初始化项目，由ModelHub XC社区提供模型

Model: laion/r2egym-gpt5-codex-160ep-1M
Source: Original Platform

.gitattributes

@@ -0,0 +1,56 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm 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
+vocab.json filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+merges.txt filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: r2egym-gpt5-codex-160ep-1M
+  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. -->
+
+# r2egym-gpt5-codex-160ep-1M
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the penfever/r2egym_gpt5_codex_solve_traces 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 16
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.56.0
+- Pytorch 2.9.0+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

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 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.0003518731812688662,
+    "achieved_tflops_per_gpu_theoretical": 1439.8594391998463,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.3174639642238617,
+    "mfu_percent": 2.4867362633842135e-05,
+    "mfu_percent_theoretical": 101.75685082684426,
+    "total_flos": 22338300149760.0,
+    "train_loss": 0.652452801803053,
+    "train_runtime": 3967.747,
+    "train_samples_per_second": 6.796,
+    "train_steps_per_second": 0.425,
+    "valid_targets_mean": 94.8,
+    "valid_targets_min": 62
+}

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": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 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": false,
+  "transformers_version": "4.56.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

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": "4.56.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519c6b37badcec1380b216ceb35356fea8116fc0df98fed40565c324ab386b1c
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030e5abc1559c53db6d09a4e26ecfd379fe6451dca3fe5456b509007513ab450
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219f709b9d0bd613cade3605efc85a6be9a471a2be4bf2adc80b4edd4d928238
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0b92f0b7e9642c183ea177ff9692279fa8f72042900f0d326979c550a0e7b8
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 308224,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

run_summary.json

@@ -0,0 +1,12 @@
+{
+  "agent_name": null,
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "penfever/r2egym_gpt5_codex_solve_traces",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/r2egym-gpt5-codex-160ep-1M/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/dc-agent/runs/r2egym_gpt5_codex_solve_traces_hub-model-id_r2egym-gpt5-codex-160ep-1M_Qwen3-8B",
+  "traces_location_s3": null
+}

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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.0003518731812688662,
+    "achieved_tflops_per_gpu_theoretical": 1439.8594391998463,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.3174639642238617,
+    "mfu_percent": 2.4867362633842135e-05,
+    "mfu_percent_theoretical": 101.75685082684426,
+    "total_flos": 22338300149760.0,
+    "train_loss": 0.652452801803053,
+    "train_runtime": 3967.747,
+    "train_samples_per_second": 6.796,
+    "train_steps_per_second": 0.425,
+    "valid_targets_mean": 94.8,
+    "valid_targets_min": 62
+}

trainer_log.jsonl

@@ -0,0 +1,338 @@
+{"current_steps": 5, "total_steps": 1687, "loss": 3.331, "lr": 9.467455621301776e-07, "epoch": 0.02074688796680498, "percentage": 0.3, "elapsed_time": "0:00:23", "remaining_time": "2:12:07"}
+{"current_steps": 10, "total_steps": 1687, "loss": 2.722, "lr": 2.1301775147929e-06, "epoch": 0.04149377593360996, "percentage": 0.59, "elapsed_time": "0:00:36", "remaining_time": "1:43:05"}
+{"current_steps": 15, "total_steps": 1687, "loss": 3.1562, "lr": 3.313609467455622e-06, "epoch": 0.06224066390041494, "percentage": 0.89, "elapsed_time": "0:00:49", "remaining_time": "1:31:45"}
+{"current_steps": 20, "total_steps": 1687, "loss": 2.9616, "lr": 4.497041420118343e-06, "epoch": 0.08298755186721991, "percentage": 1.19, "elapsed_time": "0:01:01", "remaining_time": "1:25:50"}
+{"current_steps": 25, "total_steps": 1687, "loss": 2.4025, "lr": 5.680473372781066e-06, "epoch": 0.1037344398340249, "percentage": 1.48, "elapsed_time": "0:01:12", "remaining_time": "1:20:48"}
+{"current_steps": 30, "total_steps": 1687, "loss": 2.3199, "lr": 6.863905325443787e-06, "epoch": 0.12448132780082988, "percentage": 1.78, "elapsed_time": "0:01:24", "remaining_time": "1:17:32"}
+{"current_steps": 35, "total_steps": 1687, "loss": 2.0466, "lr": 8.04733727810651e-06, "epoch": 0.14522821576763487, "percentage": 2.07, "elapsed_time": "0:01:35", "remaining_time": "1:14:49"}
+{"current_steps": 40, "total_steps": 1687, "loss": 2.0725, "lr": 9.230769230769232e-06, "epoch": 0.16597510373443983, "percentage": 2.37, "elapsed_time": "0:01:46", "remaining_time": "1:13:03"}
+{"current_steps": 45, "total_steps": 1687, "loss": 1.7968, "lr": 1.0414201183431953e-05, "epoch": 0.18672199170124482, "percentage": 2.67, "elapsed_time": "0:01:57", "remaining_time": "1:11:35"}
+{"current_steps": 50, "total_steps": 1687, "loss": 1.6917, "lr": 1.1597633136094675e-05, "epoch": 0.2074688796680498, "percentage": 2.96, "elapsed_time": "0:02:08", "remaining_time": "1:10:09"}
+{"current_steps": 55, "total_steps": 1687, "loss": 1.5291, "lr": 1.2781065088757399e-05, "epoch": 0.22821576763485477, "percentage": 3.26, "elapsed_time": "0:02:20", "remaining_time": "1:09:31"}
+{"current_steps": 60, "total_steps": 1687, "loss": 1.5082, "lr": 1.396449704142012e-05, "epoch": 0.24896265560165975, "percentage": 3.56, "elapsed_time": "0:02:31", "remaining_time": "1:08:26"}
+{"current_steps": 65, "total_steps": 1687, "loss": 1.3951, "lr": 1.5147928994082842e-05, "epoch": 0.2697095435684647, "percentage": 3.85, "elapsed_time": "0:02:42", "remaining_time": "1:07:36"}
+{"current_steps": 70, "total_steps": 1687, "loss": 1.4802, "lr": 1.6331360946745562e-05, "epoch": 0.29045643153526973, "percentage": 4.15, "elapsed_time": "0:02:53", "remaining_time": "1:06:36"}
+{"current_steps": 75, "total_steps": 1687, "loss": 1.4573, "lr": 1.7514792899408286e-05, "epoch": 0.3112033195020747, "percentage": 4.45, "elapsed_time": "0:03:03", "remaining_time": "1:05:41"}
+{"current_steps": 80, "total_steps": 1687, "loss": 1.3158, "lr": 1.8698224852071007e-05, "epoch": 0.33195020746887965, "percentage": 4.74, "elapsed_time": "0:03:13", "remaining_time": "1:04:52"}
+{"current_steps": 85, "total_steps": 1687, "loss": 1.3183, "lr": 1.9881656804733727e-05, "epoch": 0.35269709543568467, "percentage": 5.04, "elapsed_time": "0:03:24", "remaining_time": "1:04:19"}
+{"current_steps": 90, "total_steps": 1687, "loss": 1.1263, "lr": 2.106508875739645e-05, "epoch": 0.37344398340248963, "percentage": 5.33, "elapsed_time": "0:03:35", "remaining_time": "1:03:45"}
+{"current_steps": 95, "total_steps": 1687, "loss": 1.2161, "lr": 2.224852071005917e-05, "epoch": 0.3941908713692946, "percentage": 5.63, "elapsed_time": "0:03:46", "remaining_time": "1:03:12"}
+{"current_steps": 100, "total_steps": 1687, "loss": 1.179, "lr": 2.3431952662721896e-05, "epoch": 0.4149377593360996, "percentage": 5.93, "elapsed_time": "0:03:57", "remaining_time": "1:02:42"}
+{"current_steps": 105, "total_steps": 1687, "loss": 1.2358, "lr": 2.461538461538462e-05, "epoch": 0.43568464730290457, "percentage": 6.22, "elapsed_time": "0:04:07", "remaining_time": "1:02:15"}
+{"current_steps": 110, "total_steps": 1687, "loss": 1.2222, "lr": 2.5798816568047337e-05, "epoch": 0.45643153526970953, "percentage": 6.52, "elapsed_time": "0:04:18", "remaining_time": "1:01:53"}
+{"current_steps": 115, "total_steps": 1687, "loss": 1.1238, "lr": 2.698224852071006e-05, "epoch": 0.47717842323651455, "percentage": 6.82, "elapsed_time": "0:04:30", "remaining_time": "1:01:34"}
+{"current_steps": 120, "total_steps": 1687, "loss": 1.1292, "lr": 2.8165680473372784e-05, "epoch": 0.4979253112033195, "percentage": 7.11, "elapsed_time": "0:04:41", "remaining_time": "1:01:10"}
+{"current_steps": 125, "total_steps": 1687, "loss": 1.2792, "lr": 2.9349112426035505e-05, "epoch": 0.5186721991701245, "percentage": 7.41, "elapsed_time": "0:04:51", "remaining_time": "1:00:44"}
+{"current_steps": 130, "total_steps": 1687, "loss": 1.2547, "lr": 3.0532544378698226e-05, "epoch": 0.5394190871369294, "percentage": 7.71, "elapsed_time": "0:05:02", "remaining_time": "1:00:24"}
+{"current_steps": 135, "total_steps": 1687, "loss": 1.1989, "lr": 3.171597633136095e-05, "epoch": 0.5601659751037344, "percentage": 8.0, "elapsed_time": "0:05:13", "remaining_time": "1:00:05"}
