 5000, "loss": 0.5923, "lr": 1.9244440497513895e-06, "epoch": 1.48, "percentage": 74.0, "elapsed_time": "7:37:07", "remaining_time": "2:40:36"}
+{"current_steps": 3720, "total_steps": 5000, "loss": 0.5828, "lr": 1.8697021091491991e-06, "epoch": 1.488, "percentage": 74.4, "elapsed_time": "7:39:38", "remaining_time": "2:38:09"}
+{"current_steps": 3740, "total_steps": 5000, "loss": 0.605, "lr": 1.8155704263231777e-06, "epoch": 1.496, "percentage": 74.8, "elapsed_time": "7:42:05", "remaining_time": "2:35:40"}
+{"current_steps": 3760, "total_steps": 5000, "loss": 0.5957, "lr": 1.762059554352143e-06, "epoch": 1.504, "percentage": 75.2, "elapsed_time": "7:44:35", "remaining_time": "2:33:12"}
+{"current_steps": 3780, "total_steps": 5000, "loss": 0.5861, "lr": 1.709179925286617e-06, "epoch": 1.512, "percentage": 75.6, "elapsed_time": "7:47:04", "remaining_time": "2:30:44"}
+{"current_steps": 3800, "total_steps": 5000, "loss": 0.5832, "lr": 1.6569418481150596e-06, "epoch": 1.52, "percentage": 76.0, "elapsed_time": "7:49:28", "remaining_time": "2:28:15"}
+{"current_steps": 3820, "total_steps": 5000, "loss": 0.5985, "lr": 1.605355506754121e-06, "epoch": 1.528, "percentage": 76.4, "elapsed_time": "7:51:56", "remaining_time": "2:25:46"}
+{"current_steps": 3840, "total_steps": 5000, "loss": 0.5742, "lr": 1.554430958063259e-06, "epoch": 1.536, "percentage": 76.8, "elapsed_time": "7:54:23", "remaining_time": "2:23:18"}
+{"current_steps": 3860, "total_steps": 5000, "loss": 0.5982, "lr": 1.5041781298841424e-06, "epoch": 1.544, "percentage": 77.2, "elapsed_time": "7:56:49", "remaining_time": "2:20:49"}
+{"current_steps": 3880, "total_steps": 5000, "loss": 0.5991, "lr": 1.4546068191051988e-06, "epoch": 1.552, "percentage": 77.6, "elapsed_time": "7:59:20", "remaining_time": "2:18:21"}
+{"current_steps": 3900, "total_steps": 5000, "loss": 0.5861, "lr": 1.4057266897516842e-06, "epoch": 1.56, "percentage": 78.0, "elapsed_time": "8:02:01", "remaining_time": "2:15:57"}
+{"current_steps": 3920, "total_steps": 5000, "loss": 0.5835, "lr": 1.3575472711016634e-06, "epoch": 1.568, "percentage": 78.4, "elapsed_time": "8:04:31", "remaining_time": "2:13:29"}
+{"current_steps": 3940, "total_steps": 5000, "loss": 0.5843, "lr": 1.3100779558282673e-06, "epoch": 1.576, "percentage": 78.8, "elapsed_time": "8:07:05", "remaining_time": "2:11:02"}
+{"current_steps": 3960, "total_steps": 5000, "loss": 0.5723, "lr": 1.2633279981685608e-06, "epoch": 1.584, "percentage": 79.2, "elapsed_time": "8:09:43", "remaining_time": "2:08:36"}
+{"current_steps": 3980, "total_steps": 5000, "loss": 0.5701, "lr": 1.217306512119425e-06, "epoch": 1.592, "percentage": 79.6, "elapsed_time": "8:12:18", "remaining_time": "2:06:10"}
+{"current_steps": 4000, "total_steps": 5000, "loss": 0.5952, "lr": 1.1720224696607474e-06, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "8:14:48", "remaining_time": "2:03:42"}
+{"current_steps": 4020, "total_steps": 5000, "loss": 0.5852, "lr": 1.1274846990063314e-06, "epoch": 1.608, "percentage": 80.4, "elapsed_time": "8:17:14", "remaining_time": "2:01:13"}
