初始化项目，由ModelHub XC社区提供模型

Model: laion/nemotron-terminal-debugging__Qwen3-8B
Source: Original Platform

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: nemotron-debugging__Qwen3-8B
+  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. -->
+
+# nemotron-debugging__Qwen3-8B
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/data1/datasets/playground/ot/hf_hub/datasets--laion--nemotron-terminal-debugging/snapshots/fa40710cd019cebe2c95d8f7e3bb09511ca40b30_thinking_preprocessed 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: 32
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 96
+- total_eval_batch_size: 256
+- 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 4.57.6
+- Pytorch 2.9.1+cu130
+- Datasets 4.7.0
+- Tokenizers 0.22.2

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 134266.39948678762,
+    "achieved_tflops_per_gpu_theoretical": 3485791.289356818,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.4433520436286926,
+    "mfu_percent": 9488.791483165203,
+    "mfu_percent_theoretical": 246345.67415949245,
+    "total_flos": 5.319956987025293e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.2382,
+    "train_samples_per_second": 98264.932,
+    "train_steps_per_second": 1028.893,
+    "valid_targets_mean": 9841.1,
+    "valid_targets_min": 3598
+}

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": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1529b412aad486ce92f881f923daf40f2ab578f3274514c2c629505dd6803f
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815349440f4a28b80d3a50cdf623e4dc38c27448625d1adac55fefd08f9ff9fd
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57d9233cd05ecb0e4b45027db84cd0566d706969b649328553e58ecca2b7f56
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70dd8b52775568243bc7f06990ac1733e6b8d179c485fa92cd2ec5c10dd105ed
+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": "fa40710cd019cebe2c95d8f7e3bb09511ca40b30_thinking_preprocessed",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "/e/data1/datasets/playground/ot/hf_hub/datasets--laion--nemotron-terminal-debugging/snapshots/fa40710cd019cebe2c95d8f7e3bb09511ca40b30_thinking_preprocessed",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/nemotron-terminal-debugging__Qwen3-8B/blob/main/config.json",
+  "wandb_link": null,
+  "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.json

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

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 +1,12 @@
+{
+    "achieved_tflops_per_gpu": 134266.39948678762,
+    "achieved_tflops_per_gpu_theoretical": 3485791.289356818,
+    "epoch": 7.0,
+    "mfu_percent": 9488.791483165203,
+    "mfu_percent_theoretical": 246345.67415949245,
+    "total_flos": 5.319956987025293e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.2382,
+    "train_samples_per_second": 98264.932,
+    "train_steps_per_second": 1028.893
+}

trainer_log.jsonl

@@ -0,0 +1,260 @@
+{"current_steps": 5, "total_steps": 1274, "loss": 1.0219, "lr": 1.25e-06, "epoch": 0.027573529411764705, "percentage": 0.39, "elapsed_time": "0:02:27", "remaining_time": "10:24:24"}
+{"current_steps": 10, "total_steps": 1274, "loss": 1.0055, "lr": 2.8125e-06, "epoch": 0.05514705882352941, "percentage": 0.78, "elapsed_time": "0:04:47", "remaining_time": "10:04:37"}
+{"current_steps": 15, "total_steps": 1274, "loss": 0.9532, "lr": 4.3750000000000005e-06, "epoch": 0.08272058823529412, "percentage": 1.18, "elapsed_time": "0:07:01", "remaining_time": "9:49:26"}