+{"current_steps": 140, "total_steps": 1687, "loss": 1.291, "lr": 3.289940828402367e-05, "epoch": 0.5809128630705395, "percentage": 8.3, "elapsed_time": "0:05:24", "remaining_time": "0:59:40"}
+{"current_steps": 145, "total_steps": 1687, "loss": 1.2244, "lr": 3.40828402366864e-05, "epoch": 0.6016597510373444, "percentage": 8.6, "elapsed_time": "0:05:34", "remaining_time": "0:59:20"}
+{"current_steps": 150, "total_steps": 1687, "loss": 1.1273, "lr": 3.5266272189349114e-05, "epoch": 0.6224066390041494, "percentage": 8.89, "elapsed_time": "0:05:45", "remaining_time": "0:58:56"}
+{"current_steps": 155, "total_steps": 1687, "loss": 1.0308, "lr": 3.644970414201184e-05, "epoch": 0.6431535269709544, "percentage": 9.19, "elapsed_time": "0:05:55", "remaining_time": "0:58:38"}
+{"current_steps": 160, "total_steps": 1687, "loss": 0.9736, "lr": 3.763313609467456e-05, "epoch": 0.6639004149377593, "percentage": 9.48, "elapsed_time": "0:06:06", "remaining_time": "0:58:18"}
+{"current_steps": 165, "total_steps": 1687, "loss": 1.166, "lr": 3.881656804733728e-05, "epoch": 0.6846473029045643, "percentage": 9.78, "elapsed_time": "0:06:17", "remaining_time": "0:58:06"}
+{"current_steps": 170, "total_steps": 1687, "loss": 1.0946, "lr": 4e-05, "epoch": 0.7053941908713693, "percentage": 10.08, "elapsed_time": "0:06:28", "remaining_time": "0:57:48"}
+{"current_steps": 175, "total_steps": 1687, "loss": 1.0991, "lr": 3.999892923951514e-05, "epoch": 0.7261410788381742, "percentage": 10.37, "elapsed_time": "0:06:38", "remaining_time": "0:57:24"}
+{"current_steps": 180, "total_steps": 1687, "loss": 1.1184, "lr": 3.999571707271335e-05, "epoch": 0.7468879668049793, "percentage": 10.67, "elapsed_time": "0:06:49", "remaining_time": "0:57:06"}
+{"current_steps": 185, "total_steps": 1687, "loss": 1.0885, "lr": 3.999036384354076e-05, "epoch": 0.7676348547717843, "percentage": 10.97, "elapsed_time": "0:06:59", "remaining_time": "0:56:47"}
+{"current_steps": 190, "total_steps": 1687, "loss": 1.1776, "lr": 3.99828701252e-05, "epoch": 0.7883817427385892, "percentage": 11.26, "elapsed_time": "0:07:10", "remaining_time": "0:56:30"}
+{"current_steps": 195, "total_steps": 1687, "loss": 1.1762, "lr": 3.997323672008881e-05, "epoch": 0.8091286307053942, "percentage": 11.56, "elapsed_time": "0:07:21", "remaining_time": "0:56:15"}
+{"current_steps": 200, "total_steps": 1687, "loss": 1.0519, "lr": 3.9961464659714154e-05, "epoch": 0.8298755186721992, "percentage": 11.86, "elapsed_time": "0:07:31", "remaining_time": "0:55:56"}
+{"current_steps": 205, "total_steps": 1687, "loss": 1.2221, "lr": 3.994755520458173e-05, "epoch": 0.8506224066390041, "percentage": 12.15, "elapsed_time": "0:08:40", "remaining_time": "1:02:44"}
+{"current_steps": 210, "total_steps": 1687, "loss": 1.1059, "lr": 3.9931509844061034e-05, "epoch": 0.8713692946058091, "percentage": 12.45, "elapsed_time": "0:08:51", "remaining_time": "1:02:17"}
+{"current_steps": 215, "total_steps": 1687, "loss": 1.0881, "lr": 3.991333029622587e-05, "epoch": 0.8921161825726142, "percentage": 12.74, "elapsed_time": "0:09:01", "remaining_time": "1:01:50"}
+{"current_steps": 220, "total_steps": 1687, "loss": 1.0801, "lr": 3.9893018507670384e-05, "epoch": 0.9128630705394191, "percentage": 13.04, "elapsed_time": "0:09:12", "remaining_time": "1:01:21"}
+{"current_steps": 225, "total_steps": 1687, "loss": 1.1093, "lr": 3.987057665330063e-05, "epoch": 0.9336099585062241, "percentage": 13.34, "elapsed_time": "0:09:22", "remaining_time": "1:00:55"}
+{"current_steps": 230, "total_steps": 1687, "loss": 1.043, "lr": 3.984600713610169e-05, "epoch": 0.9543568464730291, "percentage": 13.63, "elapsed_time": "0:09:32", "remaining_time": "1:00:27"}
+{"current_steps": 235, "total_steps": 1687, "loss": 1.1468, "lr": 3.981931258688038e-05, "epoch": 0.975103734439834, "percentage": 13.93, "elapsed_time": "0:09:42", "remaining_time": "1:00:00"}
+{"current_steps": 240, "total_steps": 1687, "loss": 1.1073, "lr": 3.979049586398355e-05, "epoch": 0.995850622406639, "percentage": 14.23, "elapsed_time": "0:09:52", "remaining_time": "0:59:34"}
+{"current_steps": 245, "total_steps": 1687, "loss": 1.1062, "lr": 3.975956005299202e-05, "epoch": 1.016597510373444, "percentage": 14.52, "elapsed_time": "0:10:03", "remaining_time": "0:59:13"}
+{"current_steps": 250, "total_steps": 1687, "loss": 0.9987, "lr": 3.972650846639019e-05, "epoch": 1.037344398340249, "percentage": 14.82, "elapsed_time": "0:10:14", "remaining_time": "0:58:52"}
+{"current_steps": 255, "total_steps": 1687, "loss": 0.9541, "lr": 3.9691344643211346e-05, "epoch": 1.058091286307054, "percentage": 15.12, "elapsed_time": "0:10:24", "remaining_time": "0:58:29"}
+{"current_steps": 260, "total_steps": 1687, "loss": 1.0478, "lr": 3.965407234865871e-05, "epoch": 1.0788381742738589, "percentage": 15.41, "elapsed_time": "0:10:35", "remaining_time": "0:58:05"}
+{"current_steps": 265, "total_steps": 1687, "loss": 0.9397, "lr": 3.9614695573702325e-05, "epoch": 1.099585062240664, "percentage": 15.71, "elapsed_time": "0:10:46", "remaining_time": "0:57:47"}
+{"current_steps": 270, "total_steps": 1687, "loss": 0.9561, "lr": 3.957321853465163e-05, "epoch": 1.120331950207469, "percentage": 16.0, "elapsed_time": "0:10:57", "remaining_time": "0:57:28"}
+{"current_steps": 275, "total_steps": 1687, "loss": 0.9533, "lr": 3.952964567270409e-05, "epoch": 1.1410788381742738, "percentage": 16.3, "elapsed_time": "0:11:07", "remaining_time": "0:57:06"}
+{"current_steps": 280, "total_steps": 1687, "loss": 0.9866, "lr": 3.9483981653469586e-05, "epoch": 1.161825726141079, "percentage": 16.6, "elapsed_time": "0:11:17", "remaining_time": "0:56:45"}
+{"current_steps": 285, "total_steps": 1687, "loss": 1.0861, "lr": 3.9436231366470836e-05, "epoch": 1.1825726141078838, "percentage": 16.89, "elapsed_time": "0:11:28", "remaining_time": "0:56:25"}
+{"current_steps": 290, "total_steps": 1687, "loss": 0.8913, "lr": 3.93863999246199e-05, "epoch": 1.2033195020746887, "percentage": 17.19, "elapsed_time": "0:11:38", "remaining_time": "0:56:06"}
+{"current_steps": 295, "total_steps": 1687, "loss": 0.9027, "lr": 3.933449266367066e-05, "epoch": 1.2240663900414939, "percentage": 17.49, "elapsed_time": "0:11:49", "remaining_time": "0:55:46"}
+{"current_steps": 300, "total_steps": 1687, "loss": 0.984, "lr": 3.92805151416475e-05, "epoch": 1.2448132780082988, "percentage": 17.78, "elapsed_time": "0:11:59", "remaining_time": "0:55:25"}
+{"current_steps": 305, "total_steps": 1687, "loss": 0.9891, "lr": 3.9224473138250186e-05, "epoch": 1.2655601659751037, "percentage": 18.08, "elapsed_time": "0:12:09", "remaining_time": "0:55:07"}
+{"current_steps": 310, "total_steps": 1687, "loss": 0.8473, "lr": 3.9166372654235e-05, "epoch": 1.2863070539419086, "percentage": 18.38, "elapsed_time": "0:12:20", "remaining_time": "0:54:50"}
+{"current_steps": 315, "total_steps": 1687, "loss": 0.9896, "lr": 3.9106219910772184e-05, "epoch": 1.3070539419087137, "percentage": 18.67, "elapsed_time": "0:12:30", "remaining_time": "0:54:30"}
+{"current_steps": 320, "total_steps": 1687, "loss": 0.9571, "lr": 3.90440213487798e-05, "epoch": 1.3278008298755186, "percentage": 18.97, "elapsed_time": "0:12:41", "remaining_time": "0:54:13"}
+{"current_steps": 325, "total_steps": 1687, "loss": 0.9725, "lr": 3.897978362823411e-05, "epoch": 1.3485477178423237, "percentage": 19.26, "elapsed_time": "0:12:52", "remaining_time": "0:53:56"}
+{"current_steps": 330, "total_steps": 1687, "loss": 1.0897, "lr": 3.8913513627456374e-05, "epoch": 1.3692946058091287, "percentage": 19.56, "elapsed_time": "0:13:02", "remaining_time": "0:53:38"}
+{"current_steps": 335, "total_steps": 1687, "loss": 1.0984, "lr": 3.8845218442376416e-05, "epoch": 1.3900414937759336, "percentage": 19.86, "elapsed_time": "0:13:13", "remaining_time": "0:53:21"}
+{"current_steps": 340, "total_steps": 1687, "loss": 0.9807, "lr": 3.877490538577278e-05, "epoch": 1.4107883817427385, "percentage": 20.15, "elapsed_time": "0:13:23", "remaining_time": "0:53:04"}
+{"current_steps": 345, "total_steps": 1687, "loss": 0.8938, "lr": 3.870258198648974e-05, "epoch": 1.4315352697095436, "percentage": 20.45, "elapsed_time": "0:13:34", "remaining_time": "0:52:47"}
+{"current_steps": 350, "total_steps": 1687, "loss": 0.9289, "lr": 3.862825598863108e-05, "epoch": 1.4522821576763485, "percentage": 20.75, "elapsed_time": "0:13:44", "remaining_time": "0:52:30"}
+{"current_steps": 355, "total_steps": 1687, "loss": 0.9448, "lr": 3.855193535073097e-05, "epoch": 1.4730290456431536, "percentage": 21.04, "elapsed_time": "0:13:55", "remaining_time": "0:52:13"}
+{"current_steps": 360, "total_steps": 1687, "loss": 0.9142, "lr": 3.847362824490173e-05, "epoch": 1.4937759336099585, "percentage": 21.34, "elapsed_time": "0:14:05", "remaining_time": "0:51:56"}