+{"current_steps": 4040, "total_steps": 5000, "loss": 0.6007, "lr": 1.0837018828828133e-06, "epoch": 1.616, "percentage": 80.8, "elapsed_time": "8:19:39", "remaining_time": "1:58:43"}
+{"current_steps": 4060, "total_steps": 5000, "loss": 0.5916, "lr": 1.0406825568369478e-06, "epoch": 1.624, "percentage": 81.2, "elapsed_time": "8:22:10", "remaining_time": "1:56:15"}
+{"current_steps": 4080, "total_steps": 5000, "loss": 0.5828, "lr": 9.984351075715848e-07, "epoch": 1.6320000000000001, "percentage": 81.6, "elapsed_time": "8:24:48", "remaining_time": "1:53:49"}
+{"current_steps": 4100, "total_steps": 5000, "loss": 0.5955, "lr": 9.569677713106673e-07, "epoch": 1.6400000000000001, "percentage": 82.0, "elapsed_time": "8:27:14", "remaining_time": "1:51:20"}
+{"current_steps": 4120, "total_steps": 5000, "loss": 0.5891, "lr": 9.162886321935632e-07, "epoch": 1.6480000000000001, "percentage": 82.4, "elapsed_time": "8:29:48", "remaining_time": "1:48:53"}
+{"current_steps": 4140, "total_steps": 5000, "loss": 0.5837, "lr": 8.764056206990446e-07, "epoch": 1.6560000000000001, "percentage": 82.8, "elapsed_time": "8:32:10", "remaining_time": "1:46:23"}
+{"current_steps": 4160, "total_steps": 5000, "loss": 0.5786, "lr": 8.373265120992252e-07, "epoch": 1.6640000000000001, "percentage": 83.2, "elapsed_time": "8:34:43", "remaining_time": "1:43:56"}
+{"current_steps": 4180, "total_steps": 5000, "loss": 0.585, "lr": 7.990589249437591e-07, "epoch": 1.6720000000000002, "percentage": 83.6, "elapsed_time": "8:37:15", "remaining_time": "1:41:28"}
+{"current_steps": 4200, "total_steps": 5000, "loss": 0.5842, "lr": 7.61610319574585e-07, "epoch": 1.6800000000000002, "percentage": 84.0, "elapsed_time": "8:39:52", "remaining_time": "1:39:01"}
+{"current_steps": 4220, "total_steps": 5000, "loss": 0.6006, "lr": 7.249879966715174e-07, "epoch": 1.688, "percentage": 84.4, "elapsed_time": "8:42:19", "remaining_time": "1:36:32"}
+{"current_steps": 4240, "total_steps": 5000, "loss": 0.5933, "lr": 6.891990958289724e-07, "epoch": 1.696, "percentage": 84.8, "elapsed_time": "8:44:49", "remaining_time": "1:34:04"}
+{"current_steps": 4260, "total_steps": 5000, "loss": 0.5783, "lr": 6.542505941640803e-07, "epoch": 1.704, "percentage": 85.2, "elapsed_time": "8:47:23", "remaining_time": "1:31:36"}
+{"current_steps": 4280, "total_steps": 5000, "loss": 0.5902, "lr": 6.201493049564883e-07, "epoch": 1.712, "percentage": 85.6, "elapsed_time": "8:49:46", "remaining_time": "1:29:07"}
+{"current_steps": 4300, "total_steps": 5000, "loss": 0.5896, "lr": 5.869018763200929e-07, "epoch": 1.72, "percentage": 86.0, "elapsed_time": "8:52:16", "remaining_time": "1:26:38"}
+{"current_steps": 4320, "total_steps": 5000, "loss": 0.5918, "lr": 5.545147899069836e-07, "epoch": 1.728, "percentage": 86.4, "elapsed_time": "8:54:42", "remaining_time": "1:24:10"}
+{"current_steps": 4340, "total_steps": 5000, "loss": 0.5899, "lr": 5.229943596438297e-07, "epoch": 1.736, "percentage": 86.8, "elapsed_time": "8:57:06", "remaining_time": "1:21:40"}
+{"current_steps": 4360, "total_steps": 5000, "loss": 0.6075, "lr": 4.92346730500966e-07, "epoch": 1.744, "percentage": 87.2, "elapsed_time": "8:59:30", "remaining_time": "1:19:11"}