+{"current_steps": 20, "total_steps": 1274, "loss": 0.8851, "lr": 5.9375e-06, "epoch": 0.11029411764705882, "percentage": 1.57, "elapsed_time": "0:09:20", "remaining_time": "9:45:40"}
+{"current_steps": 25, "total_steps": 1274, "loss": 0.8505, "lr": 7.500000000000001e-06, "epoch": 0.13786764705882354, "percentage": 1.96, "elapsed_time": "0:11:34", "remaining_time": "9:37:53"}
+{"current_steps": 30, "total_steps": 1274, "loss": 0.8194, "lr": 9.0625e-06, "epoch": 0.16544117647058823, "percentage": 2.35, "elapsed_time": "0:13:55", "remaining_time": "9:37:36"}
+{"current_steps": 35, "total_steps": 1274, "loss": 0.79, "lr": 1.0625e-05, "epoch": 0.19301470588235295, "percentage": 2.75, "elapsed_time": "0:16:16", "remaining_time": "9:36:09"}
+{"current_steps": 40, "total_steps": 1274, "loss": 0.7763, "lr": 1.2187500000000001e-05, "epoch": 0.22058823529411764, "percentage": 3.14, "elapsed_time": "0:18:32", "remaining_time": "9:31:51"}
+{"current_steps": 45, "total_steps": 1274, "loss": 0.7367, "lr": 1.375e-05, "epoch": 0.24816176470588236, "percentage": 3.53, "elapsed_time": "0:20:51", "remaining_time": "9:29:46"}
+{"current_steps": 50, "total_steps": 1274, "loss": 0.7257, "lr": 1.5312500000000003e-05, "epoch": 0.2757352941176471, "percentage": 3.92, "elapsed_time": "0:23:10", "remaining_time": "9:27:29"}
+{"current_steps": 55, "total_steps": 1274, "loss": 0.7035, "lr": 1.6875e-05, "epoch": 0.30330882352941174, "percentage": 4.32, "elapsed_time": "0:25:32", "remaining_time": "9:26:03"}
+{"current_steps": 60, "total_steps": 1274, "loss": 0.6873, "lr": 1.84375e-05, "epoch": 0.33088235294117646, "percentage": 4.71, "elapsed_time": "0:27:50", "remaining_time": "9:23:17"}
+{"current_steps": 65, "total_steps": 1274, "loss": 0.6644, "lr": 2e-05, "epoch": 0.3584558823529412, "percentage": 5.1, "elapsed_time": "0:30:09", "remaining_time": "9:21:05"}
+{"current_steps": 70, "total_steps": 1274, "loss": 0.6489, "lr": 2.1562500000000002e-05, "epoch": 0.3860294117647059, "percentage": 5.49, "elapsed_time": "0:32:33", "remaining_time": "9:19:58"}
+{"current_steps": 75, "total_steps": 1274, "loss": 0.6346, "lr": 2.3125000000000003e-05, "epoch": 0.41360294117647056, "percentage": 5.89, "elapsed_time": "0:34:57", "remaining_time": "9:18:52"}
+{"current_steps": 80, "total_steps": 1274, "loss": 0.6256, "lr": 2.46875e-05, "epoch": 0.4411764705882353, "percentage": 6.28, "elapsed_time": "0:37:13", "remaining_time": "9:15:32"}
+{"current_steps": 85, "total_steps": 1274, "loss": 0.612, "lr": 2.625e-05, "epoch": 0.46875, "percentage": 6.67, "elapsed_time": "0:39:34", "remaining_time": "9:13:28"}
+{"current_steps": 90, "total_steps": 1274, "loss": 0.607, "lr": 2.7812500000000002e-05, "epoch": 0.4963235294117647, "percentage": 7.06, "elapsed_time": "0:41:53", "remaining_time": "9:11:08"}
+{"current_steps": 95, "total_steps": 1274, "loss": 0.5981, "lr": 2.9375000000000003e-05, "epoch": 0.5238970588235294, "percentage": 7.46, "elapsed_time": "0:44:07", "remaining_time": "9:07:31"}
+{"current_steps": 100, "total_steps": 1274, "loss": 0.5915, "lr": 3.09375e-05, "epoch": 0.5514705882352942, "percentage": 7.85, "elapsed_time": "0:46:29", "remaining_time": "9:05:44"}
+{"current_steps": 105, "total_steps": 1274, "loss": 0.5845, "lr": 3.2500000000000004e-05, "epoch": 0.5790441176470589, "percentage": 8.24, "elapsed_time": "0:48:48", "remaining_time": "9:03:28"}