+{"current_steps": 365, "total_steps": 1687, "loss": 0.9044, "lr": 3.839334305595881e-05, "epoch": 1.5145228215767634, "percentage": 21.64, "elapsed_time": "0:14:15", "remaining_time": "0:51:38"}
+{"current_steps": 370, "total_steps": 1687, "loss": 1.0486, "lr": 3.831108838052301e-05, "epoch": 1.5352697095435683, "percentage": 21.93, "elapsed_time": "0:14:25", "remaining_time": "0:51:19"}
+{"current_steps": 375, "total_steps": 1687, "loss": 1.0625, "lr": 3.822687302609994e-05, "epoch": 1.5560165975103735, "percentage": 22.23, "elapsed_time": "0:14:35", "remaining_time": "0:51:02"}
+{"current_steps": 380, "total_steps": 1687, "loss": 0.99, "lr": 3.814070601013697e-05, "epoch": 1.5767634854771784, "percentage": 22.53, "elapsed_time": "0:14:45", "remaining_time": "0:50:45"}
+{"current_steps": 385, "total_steps": 1687, "loss": 1.0098, "lr": 3.8052596559057674e-05, "epoch": 1.5975103734439835, "percentage": 22.82, "elapsed_time": "0:14:55", "remaining_time": "0:50:28"}
+{"current_steps": 390, "total_steps": 1687, "loss": 0.9996, "lr": 3.7962554107273926e-05, "epoch": 1.6182572614107884, "percentage": 23.12, "elapsed_time": "0:15:05", "remaining_time": "0:50:12"}
+{"current_steps": 395, "total_steps": 1687, "loss": 0.9104, "lr": 3.7870588296175644e-05, "epoch": 1.6390041493775933, "percentage": 23.41, "elapsed_time": "0:15:16", "remaining_time": "0:49:57"}
+{"current_steps": 400, "total_steps": 1687, "loss": 0.9904, "lr": 3.7776708973098476e-05, "epoch": 1.6597510373443982, "percentage": 23.71, "elapsed_time": "0:15:26", "remaining_time": "0:49:41"}
+{"current_steps": 405, "total_steps": 1687, "loss": 1.0073, "lr": 3.768092619026937e-05, "epoch": 1.6804979253112033, "percentage": 24.01, "elapsed_time": "0:16:32", "remaining_time": "0:52:21"}
+{"current_steps": 410, "total_steps": 1687, "loss": 0.9565, "lr": 3.7583250203730234e-05, "epoch": 1.7012448132780082, "percentage": 24.3, "elapsed_time": "0:16:42", "remaining_time": "0:52:02"}
+{"current_steps": 415, "total_steps": 1687, "loss": 1.0132, "lr": 3.7483691472239744e-05, "epoch": 1.7219917012448134, "percentage": 24.6, "elapsed_time": "0:16:52", "remaining_time": "0:51:44"}
+{"current_steps": 420, "total_steps": 1687, "loss": 0.8144, "lr": 3.7382260656153436e-05, "epoch": 1.7427385892116183, "percentage": 24.9, "elapsed_time": "0:17:03", "remaining_time": "0:51:27"}
+{"current_steps": 425, "total_steps": 1687, "loss": 0.9513, "lr": 3.727896861628231e-05, "epoch": 1.7634854771784232, "percentage": 25.19, "elapsed_time": "0:17:13", "remaining_time": "0:51:09"}
+{"current_steps": 430, "total_steps": 1687, "loss": 0.9952, "lr": 3.717382641272984e-05, "epoch": 1.784232365145228, "percentage": 25.49, "elapsed_time": "0:17:24", "remaining_time": "0:50:52"}
+{"current_steps": 435, "total_steps": 1687, "loss": 0.8269, "lr": 3.7066845303707694e-05, "epoch": 1.8049792531120332, "percentage": 25.79, "elapsed_time": "0:17:35", "remaining_time": "0:50:37"}
+{"current_steps": 440, "total_steps": 1687, "loss": 1.0451, "lr": 3.6958036744330297e-05, "epoch": 1.8257261410788381, "percentage": 26.08, "elapsed_time": "0:17:46", "remaining_time": "0:50:21"}
+{"current_steps": 445, "total_steps": 1687, "loss": 0.8965, "lr": 3.6847412385388236e-05, "epoch": 1.8464730290456433, "percentage": 26.38, "elapsed_time": "0:17:56", "remaining_time": "0:50:04"}
+{"current_steps": 450, "total_steps": 1687, "loss": 0.9751, "lr": 3.673498407210073e-05, "epoch": 1.8672199170124482, "percentage": 26.67, "elapsed_time": "0:18:06", "remaining_time": "0:49:46"}
+{"current_steps": 455, "total_steps": 1687, "loss": 0.9165, "lr": 3.662076384284729e-05, "epoch": 1.887966804979253, "percentage": 26.97, "elapsed_time": "0:18:16", "remaining_time": "0:49:28"}
+{"current_steps": 460, "total_steps": 1687, "loss": 0.9068, "lr": 3.650476392787873e-05, "epoch": 1.908713692946058, "percentage": 27.27, "elapsed_time": "0:18:26", "remaining_time": "0:49:11"}
+{"current_steps": 465, "total_steps": 1687, "loss": 0.9429, "lr": 3.638699674800758e-05, "epoch": 1.929460580912863, "percentage": 27.56, "elapsed_time": "0:18:36", "remaining_time": "0:48:54"}
+{"current_steps": 470, "total_steps": 1687, "loss": 1.0307, "lr": 3.6267474913278086e-05, "epoch": 1.950207468879668, "percentage": 27.86, "elapsed_time": "0:18:47", "remaining_time": "0:48:39"}
+{"current_steps": 475, "total_steps": 1687, "loss": 1.0214, "lr": 3.614621122161603e-05, "epoch": 1.9709543568464731, "percentage": 28.16, "elapsed_time": "0:18:57", "remaining_time": "0:48:22"}
+{"current_steps": 480, "total_steps": 1687, "loss": 1.0285, "lr": 3.6023218657458334e-05, "epoch": 1.991701244813278, "percentage": 28.45, "elapsed_time": "0:19:08", "remaining_time": "0:48:07"}
+{"current_steps": 485, "total_steps": 1687, "loss": 0.8016, "lr": 3.589851039036277e-05, "epoch": 2.012448132780083, "percentage": 28.75, "elapsed_time": "0:19:18", "remaining_time": "0:47:50"}
+{"current_steps": 490, "total_steps": 1687, "loss": 0.697, "lr": 3.577209977359778e-05, "epoch": 2.033195020746888, "percentage": 29.05, "elapsed_time": "0:19:29", "remaining_time": "0:47:35"}
+{"current_steps": 495, "total_steps": 1687, "loss": 0.803, "lr": 3.5644000342712695e-05, "epoch": 2.0539419087136928, "percentage": 29.34, "elapsed_time": "0:19:39", "remaining_time": "0:47:20"}
+{"current_steps": 500, "total_steps": 1687, "loss": 0.6451, "lr": 3.55142258140884e-05, "epoch": 2.074688796680498, "percentage": 29.64, "elapsed_time": "0:19:50", "remaining_time": "0:47:05"}
+{"current_steps": 505, "total_steps": 1687, "loss": 0.7953, "lr": 3.538279008346861e-05, "epoch": 2.095435684647303, "percentage": 29.93, "elapsed_time": "0:20:00", "remaining_time": "0:46:49"}
+{"current_steps": 510, "total_steps": 1687, "loss": 0.6491, "lr": 3.524970722447197e-05, "epoch": 2.116182572614108, "percentage": 30.23, "elapsed_time": "0:20:10", "remaining_time": "0:46:33"}
+{"current_steps": 515, "total_steps": 1687, "loss": 0.8269, "lr": 3.511499148708517e-05, "epoch": 2.136929460580913, "percentage": 30.53, "elapsed_time": "0:20:20", "remaining_time": "0:46:17"}
+{"current_steps": 520, "total_steps": 1687, "loss": 0.7598, "lr": 3.497865729613702e-05, "epoch": 2.1576763485477177, "percentage": 30.82, "elapsed_time": "0:20:30", "remaining_time": "0:46:00"}
+{"current_steps": 525, "total_steps": 1687, "loss": 0.8091, "lr": 3.484071924975398e-05, "epoch": 2.1784232365145226, "percentage": 31.12, "elapsed_time": "0:20:40", "remaining_time": "0:45:44"}
+{"current_steps": 530, "total_steps": 1687, "loss": 0.7631, "lr": 3.4701192117796964e-05, "epoch": 2.199170124481328, "percentage": 31.42, "elapsed_time": "0:20:50", "remaining_time": "0:45:29"}
+{"current_steps": 535, "total_steps": 1687, "loss": 0.696, "lr": 3.456009084027995e-05, "epoch": 2.219917012448133, "percentage": 31.71, "elapsed_time": "0:21:00", "remaining_time": "0:45:13"}
+{"current_steps": 540, "total_steps": 1687, "loss": 0.7411, "lr": 3.441743052577014e-05, "epoch": 2.240663900414938, "percentage": 32.01, "elapsed_time": "0:21:10", "remaining_time": "0:44:59"}
+{"current_steps": 545, "total_steps": 1687, "loss": 0.7664, "lr": 3.4273226449770314e-05, "epoch": 2.2614107883817427, "percentage": 32.31, "elapsed_time": "0:21:20", "remaining_time": "0:44:42"}
+{"current_steps": 550, "total_steps": 1687, "loss": 0.6762, "lr": 3.4127494053083086e-05, "epoch": 2.2821576763485476, "percentage": 32.6, "elapsed_time": "0:21:30", "remaining_time": "0:44:28"}
+{"current_steps": 555, "total_steps": 1687, "loss": 0.6597, "lr": 3.398024894015764e-05, "epoch": 2.3029045643153525, "percentage": 32.9, "elapsed_time": "0:21:41", "remaining_time": "0:44:14"}
+{"current_steps": 560, "total_steps": 1687, "loss": 0.8247, "lr": 3.383150687741883e-05, "epoch": 2.323651452282158, "percentage": 33.2, "elapsed_time": "0:21:51", "remaining_time": "0:43:59"}
+{"current_steps": 565, "total_steps": 1687, "loss": 0.7557, "lr": 3.368128379157897e-05, "epoch": 2.3443983402489628, "percentage": 33.49, "elapsed_time": "0:22:01", "remaining_time": "0:43:43"}
+{"current_steps": 570, "total_steps": 1687, "loss": 0.7067, "lr": 3.3529595767932496e-05, "epoch": 2.3651452282157677, "percentage": 33.79, "elapsed_time": "0:22:11", "remaining_time": "0:43:29"}
+{"current_steps": 575, "total_steps": 1687, "loss": 0.8143, "lr": 3.3376459048633565e-05, "epoch": 2.3858921161825726, "percentage": 34.08, "elapsed_time": "0:22:21", "remaining_time": "0:43:14"}
+{"current_steps": 580, "total_steps": 1687, "loss": 0.7022, "lr": 3.322189003095696e-05, "epoch": 2.4066390041493775, "percentage": 34.38, "elapsed_time": "0:22:31", "remaining_time": "0:43:00"}