+{"current_steps": 4380, "total_steps": 5000, "loss": 0.5742, "lr": 4.625778772944156e-07, "epoch": 1.752, "percentage": 87.6, "elapsed_time": "9:02:09", "remaining_time": "1:16:44"}
+{"current_steps": 4400, "total_steps": 5000, "loss": 0.591, "lr": 4.33693603521097e-07, "epoch": 1.76, "percentage": 88.0, "elapsed_time": "9:04:41", "remaining_time": "1:14:16"}
+{"current_steps": 4420, "total_steps": 5000, "loss": 0.5884, "lr": 4.056995402274122e-07, "epoch": 1.768, "percentage": 88.4, "elapsed_time": "9:07:01", "remaining_time": "1:11:46"}
+{"current_steps": 4440, "total_steps": 5000, "loss": 0.5857, "lr": 3.7860114491147017e-07, "epoch": 1.776, "percentage": 88.8, "elapsed_time": "9:09:29", "remaining_time": "1:09:18"}
+{"current_steps": 4460, "total_steps": 5000, "loss": 0.5812, "lr": 3.524037004591274e-07, "epoch": 1.784, "percentage": 89.2, "elapsed_time": "9:12:05", "remaining_time": "1:06:50"}
+{"current_steps": 4480, "total_steps": 5000, "loss": 0.5973, "lr": 3.271123141140886e-07, "epoch": 1.792, "percentage": 89.6, "elapsed_time": "9:14:35", "remaining_time": "1:04:22"}
+{"current_steps": 4500, "total_steps": 5000, "loss": 0.5982, "lr": 3.027319164822329e-07, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "9:17:01", "remaining_time": "1:01:53"}
+{"current_steps": 4520, "total_steps": 5000, "loss": 0.5888, "lr": 2.792672605703867e-07, "epoch": 1.808, "percentage": 90.4, "elapsed_time": "9:19:32", "remaining_time": "0:59:25"}
+{"current_steps": 4540, "total_steps": 5000, "loss": 0.5902, "lr": 2.5672292085971276e-07, "epoch": 1.8159999999999998, "percentage": 90.8, "elapsed_time": "9:22:02", "remaining_time": "0:56:56"}
+{"current_steps": 4560, "total_steps": 5000, "loss": 0.597, "lr": 2.351032924139063e-07, "epoch": 1.8239999999999998, "percentage": 91.2, "elapsed_time": "9:24:31", "remaining_time": "0:54:28"}
+{"current_steps": 4580, "total_steps": 5000, "loss": 0.5907, "lr": 2.1441259002236924e-07, "epoch": 1.8319999999999999, "percentage": 91.6, "elapsed_time": "9:26:53", "remaining_time": "0:51:59"}
+{"current_steps": 4600, "total_steps": 5000, "loss": 0.5953, "lr": 1.9465484737853092e-07, "epoch": 1.8399999999999999, "percentage": 92.0, "elapsed_time": "9:29:17", "remaining_time": "0:49:30"}
+{"current_steps": 4620, "total_steps": 5000, "loss": 0.5664, "lr": 1.758339162934658e-07, "epoch": 1.8479999999999999, "percentage": 92.4, "elapsed_time": "9:31:44", "remaining_time": "0:47:01"}
+{"current_steps": 4640, "total_steps": 5000, "loss": 0.5895, "lr": 1.5795346594498162e-07, "epoch": 1.8559999999999999, "percentage": 92.8, "elapsed_time": "9:34:12", "remaining_time": "0:44:33"}
+{"current_steps": 4660, "total_steps": 5000, "loss": 0.5906, "lr": 1.4101698216230254e-07, "epoch": 1.8639999999999999, "percentage": 93.2, "elapsed_time": "9:36:41", "remaining_time": "0:42:04"}
+{"current_steps": 4680, "total_steps": 5000, "loss": 0.5729, "lr": 1.2502776674649776e-07, "epoch": 1.8719999999999999, "percentage": 93.6, "elapsed_time": "9:39:31", "remaining_time": "0:39:37"}