+{"current_steps": 110, "total_steps": 1274, "loss": 0.5806, "lr": 3.40625e-05, "epoch": 0.6066176470588235, "percentage": 8.63, "elapsed_time": "0:51:07", "remaining_time": "9:00:57"}
+{"current_steps": 115, "total_steps": 1274, "loss": 0.5777, "lr": 3.5625000000000005e-05, "epoch": 0.6341911764705882, "percentage": 9.03, "elapsed_time": "0:58:11", "remaining_time": "9:46:28"}
+{"current_steps": 120, "total_steps": 1274, "loss": 0.5672, "lr": 3.71875e-05, "epoch": 0.6617647058823529, "percentage": 9.42, "elapsed_time": "1:00:31", "remaining_time": "9:42:07"}
+{"current_steps": 125, "total_steps": 1274, "loss": 0.5646, "lr": 3.875e-05, "epoch": 0.6893382352941176, "percentage": 9.81, "elapsed_time": "1:02:46", "remaining_time": "9:37:00"}
+{"current_steps": 130, "total_steps": 1274, "loss": 0.5644, "lr": 3.999992484978314e-05, "epoch": 0.7169117647058824, "percentage": 10.2, "elapsed_time": "1:05:11", "remaining_time": "9:33:37"}
+{"current_steps": 135, "total_steps": 1274, "loss": 0.557, "lr": 3.999729465149199e-05, "epoch": 0.7444852941176471, "percentage": 10.6, "elapsed_time": "1:07:31", "remaining_time": "9:29:40"}
+{"current_steps": 140, "total_steps": 1274, "loss": 0.5497, "lr": 3.9990907507094396e-05, "epoch": 0.7720588235294118, "percentage": 10.99, "elapsed_time": "1:09:48", "remaining_time": "9:25:25"}
+{"current_steps": 145, "total_steps": 1274, "loss": 0.5564, "lr": 3.9980764616560544e-05, "epoch": 0.7996323529411765, "percentage": 11.38, "elapsed_time": "1:12:06", "remaining_time": "9:21:30"}
+{"current_steps": 150, "total_steps": 1274, "loss": 0.5555, "lr": 3.9966867885462854e-05, "epoch": 0.8272058823529411, "percentage": 11.77, "elapsed_time": "1:14:26", "remaining_time": "9:17:52"}
+{"current_steps": 155, "total_steps": 1274, "loss": 0.5461, "lr": 3.994921992461797e-05, "epoch": 0.8547794117647058, "percentage": 12.17, "elapsed_time": "1:16:46", "remaining_time": "9:14:14"}
+{"current_steps": 160, "total_steps": 1274, "loss": 0.5485, "lr": 3.992782404959627e-05, "epoch": 0.8823529411764706, "percentage": 12.56, "elapsed_time": "1:19:05", "remaining_time": "9:10:43"}
+{"current_steps": 165, "total_steps": 1274, "loss": 0.5476, "lr": 3.9902684280098965e-05, "epoch": 0.9099264705882353, "percentage": 12.95, "elapsed_time": "1:21:25", "remaining_time": "9:07:13"}
+{"current_steps": 170, "total_steps": 1274, "loss": 0.5392, "lr": 3.987380533920287e-05, "epoch": 0.9375, "percentage": 13.34, "elapsed_time": "1:23:46", "remaining_time": "9:04:01"}
+{"current_steps": 175, "total_steps": 1274, "loss": 0.5474, "lr": 3.984119265247314e-05, "epoch": 0.9650735294117647, "percentage": 13.74, "elapsed_time": "1:26:06", "remaining_time": "9:00:46"}
+{"current_steps": 180, "total_steps": 1274, "loss": 0.5426, "lr": 3.9804852346943866e-05, "epoch": 0.9926470588235294, "percentage": 14.13, "elapsed_time": "1:28:25", "remaining_time": "8:57:27"}
+{"current_steps": 185, "total_steps": 1274, "loss": 0.5428, "lr": 3.9764791249967044e-05, "epoch": 1.0165441176470589, "percentage": 14.52, "elapsed_time": "1:30:26", "remaining_time": "8:52:21"}
+{"current_steps": 190, "total_steps": 1274, "loss": 0.5312, "lr": 3.972101688792986e-05, "epoch": 1.0441176470588236, "percentage": 14.91, "elapsed_time": "1:32:46", "remaining_time": "8:49:15"}
+{"current_steps": 195, "total_steps": 1274, "loss": 0.5344, "lr": 3.967353748484071e-05, "epoch": 1.0716911764705883, "percentage": 15.31, "elapsed_time": "1:35:01", "remaining_time": "8:45:50"}