+{"current_steps": 585, "total_steps": 1687, "loss": 0.8357, "lr": 3.306590526554233e-05, "epoch": 2.4273858921161824, "percentage": 34.68, "elapsed_time": "0:22:41", "remaining_time": "0:42:44"}
+{"current_steps": 590, "total_steps": 1687, "loss": 0.8137, "lr": 3.290852145462196e-05, "epoch": 2.4481327800829877, "percentage": 34.97, "elapsed_time": "0:22:51", "remaining_time": "0:42:30"}
+{"current_steps": 595, "total_steps": 1687, "loss": 0.8062, "lr": 3.274975545023242e-05, "epoch": 2.4688796680497926, "percentage": 35.27, "elapsed_time": "0:23:01", "remaining_time": "0:42:16"}
+{"current_steps": 600, "total_steps": 1687, "loss": 0.8078, "lr": 3.258962425241011e-05, "epoch": 2.4896265560165975, "percentage": 35.57, "elapsed_time": "0:23:12", "remaining_time": "0:42:02"}
+{"current_steps": 605, "total_steps": 1687, "loss": 0.7583, "lr": 3.242814500737092e-05, "epoch": 2.5103734439834025, "percentage": 35.86, "elapsed_time": "0:24:16", "remaining_time": "0:43:24"}
+{"current_steps": 610, "total_steps": 1687, "loss": 0.8238, "lr": 3.226533500567433e-05, "epoch": 2.5311203319502074, "percentage": 36.16, "elapsed_time": "0:24:27", "remaining_time": "0:43:10"}
+{"current_steps": 615, "total_steps": 1687, "loss": 0.8316, "lr": 3.2101211680371965e-05, "epoch": 2.5518672199170123, "percentage": 36.46, "elapsed_time": "0:24:37", "remaining_time": "0:42:55"}
+{"current_steps": 620, "total_steps": 1687, "loss": 0.8382, "lr": 3.193579260514097e-05, "epoch": 2.572614107883817, "percentage": 36.75, "elapsed_time": "0:24:47", "remaining_time": "0:42:40"}
+{"current_steps": 625, "total_steps": 1687, "loss": 0.797, "lr": 3.176909549240226e-05, "epoch": 2.5933609958506225, "percentage": 37.05, "elapsed_time": "0:24:58", "remaining_time": "0:42:26"}
+{"current_steps": 630, "total_steps": 1687, "loss": 0.7022, "lr": 3.1601138191423966e-05, "epoch": 2.6141078838174274, "percentage": 37.34, "elapsed_time": "0:25:08", "remaining_time": "0:42:11"}
+{"current_steps": 635, "total_steps": 1687, "loss": 0.754, "lr": 3.143193868641019e-05, "epoch": 2.6348547717842323, "percentage": 37.64, "elapsed_time": "0:25:18", "remaining_time": "0:41:56"}
+{"current_steps": 640, "total_steps": 1687, "loss": 0.7797, "lr": 3.1261515094575335e-05, "epoch": 2.6556016597510372, "percentage": 37.94, "elapsed_time": "0:25:29", "remaining_time": "0:41:42"}
+{"current_steps": 645, "total_steps": 1687, "loss": 0.6938, "lr": 3.108988566420417e-05, "epoch": 2.6763485477178426, "percentage": 38.23, "elapsed_time": "0:25:39", "remaining_time": "0:41:27"}
+{"current_steps": 650, "total_steps": 1687, "loss": 0.7476, "lr": 3.0917068772697934e-05, "epoch": 2.6970954356846475, "percentage": 38.53, "elapsed_time": "0:25:49", "remaining_time": "0:41:12"}
+{"current_steps": 655, "total_steps": 1687, "loss": 0.6439, "lr": 3.074308292460646e-05, "epoch": 2.7178423236514524, "percentage": 38.83, "elapsed_time": "0:26:00", "remaining_time": "0:40:58"}
+{"current_steps": 660, "total_steps": 1687, "loss": 0.6437, "lr": 3.056794674964685e-05, "epoch": 2.7385892116182573, "percentage": 39.12, "elapsed_time": "0:26:10", "remaining_time": "0:40:43"}
+{"current_steps": 665, "total_steps": 1687, "loss": 0.7794, "lr": 3.0391679000708673e-05, "epoch": 2.759336099585062, "percentage": 39.42, "elapsed_time": "0:26:20", "remaining_time": "0:40:29"}
+{"current_steps": 670, "total_steps": 1687, "loss": 0.7425, "lr": 3.0214298551845967e-05, "epoch": 2.780082987551867, "percentage": 39.72, "elapsed_time": "0:26:31", "remaining_time": "0:40:15"}
+{"current_steps": 675, "total_steps": 1687, "loss": 0.799, "lr": 3.0035824396256267e-05, "epoch": 2.800829875518672, "percentage": 40.01, "elapsed_time": "0:26:41", "remaining_time": "0:40:00"}
+{"current_steps": 680, "total_steps": 1687, "loss": 0.7134, "lr": 2.9856275644246903e-05, "epoch": 2.821576763485477, "percentage": 40.31, "elapsed_time": "0:26:51", "remaining_time": "0:39:46"}
+{"current_steps": 685, "total_steps": 1687, "loss": 0.7767, "lr": 2.9675671521188766e-05, "epoch": 2.8423236514522823, "percentage": 40.6, "elapsed_time": "0:27:01", "remaining_time": "0:39:32"}
+{"current_steps": 690, "total_steps": 1687, "loss": 0.8742, "lr": 2.949403136545769e-05, "epoch": 2.863070539419087, "percentage": 40.9, "elapsed_time": "0:27:11", "remaining_time": "0:39:17"}
+{"current_steps": 695, "total_steps": 1687, "loss": 0.6692, "lr": 2.9311374626363793e-05, "epoch": 2.883817427385892, "percentage": 41.2, "elapsed_time": "0:27:21", "remaining_time": "0:39:03"}
+{"current_steps": 700, "total_steps": 1687, "loss": 0.7173, "lr": 2.9127720862068928e-05, "epoch": 2.904564315352697, "percentage": 41.49, "elapsed_time": "0:27:31", "remaining_time": "0:38:49"}
+{"current_steps": 705, "total_steps": 1687, "loss": 0.7826, "lr": 2.8943089737492465e-05, "epoch": 2.9253112033195023, "percentage": 41.79, "elapsed_time": "0:27:41", "remaining_time": "0:38:34"}
+{"current_steps": 710, "total_steps": 1687, "loss": 0.7881, "lr": 2.8757501022205653e-05, "epoch": 2.9460580912863072, "percentage": 42.09, "elapsed_time": "0:27:52", "remaining_time": "0:38:21"}
+{"current_steps": 715, "total_steps": 1687, "loss": 0.638, "lr": 2.8570974588314767e-05, "epoch": 2.966804979253112, "percentage": 42.38, "elapsed_time": "0:28:02", "remaining_time": "0:38:07"}
+{"current_steps": 720, "total_steps": 1687, "loss": 0.7669, "lr": 2.8383530408333285e-05, "epoch": 2.987551867219917, "percentage": 42.68, "elapsed_time": "0:28:13", "remaining_time": "0:37:53"}
+{"current_steps": 725, "total_steps": 1687, "loss": 0.6422, "lr": 2.8195188553043317e-05, "epoch": 3.008298755186722, "percentage": 42.98, "elapsed_time": "0:28:23", "remaining_time": "0:37:39"}
+{"current_steps": 730, "total_steps": 1687, "loss": 0.5641, "lr": 2.800596918934648e-05, "epoch": 3.029045643153527, "percentage": 43.27, "elapsed_time": "0:28:33", "remaining_time": "0:37:25"}
+{"current_steps": 735, "total_steps": 1687, "loss": 0.6125, "lr": 2.7815892578104554e-05, "epoch": 3.0497925311203318, "percentage": 43.57, "elapsed_time": "0:28:42", "remaining_time": "0:37:11"}
+{"current_steps": 740, "total_steps": 1687, "loss": 0.4968, "lr": 2.762497907196996e-05, "epoch": 3.070539419087137, "percentage": 43.86, "elapsed_time": "0:28:52", "remaining_time": "0:36:57"}
+{"current_steps": 745, "total_steps": 1687, "loss": 0.591, "lr": 2.743324911320655e-05, "epoch": 3.091286307053942, "percentage": 44.16, "elapsed_time": "0:29:02", "remaining_time": "0:36:43"}
+{"current_steps": 750, "total_steps": 1687, "loss": 0.5391, "lr": 2.724072323150069e-05, "epoch": 3.112033195020747, "percentage": 44.46, "elapsed_time": "0:29:12", "remaining_time": "0:36:29"}
+{"current_steps": 755, "total_steps": 1687, "loss": 0.5404, "lr": 2.704742204176301e-05, "epoch": 3.132780082987552, "percentage": 44.75, "elapsed_time": "0:29:22", "remaining_time": "0:36:15"}
+{"current_steps": 760, "total_steps": 1687, "loss": 0.546, "lr": 2.6853366241921083e-05, "epoch": 3.1535269709543567, "percentage": 45.05, "elapsed_time": "0:29:32", "remaining_time": "0:36:01"}
+{"current_steps": 765, "total_steps": 1687, "loss": 0.5017, "lr": 2.6658576610703142e-05, "epoch": 3.1742738589211617, "percentage": 45.35, "elapsed_time": "0:29:42", "remaining_time": "0:35:48"}
+{"current_steps": 770, "total_steps": 1687, "loss": 0.4833, "lr": 2.6463074005413187e-05, "epoch": 3.195020746887967, "percentage": 45.64, "elapsed_time": "0:29:53", "remaining_time": "0:35:35"}
+{"current_steps": 775, "total_steps": 1687, "loss": 0.5946, "lr": 2.6266879359697647e-05, "epoch": 3.215767634854772, "percentage": 45.94, "elapsed_time": "0:30:03", "remaining_time": "0:35:22"}
+{"current_steps": 780, "total_steps": 1687, "loss": 0.5182, "lr": 2.6070013681303933e-05, "epoch": 3.236514522821577, "percentage": 46.24, "elapsed_time": "0:30:13", "remaining_time": "0:35:08"}
+{"current_steps": 785, "total_steps": 1687, "loss": 0.5421, "lr": 2.5872498049830973e-05, "epoch": 3.2572614107883817, "percentage": 46.53, "elapsed_time": "0:30:23", "remaining_time": "0:34:55"}
+{"current_steps": 790, "total_steps": 1687, "loss": 0.4724, "lr": 2.5674353614472084e-05, "epoch": 3.2780082987551866, "percentage": 46.83, "elapsed_time": "0:30:33", "remaining_time": "0:34:42"}
+{"current_steps": 795, "total_steps": 1687, "loss": 0.4999, "lr": 2.5475601591750448e-05, "epoch": 3.2987551867219915, "percentage": 47.13, "elapsed_time": "0:30:43", "remaining_time": "0:34:28"}
+{"current_steps": 800, "total_steps": 1687, "loss": 0.5116, "lr": 2.5276263263247282e-05, "epoch": 3.3195020746887964, "percentage": 47.42, "elapsed_time": "0:30:54", "remaining_time": "0:34:15"}
+{"current_steps": 805, "total_steps": 1687, "loss": 0.6154, "lr": 2.5076359973323107e-05, "epoch": 3.340248962655602, "percentage": 47.72, "elapsed_time": "0:31:58", "remaining_time": "0:35:01"}