+{"current_steps": 4700, "total_steps": 5000, "loss": 0.5848, "lr": 1.0998893682679479e-07, "epoch": 1.88, "percentage": 94.0, "elapsed_time": "9:42:01", "remaining_time": "0:37:09"}
+{"current_steps": 4720, "total_steps": 5000, "loss": 0.5693, "lr": 9.590342425288446e-08, "epoch": 1.888, "percentage": 94.4, "elapsed_time": "9:44:40", "remaining_time": "0:34:41"}
+{"current_steps": 4740, "total_steps": 5000, "loss": 0.5706, "lr": 8.277397502335194e-08, "epoch": 1.896, "percentage": 94.8, "elapsed_time": "9:47:01", "remaining_time": "0:32:11"}
+{"current_steps": 4760, "total_steps": 5000, "loss": 0.5884, "lr": 7.060314875033836e-08, "epoch": 1.904, "percentage": 95.2, "elapsed_time": "9:49:27", "remaining_time": "0:29:43"}
+{"current_steps": 4780, "total_steps": 5000, "loss": 0.5675, "lr": 5.939331816054161e-08, "epoch": 1.912, "percentage": 95.6, "elapsed_time": "9:52:16", "remaining_time": "0:27:15"}
+{"current_steps": 4800, "total_steps": 5000, "loss": 0.6013, "lr": 4.914666863264528e-08, "epoch": 1.92, "percentage": 96.0, "elapsed_time": "9:54:45", "remaining_time": "0:24:46"}
+{"current_steps": 4820, "total_steps": 5000, "loss": 0.5873, "lr": 3.986519777127884e-08, "epoch": 1.928, "percentage": 96.4, "elapsed_time": "9:57:09", "remaining_time": "0:22:18"}
+{"current_steps": 4840, "total_steps": 5000, "loss": 0.5846, "lr": 3.1550715017575895e-08, "epoch": 1.936, "percentage": 96.8, "elapsed_time": "9:59:34", "remaining_time": "0:19:49"}
+{"current_steps": 4860, "total_steps": 5000, "loss": 0.5773, "lr": 2.4204841296424086e-08, "epoch": 1.944, "percentage": 97.2, "elapsed_time": "10:01:59", "remaining_time": "0:17:20"}
+{"current_steps": 4880, "total_steps": 5000, "loss": 0.5826, "lr": 1.7829008700460116e-08, "epoch": 1.952, "percentage": 97.6, "elapsed_time": "10:04:22", "remaining_time": "0:14:51"}
+{"current_steps": 4900, "total_steps": 5000, "loss": 0.5787, "lr": 1.2424460210881394e-08, "epoch": 1.96, "percentage": 98.0, "elapsed_time": "10:06:54", "remaining_time": "0:12:23"}
+{"current_steps": 4920, "total_steps": 5000, "loss": 0.5897, "lr": 7.992249455124889e-09, "epoch": 1.968, "percentage": 98.4, "elapsed_time": "10:09:22", "remaining_time": "0:09:54"}
+{"current_steps": 4940, "total_steps": 5000, "loss": 0.5814, "lr": 4.533240501459202e-09, "epoch": 1.976, "percentage": 98.8, "elapsed_time": "10:11:41", "remaining_time": "0:07:25"}
+{"current_steps": 4960, "total_steps": 5000, "loss": 0.5906, "lr": 2.0481076905332074e-09, "epoch": 1.984, "percentage": 99.2, "elapsed_time": "10:14:08", "remaining_time": "0:04:57"}
+{"current_steps": 4980, "total_steps": 5000, "loss": 0.5983, "lr": 5.373355039128836e-10, "epoch": 1.992, "percentage": 99.6, "elapsed_time": "10:16:31", "remaining_time": "0:02:28"}
+{"current_steps": 5000, "total_steps": 5000, "loss": 0.5883, "lr": 1.2184696296380083e-12, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "10:18:57", "remaining_time": "0:00:00"}
+{"current_steps": 5000, "total_steps": 5000, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "10:19:11", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f70fc5a32aa0acbde92102c2325cc7163750d48ef322d11d0ea4a63ca4c0ff6
+size 6481