+{"current_steps": 200, "total_steps": 1274, "loss": 0.5225, "lr": 3.962236196078411e-05, "epoch": 1.099264705882353, "percentage": 15.7, "elapsed_time": "1:37:17", "remaining_time": "8:42:25"}
+{"current_steps": 205, "total_steps": 1274, "loss": 0.5257, "lr": 3.956749993024489e-05, "epoch": 1.1268382352941178, "percentage": 16.09, "elapsed_time": "1:39:39", "remaining_time": "8:39:38"}
+{"current_steps": 210, "total_steps": 1274, "loss": 0.5259, "lr": 3.950896170030186e-05, "epoch": 1.1544117647058822, "percentage": 16.48, "elapsed_time": "1:41:54", "remaining_time": "8:36:22"}
+{"current_steps": 215, "total_steps": 1274, "loss": 0.5268, "lr": 3.9446758268691395e-05, "epoch": 1.181985294117647, "percentage": 16.88, "elapsed_time": "1:44:11", "remaining_time": "8:33:10"}
+{"current_steps": 220, "total_steps": 1274, "loss": 0.5185, "lr": 3.9380901321741315e-05, "epoch": 1.2095588235294117, "percentage": 17.27, "elapsed_time": "1:46:32", "remaining_time": "8:30:26"}
+{"current_steps": 225, "total_steps": 1274, "loss": 0.526, "lr": 3.931140323217524e-05, "epoch": 1.2371323529411764, "percentage": 17.66, "elapsed_time": "1:48:47", "remaining_time": "8:27:11"}
+{"current_steps": 230, "total_steps": 1274, "loss": 0.5219, "lr": 3.923827705678818e-05, "epoch": 1.2647058823529411, "percentage": 18.05, "elapsed_time": "1:51:03", "remaining_time": "8:24:06"}
+{"current_steps": 235, "total_steps": 1274, "loss": 0.5215, "lr": 3.916153653399352e-05, "epoch": 1.2922794117647058, "percentage": 18.45, "elapsed_time": "1:53:22", "remaining_time": "8:21:15"}
+{"current_steps": 240, "total_steps": 1274, "loss": 0.522, "lr": 3.908119608124184e-05, "epoch": 1.3198529411764706, "percentage": 18.84, "elapsed_time": "1:55:38", "remaining_time": "8:18:11"}
+{"current_steps": 245, "total_steps": 1274, "loss": 0.5139, "lr": 3.8997270792312435e-05, "epoch": 1.3474264705882353, "percentage": 19.23, "elapsed_time": "1:58:01", "remaining_time": "8:15:42"}
+{"current_steps": 250, "total_steps": 1274, "loss": 0.5224, "lr": 3.890977643447746e-05, "epoch": 1.375, "percentage": 19.62, "elapsed_time": "2:00:18", "remaining_time": "8:12:48"}
+{"current_steps": 255, "total_steps": 1274, "loss": 0.5096, "lr": 3.8818729445539765e-05, "epoch": 1.4025735294117647, "percentage": 20.02, "elapsed_time": "2:02:38", "remaining_time": "8:10:03"}
+{"current_steps": 260, "total_steps": 1274, "loss": 0.5148, "lr": 3.872414693074466e-05, "epoch": 1.4301470588235294, "percentage": 20.41, "elapsed_time": "2:05:00", "remaining_time": "8:07:30"}
+{"current_steps": 265, "total_steps": 1274, "loss": 0.5115, "lr": 3.862604665956632e-05, "epoch": 1.4577205882352942, "percentage": 20.8, "elapsed_time": "2:07:18", "remaining_time": "8:04:43"}
+{"current_steps": 270, "total_steps": 1274, "loss": 0.5134, "lr": 3.8524447062369355e-05, "epoch": 1.4852941176470589, "percentage": 21.19, "elapsed_time": "2:09:37", "remaining_time": "8:02:01"}
+{"current_steps": 275, "total_steps": 1274, "loss": 0.5167, "lr": 3.8419367226946286e-05, "epoch": 1.5128676470588234, "percentage": 21.59, "elapsed_time": "2:11:57", "remaining_time": "7:59:22"}
+{"current_steps": 280, "total_steps": 1274, "loss": 0.5176, "lr": 3.831082689493143e-05, "epoch": 1.5404411764705883, "percentage": 21.98, "elapsed_time": "2:14:15", "remaining_time": "7:56:37"}