+{"current_steps": 810, "total_steps": 1687, "loss": 0.5952, "lr": 2.4875913126832297e-05, "epoch": 3.3609958506224067, "percentage": 48.01, "elapsed_time": "0:32:08", "remaining_time": "0:34:48"}
+{"current_steps": 815, "total_steps": 1687, "loss": 0.4865, "lr": 2.4674944186831108e-05, "epoch": 3.3817427385892116, "percentage": 48.31, "elapsed_time": "0:32:19", "remaining_time": "0:34:34"}
+{"current_steps": 820, "total_steps": 1687, "loss": 0.504, "lr": 2.4473474672279497e-05, "epoch": 3.4024896265560165, "percentage": 48.61, "elapsed_time": "0:32:29", "remaining_time": "0:34:21"}
+{"current_steps": 825, "total_steps": 1687, "loss": 0.5078, "lr": 2.427152615573697e-05, "epoch": 3.4232365145228214, "percentage": 48.9, "elapsed_time": "0:32:40", "remaining_time": "0:34:08"}
+{"current_steps": 830, "total_steps": 1687, "loss": 0.5275, "lr": 2.4069120261052682e-05, "epoch": 3.4439834024896268, "percentage": 49.2, "elapsed_time": "0:32:49", "remaining_time": "0:33:53"}
+{"current_steps": 835, "total_steps": 1687, "loss": 0.5831, "lr": 2.386627866105002e-05, "epoch": 3.4647302904564317, "percentage": 49.5, "elapsed_time": "0:32:59", "remaining_time": "0:33:39"}
+{"current_steps": 840, "total_steps": 1687, "loss": 0.5253, "lr": 2.3663023075205992e-05, "epoch": 3.4854771784232366, "percentage": 49.79, "elapsed_time": "0:33:09", "remaining_time": "0:33:26"}
+{"current_steps": 845, "total_steps": 1687, "loss": 0.5637, "lr": 2.3459375267325552e-05, "epoch": 3.5062240663900415, "percentage": 50.09, "elapsed_time": "0:33:19", "remaining_time": "0:33:12"}
+{"current_steps": 850, "total_steps": 1687, "loss": 0.612, "lr": 2.325535704321126e-05, "epoch": 3.5269709543568464, "percentage": 50.39, "elapsed_time": "0:33:29", "remaining_time": "0:32:58"}
+{"current_steps": 855, "total_steps": 1687, "loss": 0.5303, "lr": 2.3050990248328365e-05, "epoch": 3.5477178423236513, "percentage": 50.68, "elapsed_time": "0:33:39", "remaining_time": "0:32:44"}
+{"current_steps": 860, "total_steps": 1687, "loss": 0.5785, "lr": 2.2846296765465708e-05, "epoch": 3.568464730290456, "percentage": 50.98, "elapsed_time": "0:33:49", "remaining_time": "0:32:31"}
+{"current_steps": 865, "total_steps": 1687, "loss": 0.5289, "lr": 2.2641298512392585e-05, "epoch": 3.5892116182572615, "percentage": 51.27, "elapsed_time": "0:33:58", "remaining_time": "0:32:17"}
+{"current_steps": 870, "total_steps": 1687, "loss": 0.519, "lr": 2.2436017439511878e-05, "epoch": 3.6099585062240664, "percentage": 51.57, "elapsed_time": "0:34:08", "remaining_time": "0:32:03"}
+{"current_steps": 875, "total_steps": 1687, "loss": 0.5643, "lr": 2.2230475527509712e-05, "epoch": 3.6307053941908713, "percentage": 51.87, "elapsed_time": "0:34:18", "remaining_time": "0:31:50"}
+{"current_steps": 880, "total_steps": 1687, "loss": 0.5333, "lr": 2.2024694785001814e-05, "epoch": 3.6514522821576763, "percentage": 52.16, "elapsed_time": "0:34:28", "remaining_time": "0:31:36"}
+{"current_steps": 885, "total_steps": 1687, "loss": 0.5145, "lr": 2.1818697246176943e-05, "epoch": 3.6721991701244816, "percentage": 52.46, "elapsed_time": "0:34:37", "remaining_time": "0:31:22"}
+{"current_steps": 890, "total_steps": 1687, "loss": 0.6124, "lr": 2.161250496843756e-05, "epoch": 3.6929460580912865, "percentage": 52.76, "elapsed_time": "0:34:48", "remaining_time": "0:31:10"}
+{"current_steps": 895, "total_steps": 1687, "loss": 0.5131, "lr": 2.1406140030037988e-05, "epoch": 3.7136929460580914, "percentage": 53.05, "elapsed_time": "0:34:58", "remaining_time": "0:30:56"}
+{"current_steps": 900, "total_steps": 1687, "loss": 0.6005, "lr": 2.119962452772039e-05, "epoch": 3.7344398340248963, "percentage": 53.35, "elapsed_time": "0:35:08", "remaining_time": "0:30:43"}
+{"current_steps": 905, "total_steps": 1687, "loss": 0.637, "lr": 2.0992980574348687e-05, "epoch": 3.7551867219917012, "percentage": 53.65, "elapsed_time": "0:35:17", "remaining_time": "0:30:30"}
+{"current_steps": 910, "total_steps": 1687, "loss": 0.562, "lr": 2.0786230296540864e-05, "epoch": 3.775933609958506, "percentage": 53.94, "elapsed_time": "0:35:28", "remaining_time": "0:30:17"}
+{"current_steps": 915, "total_steps": 1687, "loss": 0.4917, "lr": 2.0579395832299688e-05, "epoch": 3.796680497925311, "percentage": 54.24, "elapsed_time": "0:35:38", "remaining_time": "0:30:04"}
+{"current_steps": 920, "total_steps": 1687, "loss": 0.6087, "lr": 2.0372499328642277e-05, "epoch": 3.817427385892116, "percentage": 54.53, "elapsed_time": "0:35:48", "remaining_time": "0:29:50"}
+{"current_steps": 925, "total_steps": 1687, "loss": 0.54, "lr": 2.016556293922869e-05, "epoch": 3.8381742738589213, "percentage": 54.83, "elapsed_time": "0:35:58", "remaining_time": "0:29:37"}
+{"current_steps": 930, "total_steps": 1687, "loss": 0.5028, "lr": 1.9958608821989792e-05, "epoch": 3.858921161825726, "percentage": 55.13, "elapsed_time": "0:36:08", "remaining_time": "0:29:24"}
+{"current_steps": 935, "total_steps": 1687, "loss": 0.4334, "lr": 1.9751659136754686e-05, "epoch": 3.879668049792531, "percentage": 55.42, "elapsed_time": "0:36:19", "remaining_time": "0:29:12"}
+{"current_steps": 940, "total_steps": 1687, "loss": 0.3988, "lr": 1.9544736042877886e-05, "epoch": 3.900414937759336, "percentage": 55.72, "elapsed_time": "0:36:29", "remaining_time": "0:29:00"}
+{"current_steps": 945, "total_steps": 1687, "loss": 0.5395, "lr": 1.9337861696866643e-05, "epoch": 3.921161825726141, "percentage": 56.02, "elapsed_time": "0:36:39", "remaining_time": "0:28:47"}
+{"current_steps": 950, "total_steps": 1687, "loss": 0.6749, "lr": 1.913105825000844e-05, "epoch": 3.9419087136929463, "percentage": 56.31, "elapsed_time": "0:36:50", "remaining_time": "0:28:34"}
+{"current_steps": 955, "total_steps": 1687, "loss": 0.5692, "lr": 1.8924347845999197e-05, "epoch": 3.962655601659751, "percentage": 56.61, "elapsed_time": "0:37:00", "remaining_time": "0:28:21"}
+{"current_steps": 960, "total_steps": 1687, "loss": 0.5391, "lr": 1.871775261857215e-05, "epoch": 3.983402489626556, "percentage": 56.91, "elapsed_time": "0:37:10", "remaining_time": "0:28:08"}
+{"current_steps": 965, "total_steps": 1687, "loss": 0.5623, "lr": 1.8511294689127887e-05, "epoch": 4.004149377593361, "percentage": 57.2, "elapsed_time": "0:37:20", "remaining_time": "0:27:56"}
+{"current_steps": 970, "total_steps": 1687, "loss": 0.4125, "lr": 1.830499616436567e-05, "epoch": 4.024896265560166, "percentage": 57.5, "elapsed_time": "0:37:30", "remaining_time": "0:27:43"}
+{"current_steps": 975, "total_steps": 1687, "loss": 0.4243, "lr": 1.8098879133916352e-05, "epoch": 4.045643153526971, "percentage": 57.79, "elapsed_time": "0:37:40", "remaining_time": "0:27:30"}
+{"current_steps": 980, "total_steps": 1687, "loss": 0.4303, "lr": 1.789296566797706e-05, "epoch": 4.066390041493776, "percentage": 58.09, "elapsed_time": "0:37:50", "remaining_time": "0:27:17"}
+{"current_steps": 985, "total_steps": 1687, "loss": 0.418, "lr": 1.768727781494807e-05, "epoch": 4.087136929460581, "percentage": 58.39, "elapsed_time": "0:38:00", "remaining_time": "0:27:05"}
+{"current_steps": 990, "total_steps": 1687, "loss": 0.3992, "lr": 1.7481837599071903e-05, "epoch": 4.1078838174273855, "percentage": 58.68, "elapsed_time": "0:38:10", "remaining_time": "0:26:52"}
+{"current_steps": 995, "total_steps": 1687, "loss": 0.379, "lr": 1.7276667018075073e-05, "epoch": 4.12863070539419, "percentage": 58.98, "elapsed_time": "0:38:20", "remaining_time": "0:26:39"}
+{"current_steps": 1000, "total_steps": 1687, "loss": 0.3745, "lr": 1.7071788040812655e-05, "epoch": 4.149377593360996, "percentage": 59.28, "elapsed_time": "0:38:31", "remaining_time": "0:26:27"}
+{"current_steps": 1005, "total_steps": 1687, "loss": 0.3669, "lr": 1.686722260491597e-05, "epoch": 4.170124481327801, "percentage": 59.57, "elapsed_time": "0:39:36", "remaining_time": "0:26:52"}
+{"current_steps": 1010, "total_steps": 1687, "loss": 0.3601, "lr": 1.6662992614443525e-05, "epoch": 4.190871369294606, "percentage": 59.87, "elapsed_time": "0:39:46", "remaining_time": "0:26:39"}
+{"current_steps": 1015, "total_steps": 1687, "loss": 0.3598, "lr": 1.6459119937535702e-05, "epoch": 4.211618257261411, "percentage": 60.17, "elapsed_time": "0:39:57", "remaining_time": "0:26:27"}
+{"current_steps": 1020, "total_steps": 1687, "loss": 0.3857, "lr": 1.6255626404073132e-05, "epoch": 4.232365145228216, "percentage": 60.46, "elapsed_time": "0:40:07", "remaining_time": "0:26:14"}
+{"current_steps": 1025, "total_steps": 1687, "loss": 0.3545, "lr": 1.605253380333927e-05, "epoch": 4.253112033195021, "percentage": 60.76, "elapsed_time": "0:40:17", "remaining_time": "0:26:01"}
+{"current_steps": 1030, "total_steps": 1687, "loss": 0.327, "lr": 1.584986388168728e-05, "epoch": 4.273858921161826, "percentage": 61.06, "elapsed_time": "0:40:27", "remaining_time": "0:25:48"}
+{"current_steps": 1035, "total_steps": 1687, "loss": 0.4217, "lr": 1.5647638340211525e-05, "epoch": 4.2946058091286305, "percentage": 61.35, "elapsed_time": "0:40:37", "remaining_time": "0:25:35"}
+{"current_steps": 1040, "total_steps": 1687, "loss": 0.3972, "lr": 1.5445878832423876e-05, "epoch": 4.3153526970954355, "percentage": 61.65, "elapsed_time": "0:40:47", "remaining_time": "0:25:22"}
+{"current_steps": 1045, "total_steps": 1687, "loss": 0.4227, "lr": 1.5244606961935187e-05, "epoch": 4.33609958506224, "percentage": 61.94, "elapsed_time": "0:40:57", "remaining_time": "0:25:09"}
+{"current_steps": 1050, "total_steps": 1687, "loss": 0.3818, "lr": 1.5043844280142005e-05, "epoch": 4.356846473029045, "percentage": 62.24, "elapsed_time": "0:41:08", "remaining_time": "0:24:57"}
+{"current_steps": 1055, "total_steps": 1687, "loss": 0.3707, "lr": 1.4843612283918995e-05, "epoch": 4.377593360995851, "percentage": 62.54, "elapsed_time": "0:41:18", "remaining_time": "0:24:44"}
+{"current_steps": 1060, "total_steps": 1687, "loss": 0.3399, "lr": 1.4643932413317079e-05, "epoch": 4.398340248962656, "percentage": 62.83, "elapsed_time": "0:41:28", "remaining_time": "0:24:32"}
+{"current_steps": 1065, "total_steps": 1687, "loss": 0.3923, "lr": 1.4444826049267784e-05, "epoch": 4.419087136929461, "percentage": 63.13, "elapsed_time": "0:41:38", "remaining_time": "0:24:19"}
+{"current_steps": 1070, "total_steps": 1687, "loss": 0.3607, "lr": 1.4246314511293777e-05, "epoch": 4.439834024896266, "percentage": 63.43, "elapsed_time": "0:41:48", "remaining_time": "0:24:06"}
+{"current_steps": 1075, "total_steps": 1687, "loss": 0.4178, "lr": 1.4048419055226146e-05, "epoch": 4.460580912863071, "percentage": 63.72, "elapsed_time": "0:41:58", "remaining_time": "0:23:53"}
+{"current_steps": 1080, "total_steps": 1687, "loss": 0.4052, "lr": 1.3851160870928317e-05, "epoch": 4.481327800829876, "percentage": 64.02, "elapsed_time": "0:42:08", "remaining_time": "0:23:41"}
+{"current_steps": 1085, "total_steps": 1687, "loss": 0.343, "lr": 1.3654561080027213e-05, "epoch": 4.5020746887966805, "percentage": 64.32, "elapsed_time": "0:42:19", "remaining_time": "0:23:28"}
+{"current_steps": 1090, "total_steps": 1687, "loss": 0.393, "lr": 1.345864073365157e-05, "epoch": 4.522821576763485, "percentage": 64.61, "elapsed_time": "0:42:29", "remaining_time": "0:23:16"}
+{"current_steps": 1095, "total_steps": 1687, "loss": 0.4336, "lr": 1.3263420810177902e-05, "epoch": 4.54356846473029, "percentage": 64.91, "elapsed_time": "0:42:38", "remaining_time": "0:23:03"}
+{"current_steps": 1100, "total_steps": 1687, "loss": 0.4127, "lr": 1.3068922212984188e-05, "epoch": 4.564315352697095, "percentage": 65.2, "elapsed_time": "0:42:48", "remaining_time": "0:22:50"}
+{"current_steps": 1105, "total_steps": 1687, "loss": 0.4029, "lr": 1.287516576821167e-05, "epoch": 4.5850622406639, "percentage": 65.5, "elapsed_time": "0:42:58", "remaining_time": "0:22:38"}
+{"current_steps": 1110, "total_steps": 1687, "loss": 0.3313, "lr": 1.2682172222534805e-05, "epoch": 4.605809128630705, "percentage": 65.8, "elapsed_time": "0:43:08", "remaining_time": "0:22:25"}
+{"current_steps": 1115, "total_steps": 1687, "loss": 0.3613, "lr": 1.2489962240939857e-05, "epoch": 4.62655601659751, "percentage": 66.09, "elapsed_time": "0:43:18", "remaining_time": "0:22:13"}
+{"current_steps": 1120, "total_steps": 1687, "loss": 0.3179, "lr": 1.229855640451213e-05, "epoch": 4.647302904564316, "percentage": 66.39, "elapsed_time": "0:43:29", "remaining_time": "0:22:00"}
+{"current_steps": 1125, "total_steps": 1687, "loss": 0.4198, "lr": 1.2107975208232259e-05, "epoch": 4.668049792531121, "percentage": 66.69, "elapsed_time": "0:43:38", "remaining_time": "0:21:48"}
+{"current_steps": 1130, "total_steps": 1687, "loss": 0.3607, "lr": 1.1918239058781636e-05, "epoch": 4.6887966804979255, "percentage": 66.98, "elapsed_time": "0:43:48", "remaining_time": "0:21:35"}
+{"current_steps": 1135, "total_steps": 1687, "loss": 0.3285, "lr": 1.1729368272357419e-05, "epoch": 4.70954356846473, "percentage": 67.28, "elapsed_time": "0:43:58", "remaining_time": "0:21:23"}
+{"current_steps": 1140, "total_steps": 1687, "loss": 0.3855, "lr": 1.1541383072497077e-05, "epoch": 4.730290456431535, "percentage": 67.58, "elapsed_time": "0:44:08", "remaining_time": "0:21:10"}
+{"current_steps": 1145, "total_steps": 1687, "loss": 0.337, "lr": 1.1354303587913003e-05, "epoch": 4.75103734439834, "percentage": 67.87, "elapsed_time": "0:44:18", "remaining_time": "0:20:58"}
+{"current_steps": 1150, "total_steps": 1687, "loss": 0.3401, "lr": 1.1168149850337136e-05, "epoch": 4.771784232365145, "percentage": 68.17, "elapsed_time": "0:44:28", "remaining_time": "0:20:46"}
+{"current_steps": 1155, "total_steps": 1687, "loss": 0.3953, "lr": 1.0982941792376125e-05, "epoch": 4.79253112033195, "percentage": 68.46, "elapsed_time": "0:44:38", "remaining_time": "0:20:33"}
+{"current_steps": 1160, "total_steps": 1687, "loss": 0.41, "lr": 1.0798699245376959e-05, "epoch": 4.813278008298755, "percentage": 68.76, "elapsed_time": "0:44:47", "remaining_time": "0:20:21"}
+{"current_steps": 1165, "total_steps": 1687, "loss": 0.3275, "lr": 1.0615441937303534e-05, "epoch": 4.83402489626556, "percentage": 69.06, "elapsed_time": "0:44:58", "remaining_time": "0:20:08"}
+{"current_steps": 1170, "total_steps": 1687, "loss": 0.3779, "lr": 1.0433189490624253e-05, "epoch": 4.854771784232365, "percentage": 69.35, "elapsed_time": "0:45:08", "remaining_time": "0:19:56"}
+{"current_steps": 1175, "total_steps": 1687, "loss": 0.3465, "lr": 1.0251961420210937e-05, "epoch": 4.875518672199171, "percentage": 69.65, "elapsed_time": "0:45:18", "remaining_time": "0:19:44"}
+{"current_steps": 1180, "total_steps": 1687, "loss": 0.3008, "lr": 1.0071777131249237e-05, "epoch": 4.8962655601659755, "percentage": 69.95, "elapsed_time": "0:45:28", "remaining_time": "0:19:32"}
+{"current_steps": 1185, "total_steps": 1687, "loss": 0.3767, "lr": 9.892655917160814e-06, "epoch": 4.91701244813278, "percentage": 70.24, "elapsed_time": "0:45:39", "remaining_time": "0:19:20"}
+{"current_steps": 1190, "total_steps": 1687, "loss": 0.3356, "lr": 9.714616957537466e-06, "epoch": 4.937759336099585, "percentage": 70.54, "elapsed_time": "0:45:49", "remaining_time": "0:19:08"}
+{"current_steps": 1195, "total_steps": 1687, "loss": 0.3299, "lr": 9.537679316087491e-06, "epoch": 4.95850622406639, "percentage": 70.84, "elapsed_time": "0:45:59", "remaining_time": "0:18:56"}
+{"current_steps": 1200, "total_steps": 1687, "loss": 0.3432, "lr": 9.361861938594332e-06, "epoch": 4.979253112033195, "percentage": 71.13, "elapsed_time": "0:46:09", "remaining_time": "0:18:43"}
+{"current_steps": 1205, "total_steps": 1687, "loss": 0.3926, "lr": 9.187183650888056e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "0:47:18", "remaining_time": "0:18:55"}
+{"current_steps": 1210, "total_steps": 1687, "loss": 0.2897, "lr": 9.013663156829438e-06, "epoch": 5.020746887966805, "percentage": 71.72, "elapsed_time": "0:47:28", "remaining_time": "0:18:43"}
+{"current_steps": 1215, "total_steps": 1687, "loss": 0.253, "lr": 8.841319036307334e-06, "epoch": 5.04149377593361, "percentage": 72.02, "elapsed_time": "0:47:38", "remaining_time": "0:18:30"}
+{"current_steps": 1220, "total_steps": 1687, "loss": 0.2583, "lr": 8.670169743249143e-06, "epoch": 5.062240663900415, "percentage": 72.32, "elapsed_time": "0:47:48", "remaining_time": "0:18:18"}
+{"current_steps": 1225, "total_steps": 1687, "loss": 0.2949, "lr": 8.50023360364487e-06, "epoch": 5.08298755186722, "percentage": 72.61, "elapsed_time": "0:47:59", "remaining_time": "0:18:05"}
+{"current_steps": 1230, "total_steps": 1687, "loss": 0.2688, "lr": 8.331528813584832e-06, "epoch": 5.1037344398340245, "percentage": 72.91, "elapsed_time": "0:48:09", "remaining_time": "0:17:53"}
+{"current_steps": 1235, "total_steps": 1687, "loss": 0.3074, "lr": 8.164073437311315e-06, "epoch": 5.124481327800829, "percentage": 73.21, "elapsed_time": "0:48:18", "remaining_time": "0:17:40"}
+{"current_steps": 1240, "total_steps": 1687, "loss": 0.2572, "lr": 7.997885405284305e-06, "epoch": 5.145228215767635, "percentage": 73.5, "elapsed_time": "0:48:28", "remaining_time": "0:17:28"}
+{"current_steps": 1245, "total_steps": 1687, "loss": 0.2603, "lr": 7.83298251226158e-06, "epoch": 5.16597510373444, "percentage": 73.8, "elapsed_time": "0:48:39", "remaining_time": "0:17:16"}
+{"current_steps": 1250, "total_steps": 1687, "loss": 0.2724, "lr": 7.669382415393298e-06, "epoch": 5.186721991701245, "percentage": 74.1, "elapsed_time": "0:48:48", "remaining_time": "0:17:03"}