+{"current_steps": 285, "total_steps": 1274, "loss": 0.5147, "lr": 3.819884645809203e-05, "epoch": 1.5680147058823528, "percentage": 22.37, "elapsed_time": "2:16:35", "remaining_time": "7:53:58"}
+{"current_steps": 290, "total_steps": 1274, "loss": 0.5088, "lr": 3.808344695449715e-05, "epoch": 1.5955882352941178, "percentage": 22.76, "elapsed_time": "2:18:53", "remaining_time": "7:51:16"}
+{"current_steps": 295, "total_steps": 1274, "loss": 0.5065, "lr": 3.796465006456523e-05, "epoch": 1.6231617647058822, "percentage": 23.16, "elapsed_time": "2:21:13", "remaining_time": "7:48:40"}
+{"current_steps": 300, "total_steps": 1274, "loss": 0.5101, "lr": 3.784247810699093e-05, "epoch": 1.6507352941176472, "percentage": 23.55, "elapsed_time": "2:23:26", "remaining_time": "7:45:42"}
+{"current_steps": 305, "total_steps": 1274, "loss": 0.5113, "lr": 3.7716954034552004e-05, "epoch": 1.6783088235294117, "percentage": 23.94, "elapsed_time": "2:25:56", "remaining_time": "7:43:40"}
+{"current_steps": 310, "total_steps": 1274, "loss": 0.5087, "lr": 3.758810142979719e-05, "epoch": 1.7058823529411766, "percentage": 24.33, "elapsed_time": "2:28:14", "remaining_time": "7:41:00"}
+{"current_steps": 315, "total_steps": 1274, "loss": 0.5157, "lr": 3.74559445006156e-05, "epoch": 1.7334558823529411, "percentage": 24.73, "elapsed_time": "2:30:32", "remaining_time": "7:38:17"}
+{"current_steps": 320, "total_steps": 1274, "loss": 0.5066, "lr": 3.732050807568878e-05, "epoch": 1.7610294117647058, "percentage": 25.12, "elapsed_time": "2:32:45", "remaining_time": "7:35:24"}
+{"current_steps": 325, "total_steps": 1274, "loss": 0.5073, "lr": 3.718181759982604e-05, "epoch": 1.7886029411764706, "percentage": 25.51, "elapsed_time": "2:35:07", "remaining_time": "7:32:58"}
+{"current_steps": 330, "total_steps": 1274, "loss": 0.5054, "lr": 3.703989912918409e-05, "epoch": 1.8161764705882353, "percentage": 25.9, "elapsed_time": "2:37:24", "remaining_time": "7:30:17"}
+{"current_steps": 335, "total_steps": 1274, "loss": 0.5034, "lr": 3.689477932637181e-05, "epoch": 1.84375, "percentage": 26.3, "elapsed_time": "2:39:41", "remaining_time": "7:27:36"}
+{"current_steps": 340, "total_steps": 1274, "loss": 0.5077, "lr": 3.674648545544104e-05, "epoch": 1.8713235294117647, "percentage": 26.69, "elapsed_time": "2:41:55", "remaining_time": "7:24:50"}
+{"current_steps": 345, "total_steps": 1274, "loss": 0.4975, "lr": 3.659504537676444e-05, "epoch": 1.8988970588235294, "percentage": 27.08, "elapsed_time": "2:44:11", "remaining_time": "7:22:06"}
+{"current_steps": 350, "total_steps": 1274, "loss": 0.4995, "lr": 3.6440487541801246e-05, "epoch": 1.9264705882352942, "percentage": 27.47, "elapsed_time": "2:46:28", "remaining_time": "7:19:28"}
+{"current_steps": 355, "total_steps": 1274, "loss": 0.5038, "lr": 3.628284098775207e-05, "epoch": 1.9540441176470589, "percentage": 27.86, "elapsed_time": "2:48:49", "remaining_time": "7:17:01"}
+{"current_steps": 360, "total_steps": 1274, "loss": 0.5071, "lr": 3.612213533210356e-05, "epoch": 1.9816176470588234, "percentage": 28.26, "elapsed_time": "2:51:05", "remaining_time": "7:14:22"}
+{"current_steps": 365, "total_steps": 1274, "loss": 0.5046, "lr": 3.595840076706411e-05, "epoch": 2.005514705882353, "percentage": 28.65, "elapsed_time": "2:53:03", "remaining_time": "7:10:58"}
+{"current_steps": 370, "total_steps": 1274, "loss": 0.4962, "lr": 3.579166805389154e-05, "epoch": 2.0330882352941178, "percentage": 29.04, "elapsed_time": "2:55:18", "remaining_time": "7:08:19"}