+{"current_steps": 1255, "total_steps": 1687, "loss": 0.2, "lr": 7.507102632331382e-06, "epoch": 5.20746887966805, "percentage": 74.39, "elapsed_time": "0:48:59", "remaining_time": "0:16:51"}
+{"current_steps": 1260, "total_steps": 1687, "loss": 0.2709, "lr": 7.3461605393537415e-06, "epoch": 5.228215767634855, "percentage": 74.69, "elapsed_time": "0:49:08", "remaining_time": "0:16:39"}
+{"current_steps": 1265, "total_steps": 1687, "loss": 0.2643, "lr": 7.186573369503731e-06, "epoch": 5.24896265560166, "percentage": 74.99, "elapsed_time": "0:49:18", "remaining_time": "0:16:26"}
+{"current_steps": 1270, "total_steps": 1687, "loss": 0.2853, "lr": 7.028358210744881e-06, "epoch": 5.269709543568465, "percentage": 75.28, "elapsed_time": "0:49:28", "remaining_time": "0:16:14"}
+{"current_steps": 1275, "total_steps": 1687, "loss": 0.2802, "lr": 6.8715320041312095e-06, "epoch": 5.29045643153527, "percentage": 75.58, "elapsed_time": "0:49:38", "remaining_time": "0:16:02"}
+{"current_steps": 1280, "total_steps": 1687, "loss": 0.2687, "lr": 6.716111541993213e-06, "epoch": 5.3112033195020745, "percentage": 75.87, "elapsed_time": "0:49:48", "remaining_time": "0:15:50"}
+{"current_steps": 1285, "total_steps": 1687, "loss": 0.273, "lr": 6.562113466139836e-06, "epoch": 5.331950207468879, "percentage": 76.17, "elapsed_time": "0:49:57", "remaining_time": "0:15:37"}
+{"current_steps": 1290, "total_steps": 1687, "loss": 0.2853, "lr": 6.4095542660765145e-06, "epoch": 5.352697095435684, "percentage": 76.47, "elapsed_time": "0:50:07", "remaining_time": "0:15:25"}
+{"current_steps": 1295, "total_steps": 1687, "loss": 0.2691, "lr": 6.258450277239545e-06, "epoch": 5.37344398340249, "percentage": 76.76, "elapsed_time": "0:50:17", "remaining_time": "0:15:13"}
+{"current_steps": 1300, "total_steps": 1687, "loss": 0.2528, "lr": 6.108817679246979e-06, "epoch": 5.394190871369295, "percentage": 77.06, "elapsed_time": "0:50:27", "remaining_time": "0:15:01"}
+{"current_steps": 1305, "total_steps": 1687, "loss": 0.2519, "lr": 5.960672494166113e-06, "epoch": 5.4149377593361, "percentage": 77.36, "elapsed_time": "0:50:36", "remaining_time": "0:14:48"}
+{"current_steps": 1310, "total_steps": 1687, "loss": 0.2879, "lr": 5.8140305847979895e-06, "epoch": 5.435684647302905, "percentage": 77.65, "elapsed_time": "0:50:46", "remaining_time": "0:14:36"}
+{"current_steps": 1315, "total_steps": 1687, "loss": 0.287, "lr": 5.668907652978783e-06, "epoch": 5.45643153526971, "percentage": 77.95, "elapsed_time": "0:50:57", "remaining_time": "0:14:24"}
+{"current_steps": 1320, "total_steps": 1687, "loss": 0.2254, "lr": 5.5253192378985966e-06, "epoch": 5.477178423236515, "percentage": 78.25, "elapsed_time": "0:51:07", "remaining_time": "0:14:12"}
+{"current_steps": 1325, "total_steps": 1687, "loss": 0.2503, "lr": 5.383280714437518e-06, "epoch": 5.4979253112033195, "percentage": 78.54, "elapsed_time": "0:51:17", "remaining_time": "0:14:00"}
+{"current_steps": 1330, "total_steps": 1687, "loss": 0.2999, "lr": 5.242807291519374e-06, "epoch": 5.518672199170124, "percentage": 78.84, "elapsed_time": "0:51:27", "remaining_time": "0:13:48"}
+{"current_steps": 1335, "total_steps": 1687, "loss": 0.1811, "lr": 5.103914010483206e-06, "epoch": 5.539419087136929, "percentage": 79.13, "elapsed_time": "0:51:37", "remaining_time": "0:13:36"}
+{"current_steps": 1340, "total_steps": 1687, "loss": 0.2922, "lr": 4.966615743472709e-06, "epoch": 5.560165975103734, "percentage": 79.43, "elapsed_time": "0:51:47", "remaining_time": "0:13:24"}
+{"current_steps": 1345, "total_steps": 1687, "loss": 0.2274, "lr": 4.830927191843779e-06, "epoch": 5.580912863070539, "percentage": 79.73, "elapsed_time": "0:51:57", "remaining_time": "0:13:12"}
+{"current_steps": 1350, "total_steps": 1687, "loss": 0.2435, "lr": 4.696862884590349e-06, "epoch": 5.601659751037344, "percentage": 80.02, "elapsed_time": "0:52:07", "remaining_time": "0:13:00"}
+{"current_steps": 1355, "total_steps": 1687, "loss": 0.2842, "lr": 4.564437176788681e-06, "epoch": 5.622406639004149, "percentage": 80.32, "elapsed_time": "0:52:17", "remaining_time": "0:12:48"}
+{"current_steps": 1360, "total_steps": 1687, "loss": 0.229, "lr": 4.433664248060295e-06, "epoch": 5.643153526970955, "percentage": 80.62, "elapsed_time": "0:52:27", "remaining_time": "0:12:36"}
+{"current_steps": 1365, "total_steps": 1687, "loss": 0.2755, "lr": 4.304558101053629e-06, "epoch": 5.66390041493776, "percentage": 80.91, "elapsed_time": "0:52:37", "remaining_time": "0:12:24"}
+{"current_steps": 1370, "total_steps": 1687, "loss": 0.2214, "lr": 4.177132559944761e-06, "epoch": 5.6846473029045645, "percentage": 81.21, "elapsed_time": "0:52:47", "remaining_time": "0:12:12"}
+{"current_steps": 1375, "total_steps": 1687, "loss": 0.27, "lr": 4.051401268957087e-06, "epoch": 5.7053941908713695, "percentage": 81.51, "elapsed_time": "0:52:57", "remaining_time": "0:12:00"}
+{"current_steps": 1380, "total_steps": 1687, "loss": 0.2684, "lr": 3.927377690900436e-06, "epoch": 5.726141078838174, "percentage": 81.8, "elapsed_time": "0:53:06", "remaining_time": "0:11:48"}
+{"current_steps": 1385, "total_steps": 1687, "loss": 0.2639, "lr": 3.805075105729459e-06, "epoch": 5.746887966804979, "percentage": 82.1, "elapsed_time": "0:53:16", "remaining_time": "0:11:37"}
+{"current_steps": 1390, "total_steps": 1687, "loss": 0.2862, "lr": 3.6845066091216917e-06, "epoch": 5.767634854771784, "percentage": 82.39, "elapsed_time": "0:53:26", "remaining_time": "0:11:25"}
+{"current_steps": 1395, "total_steps": 1687, "loss": 0.2365, "lr": 3.56568511107533e-06, "epoch": 5.788381742738589, "percentage": 82.69, "elapsed_time": "0:53:36", "remaining_time": "0:11:13"}
+{"current_steps": 1400, "total_steps": 1687, "loss": 0.3138, "lr": 3.448623334526853e-06, "epoch": 5.809128630705394, "percentage": 82.99, "elapsed_time": "0:53:46", "remaining_time": "0:11:01"}
+{"current_steps": 1405, "total_steps": 1687, "loss": 0.2836, "lr": 3.333333813988726e-06, "epoch": 5.829875518672199, "percentage": 83.28, "elapsed_time": "0:54:55", "remaining_time": "0:11:01"}
+{"current_steps": 1410, "total_steps": 1687, "loss": 0.2612, "lr": 3.219828894207242e-06, "epoch": 5.850622406639004, "percentage": 83.58, "elapsed_time": "0:55:04", "remaining_time": "0:10:49"}
+{"current_steps": 1415, "total_steps": 1687, "loss": 0.2353, "lr": 3.1081207288406846e-06, "epoch": 5.87136929460581, "percentage": 83.88, "elapsed_time": "0:55:14", "remaining_time": "0:10:37"}
+{"current_steps": 1420, "total_steps": 1687, "loss": 0.2309, "lr": 2.9982212791580044e-06, "epoch": 5.8921161825726145, "percentage": 84.17, "elapsed_time": "0:55:24", "remaining_time": "0:10:25"}
+{"current_steps": 1425, "total_steps": 1687, "loss": 0.2902, "lr": 2.890142312757982e-06, "epoch": 5.912863070539419, "percentage": 84.47, "elapsed_time": "0:55:34", "remaining_time": "0:10:13"}
+{"current_steps": 1430, "total_steps": 1687, "loss": 0.2352, "lr": 2.7838954023092845e-06, "epoch": 5.933609958506224, "percentage": 84.77, "elapsed_time": "0:55:45", "remaining_time": "0:10:01"}
+{"current_steps": 1435, "total_steps": 1687, "loss": 0.254, "lr": 2.679491924311226e-06, "epoch": 5.954356846473029, "percentage": 85.06, "elapsed_time": "0:55:55", "remaining_time": "0:09:49"}
+{"current_steps": 1440, "total_steps": 1687, "loss": 0.2627, "lr": 2.576943057875696e-06, "epoch": 5.975103734439834, "percentage": 85.36, "elapsed_time": "0:56:05", "remaining_time": "0:09:37"}
+{"current_steps": 1445, "total_steps": 1687, "loss": 0.2422, "lr": 2.4762597835300815e-06, "epoch": 5.995850622406639, "percentage": 85.66, "elapsed_time": "0:56:15", "remaining_time": "0:09:25"}
+{"current_steps": 1450, "total_steps": 1687, "loss": 0.2238, "lr": 2.377452882041551e-06, "epoch": 6.016597510373444, "percentage": 85.95, "elapsed_time": "0:56:24", "remaining_time": "0:09:13"}
+{"current_steps": 1455, "total_steps": 1687, "loss": 0.1914, "lr": 2.280532933262678e-06, "epoch": 6.037344398340249, "percentage": 86.25, "elapsed_time": "0:56:35", "remaining_time": "0:09:01"}
+{"current_steps": 1460, "total_steps": 1687, "loss": 0.2352, "lr": 2.1855103149985934e-06, "epoch": 6.058091286307054, "percentage": 86.54, "elapsed_time": "0:56:45", "remaining_time": "0:08:49"}
+{"current_steps": 1465, "total_steps": 1687, "loss": 0.2003, "lr": 2.0923952018957826e-06, "epoch": 6.078838174273859, "percentage": 86.84, "elapsed_time": "0:56:55", "remaining_time": "0:08:37"}
+{"current_steps": 1470, "total_steps": 1687, "loss": 0.185, "lr": 2.0011975643526106e-06, "epoch": 6.0995850622406635, "percentage": 87.14, "elapsed_time": "0:57:06", "remaining_time": "0:08:25"}
+{"current_steps": 1475, "total_steps": 1687, "loss": 0.1719, "lr": 1.9119271674517305e-06, "epoch": 6.1203319502074685, "percentage": 87.43, "elapsed_time": "0:57:15", "remaining_time": "0:08:13"}
+{"current_steps": 1480, "total_steps": 1687, "loss": 0.2254, "lr": 1.8245935699145035e-06, "epoch": 6.141078838174274, "percentage": 87.73, "elapsed_time": "0:57:25", "remaining_time": "0:08:01"}
+{"current_steps": 1485, "total_steps": 1687, "loss": 0.1786, "lr": 1.7392061230774371e-06, "epoch": 6.161825726141079, "percentage": 88.03, "elapsed_time": "0:57:35", "remaining_time": "0:07:50"}
+{"current_steps": 1490, "total_steps": 1687, "loss": 0.2062, "lr": 1.6557739698909436e-06, "epoch": 6.182572614107884, "percentage": 88.32, "elapsed_time": "0:57:45", "remaining_time": "0:07:38"}
+{"current_steps": 1495, "total_steps": 1687, "loss": 0.1752, "lr": 1.574306043940288e-06, "epoch": 6.203319502074689, "percentage": 88.62, "elapsed_time": "0:57:55", "remaining_time": "0:07:26"}
+{"current_steps": 1500, "total_steps": 1687, "loss": 0.2002, "lr": 1.4948110684890726e-06, "epoch": 6.224066390041494, "percentage": 88.92, "elapsed_time": "0:58:05", "remaining_time": "0:07:14"}
+{"current_steps": 1505, "total_steps": 1687, "loss": 0.2326, "lr": 1.4172975555451363e-06, "epoch": 6.244813278008299, "percentage": 89.21, "elapsed_time": "0:58:15", "remaining_time": "0:07:02"}
+{"current_steps": 1510, "total_steps": 1687, "loss": 0.2402, "lr": 1.3417738049491536e-06, "epoch": 6.265560165975104, "percentage": 89.51, "elapsed_time": "0:58:25", "remaining_time": "0:06:50"}
+{"current_steps": 1515, "total_steps": 1687, "loss": 0.198, "lr": 1.268247903485902e-06, "epoch": 6.286307053941909, "percentage": 89.8, "elapsed_time": "0:58:36", "remaining_time": "0:06:39"}
+{"current_steps": 1520, "total_steps": 1687, "loss": 0.21, "lr": 1.1967277240183716e-06, "epoch": 6.3070539419087135, "percentage": 90.1, "elapsed_time": "0:58:45", "remaining_time": "0:06:27"}
+{"current_steps": 1525, "total_steps": 1687, "loss": 0.2066, "lr": 1.1272209246447696e-06, "epoch": 6.327800829875518, "percentage": 90.4, "elapsed_time": "0:58:55", "remaining_time": "0:06:15"}
+{"current_steps": 1530, "total_steps": 1687, "loss": 0.199, "lr": 1.0597349478785123e-06, "epoch": 6.348547717842323, "percentage": 90.69, "elapsed_time": "0:59:05", "remaining_time": "0:06:03"}
+{"current_steps": 1535, "total_steps": 1687, "loss": 0.2284, "lr": 9.942770198513218e-07, "epoch": 6.369294605809129, "percentage": 90.99, "elapsed_time": "0:59:15", "remaining_time": "0:05:52"}
+{"current_steps": 1540, "total_steps": 1687, "loss": 0.2092, "lr": 9.308541495394751e-07, "epoch": 6.390041493775934, "percentage": 91.29, "elapsed_time": "0:59:25", "remaining_time": "0:05:40"}
+{"current_steps": 1545, "total_steps": 1687, "loss": 0.2104, "lr": 8.694731280133051e-07, "epoch": 6.410788381742739, "percentage": 91.58, "elapsed_time": "0:59:35", "remaining_time": "0:05:28"}
+{"current_steps": 1550, "total_steps": 1687, "loss": 0.2306, "lr": 8.101405277100549e-07, "epoch": 6.431535269709544, "percentage": 91.88, "elapsed_time": "0:59:44", "remaining_time": "0:05:16"}
+{"current_steps": 1555, "total_steps": 1687, "loss": 0.1801, "lr": 7.528627017301016e-07, "epoch": 6.452282157676349, "percentage": 92.18, "elapsed_time": "0:59:54", "remaining_time": "0:05:05"}
+{"current_steps": 1560, "total_steps": 1687, "loss": 0.19, "lr": 6.976457831567262e-07, "epoch": 6.473029045643154, "percentage": 92.47, "elapsed_time": "1:00:04", "remaining_time": "0:04:53"}
+{"current_steps": 1565, "total_steps": 1687, "loss": 0.2115, "lr": 6.444956843993754e-07, "epoch": 6.4937759336099585, "percentage": 92.77, "elapsed_time": "1:00:14", "remaining_time": "0:04:41"}
+{"current_steps": 1570, "total_steps": 1687, "loss": 0.2254, "lr": 5.934180965606007e-07, "epoch": 6.514522821576763, "percentage": 93.06, "elapsed_time": "1:00:24", "remaining_time": "0:04:30"}
+{"current_steps": 1575, "total_steps": 1687, "loss": 0.2009, "lr": 5.444184888266768e-07, "epoch": 6.535269709543568, "percentage": 93.36, "elapsed_time": "1:00:34", "remaining_time": "0:04:18"}
+{"current_steps": 1580, "total_steps": 1687, "loss": 0.1839, "lr": 4.975021078819731e-07, "epoch": 6.556016597510373, "percentage": 93.66, "elapsed_time": "1:00:44", "remaining_time": "0:04:06"}
+{"current_steps": 1585, "total_steps": 1687, "loss": 0.2637, "lr": 4.5267397734717113e-07, "epoch": 6.576763485477178, "percentage": 93.95, "elapsed_time": "1:00:53", "remaining_time": "0:03:55"}
+{"current_steps": 1590, "total_steps": 1687, "loss": 0.2036, "lr": 4.0993889724135314e-07, "epoch": 6.597510373443983, "percentage": 94.25, "elapsed_time": "1:01:03", "remaining_time": "0:03:43"}
+{"current_steps": 1595, "total_steps": 1687, "loss": 0.2089, "lr": 3.693014434680242e-07, "epoch": 6.618257261410788, "percentage": 94.55, "elapsed_time": "1:01:14", "remaining_time": "0:03:31"}
+{"current_steps": 1600, "total_steps": 1687, "loss": 0.2244, "lr": 3.307659673251595e-07, "epoch": 6.639004149377593, "percentage": 94.84, "elapsed_time": "1:01:23", "remaining_time": "0:03:20"}
+{"current_steps": 1605, "total_steps": 1687, "loss": 0.2327, "lr": 2.9433659503926623e-07, "epoch": 6.659751037344399, "percentage": 95.14, "elapsed_time": "1:02:29", "remaining_time": "0:03:11"}
+{"current_steps": 1610, "total_steps": 1687, "loss": 0.2035, "lr": 2.6001722732358127e-07, "epoch": 6.680497925311204, "percentage": 95.44, "elapsed_time": "1:02:38", "remaining_time": "0:02:59"}
+{"current_steps": 1615, "total_steps": 1687, "loss": 0.1913, "lr": 2.27811538960383e-07, "epoch": 6.7012448132780085, "percentage": 95.73, "elapsed_time": "1:02:48", "remaining_time": "0:02:48"}
+{"current_steps": 1620, "total_steps": 1687, "loss": 0.1967, "lr": 1.9772297840752407e-07, "epoch": 6.721991701244813, "percentage": 96.03, "elapsed_time": "1:02:58", "remaining_time": "0:02:36"}
+{"current_steps": 1625, "total_steps": 1687, "loss": 0.2021, "lr": 1.6975476742916886e-07, "epoch": 6.742738589211618, "percentage": 96.32, "elapsed_time": "1:03:08", "remaining_time": "0:02:24"}
+{"current_steps": 1630, "total_steps": 1687, "loss": 0.2313, "lr": 1.43909900750836e-07, "epoch": 6.763485477178423, "percentage": 96.62, "elapsed_time": "1:03:18", "remaining_time": "0:02:12"}
+{"current_steps": 1635, "total_steps": 1687, "loss": 0.1937, "lr": 1.2019114573871947e-07, "epoch": 6.784232365145228, "percentage": 96.92, "elapsed_time": "1:03:28", "remaining_time": "0:02:01"}
+{"current_steps": 1640, "total_steps": 1687, "loss": 0.1573, "lr": 9.860104210338562e-08, "epoch": 6.804979253112033, "percentage": 97.21, "elapsed_time": "1:03:38", "remaining_time": "0:01:49"}
+{"current_steps": 1645, "total_steps": 1687, "loss": 0.1822, "lr": 7.914190162781277e-08, "epoch": 6.825726141078838, "percentage": 97.51, "elapsed_time": "1:03:48", "remaining_time": "0:01:37"}
+{"current_steps": 1650, "total_steps": 1687, "loss": 0.2129, "lr": 6.181580791987385e-08, "epoch": 6.846473029045643, "percentage": 97.81, "elapsed_time": "1:03:58", "remaining_time": "0:01:26"}
+{"current_steps": 1655, "total_steps": 1687, "loss": 0.1678, "lr": 4.6624616189214765e-08, "epoch": 6.867219917012449, "percentage": 98.1, "elapsed_time": "1:04:08", "remaining_time": "0:01:14"}
+{"current_steps": 1660, "total_steps": 1687, "loss": 0.1979, "lr": 3.3569953048624426e-08, "epoch": 6.8879668049792535, "percentage": 98.4, "elapsed_time": "1:04:18", "remaining_time": "0:01:02"}
+{"current_steps": 1665, "total_steps": 1687, "loss": 0.2183, "lr": 2.2653216339840746e-08, "epoch": 6.908713692946058, "percentage": 98.7, "elapsed_time": "1:04:28", "remaining_time": "0:00:51"}
+{"current_steps": 1670, "total_steps": 1687, "loss": 0.1777, "lr": 1.3875574983894802e-08, "epoch": 6.929460580912863, "percentage": 98.99, "elapsed_time": "1:04:37", "remaining_time": "0:00:39"}
+{"current_steps": 1675, "total_steps": 1687, "loss": 0.1835, "lr": 7.237968855937638e-09, "epoch": 6.950207468879668, "percentage": 99.29, "elapsed_time": "1:04:47", "remaining_time": "0:00:27"}
+{"current_steps": 1680, "total_steps": 1687, "loss": 0.2133, "lr": 2.7411086846051984e-09, "epoch": 6.970954356846473, "percentage": 99.59, "elapsed_time": "1:04:57", "remaining_time": "0:00:16"}
+{"current_steps": 1685, "total_steps": 1687, "loss": 0.2164, "lr": 3.8547597591254147e-10, "epoch": 6.991701244813278, "percentage": 99.88, "elapsed_time": "1:05:07", "remaining_time": "0:00:04"}
+{"current_steps": 1687, "total_steps": 1687, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:06:05", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0170b9f48358835966e9d5b36e1ca171de58de86a537ecba59350cd4ad78c1d5
+size 8721