+{"current_steps": 375, "total_steps": 1274, "loss": 0.4878, "lr": 3.562196851711391e-05, "epoch": 2.0606617647058822, "percentage": 29.43, "elapsed_time": "2:57:33", "remaining_time": "7:05:39"}
+{"current_steps": 380, "total_steps": 1274, "loss": 0.5018, "lr": 3.5449334038644515e-05, "epoch": 2.088235294117647, "percentage": 29.83, "elapsed_time": "2:59:47", "remaining_time": "7:02:59"}
+{"current_steps": 385, "total_steps": 1274, "loss": 0.4948, "lr": 3.5273797051792114e-05, "epoch": 2.1158088235294117, "percentage": 30.22, "elapsed_time": "3:02:01", "remaining_time": "7:00:18"}
+{"current_steps": 390, "total_steps": 1274, "loss": 0.4966, "lr": 3.509539053516759e-05, "epoch": 2.1433823529411766, "percentage": 30.61, "elapsed_time": "3:04:17", "remaining_time": "6:57:44"}
+{"current_steps": 395, "total_steps": 1274, "loss": 0.4982, "lr": 3.49141480064882e-05, "epoch": 2.170955882352941, "percentage": 31.0, "elapsed_time": "3:06:33", "remaining_time": "6:55:09"}
+{"current_steps": 400, "total_steps": 1274, "loss": 0.4882, "lr": 3.47301035162805e-05, "epoch": 2.198529411764706, "percentage": 31.4, "elapsed_time": "3:08:52", "remaining_time": "6:52:41"}
+{"current_steps": 405, "total_steps": 1274, "loss": 0.4965, "lr": 3.454329164148317e-05, "epoch": 2.2261029411764706, "percentage": 31.79, "elapsed_time": "3:11:05", "remaining_time": "6:50:01"}
+{"current_steps": 410, "total_steps": 1274, "loss": 0.4873, "lr": 3.435374747895095e-05, "epoch": 2.2536764705882355, "percentage": 32.18, "elapsed_time": "3:13:22", "remaining_time": "6:47:30"}
+{"current_steps": 415, "total_steps": 1274, "loss": 0.4956, "lr": 3.4161506638860903e-05, "epoch": 2.28125, "percentage": 32.57, "elapsed_time": "3:15:36", "remaining_time": "6:44:54"}
+{"current_steps": 420, "total_steps": 1274, "loss": 0.4878, "lr": 3.396660523802225e-05, "epoch": 2.3088235294117645, "percentage": 32.97, "elapsed_time": "3:17:53", "remaining_time": "6:42:23"}
+{"current_steps": 425, "total_steps": 1274, "loss": 0.4898, "lr": 3.376907989309097e-05, "epoch": 2.3363970588235294, "percentage": 33.36, "elapsed_time": "3:20:11", "remaining_time": "6:39:53"}
+{"current_steps": 430, "total_steps": 1274, "loss": 0.4911, "lr": 3.3568967713690574e-05, "epoch": 2.363970588235294, "percentage": 33.75, "elapsed_time": "3:22:23", "remaining_time": "6:37:14"}
+{"current_steps": 435, "total_steps": 1274, "loss": 0.4835, "lr": 3.3366306295440195e-05, "epoch": 2.391544117647059, "percentage": 34.14, "elapsed_time": "3:24:34", "remaining_time": "6:34:34"}
+{"current_steps": 440, "total_steps": 1274, "loss": 0.4973, "lr": 3.316113371289137e-05, "epoch": 2.4191176470588234, "percentage": 34.54, "elapsed_time": "3:26:52", "remaining_time": "6:32:07"}
+{"current_steps": 445, "total_steps": 1274, "loss": 0.4926, "lr": 3.295348851237494e-05, "epoch": 2.4466911764705883, "percentage": 34.93, "elapsed_time": "3:29:05", "remaining_time": "6:29:32"}
+{"current_steps": 450, "total_steps": 1274, "loss": 0.495, "lr": 3.2743409704759175e-05, "epoch": 2.474264705882353, "percentage": 35.32, "elapsed_time": "3:31:16", "remaining_time": "6:26:52"}
+{"current_steps": 455, "total_steps": 1274, "loss": 0.488, "lr": 3.253093675812073e-05, "epoch": 2.5018382352941178, "percentage": 35.71, "elapsed_time": "3:33:33", "remaining_time": "6:24:23"}
+{"current_steps": 460, "total_steps": 1274, "loss": 0.4885, "lr": 3.231610959032968e-05, "epoch": 2.5294117647058822, "percentage": 36.11, "elapsed_time": "3:35:49", "remaining_time": "6:21:54"}
+{"current_steps": 465, "total_steps": 1274, "loss": 0.4868, "lr": 3.2098968561550024e-05, "epoch": 2.556985294117647, "percentage": 36.5, "elapsed_time": "3:38:01", "remaining_time": "6:19:19"}
+{"current_steps": 470, "total_steps": 1274, "loss": 0.4875, "lr": 3.18795544666571e-05, "epoch": 2.5845588235294117, "percentage": 36.89, "elapsed_time": "3:40:17", "remaining_time": "6:16:50"}
+{"current_steps": 475, "total_steps": 1274, "loss": 0.489, "lr": 3.1657908527573376e-05, "epoch": 2.6121323529411766, "percentage": 37.28, "elapsed_time": "3:42:35", "remaining_time": "6:14:24"}
+{"current_steps": 480, "total_steps": 1274, "loss": 0.4835, "lr": 3.143407238552394e-05, "epoch": 2.639705882352941, "percentage": 37.68, "elapsed_time": "3:44:51", "remaining_time": "6:11:57"}
+{"current_steps": 485, "total_steps": 1274, "loss": 0.4882, "lr": 3.1208088093213276e-05, "epoch": 2.6672794117647056, "percentage": 38.07, "elapsed_time": "3:47:12", "remaining_time": "6:09:36"}
+{"current_steps": 490, "total_steps": 1274, "loss": 0.4825, "lr": 3.097999810692468e-05, "epoch": 2.6948529411764706, "percentage": 38.46, "elapsed_time": "3:49:31", "remaining_time": "6:07:14"}
+{"current_steps": 495, "total_steps": 1274, "loss": 0.492, "lr": 3.074984527854392e-05, "epoch": 2.7224264705882355, "percentage": 38.85, "elapsed_time": "3:51:47", "remaining_time": "6:04:46"}
+{"current_steps": 500, "total_steps": 1274, "loss": 0.4858, "lr": 3.0517672847508517e-05, "epoch": 2.75, "percentage": 39.25, "elapsed_time": "3:54:07", "remaining_time": "6:02:25"}
+{"current_steps": 505, "total_steps": 1274, "loss": 0.4909, "lr": 3.0283524432684214e-05, "epoch": 2.7775735294117645, "percentage": 39.64, "elapsed_time": "3:56:19", "remaining_time": "5:59:52"}
+{"current_steps": 510, "total_steps": 1274, "loss": 0.4781, "lr": 3.0047444024170197e-05, "epoch": 2.8051470588235294, "percentage": 40.03, "elapsed_time": "3:58:31", "remaining_time": "5:57:19"}
+{"current_steps": 515, "total_steps": 1274, "loss": 0.4862, "lr": 2.9809475975034586e-05, "epoch": 2.8327205882352944, "percentage": 40.42, "elapsed_time": "4:00:52", "remaining_time": "5:54:59"}
+{"current_steps": 520, "total_steps": 1274, "loss": 0.4807, "lr": 2.9569664992981648e-05, "epoch": 2.860294117647059, "percentage": 40.82, "elapsed_time": "4:03:13", "remaining_time": "5:52:41"}
+{"current_steps": 525, "total_steps": 1274, "loss": 0.4843, "lr": 2.932805613195249e-05, "epoch": 2.8878676470588234, "percentage": 41.21, "elapsed_time": "4:05:28", "remaining_time": "5:50:12"}
+{"current_steps": 530, "total_steps": 1274, "loss": 0.4824, "lr": 2.9084694783660615e-05, "epoch": 2.9154411764705883, "percentage": 41.6, "elapsed_time": "4:07:43", "remaining_time": "5:47:44"}
+{"current_steps": 535, "total_steps": 1274, "loss": 0.486, "lr": 2.8839626669064073e-05, "epoch": 2.943014705882353, "percentage": 41.99, "elapsed_time": "4:10:00", "remaining_time": "5:45:20"}
+{"current_steps": 540, "total_steps": 1274, "loss": 0.4887, "lr": 2.8592897829775732e-05, "epoch": 2.9705882352941178, "percentage": 42.39, "elapsed_time": "4:12:20", "remaining_time": "5:43:00"}
+{"current_steps": 545, "total_steps": 1274, "loss": 0.486, "lr": 2.8344554619413355e-05, "epoch": 2.9981617647058822, "percentage": 42.78, "elapsed_time": "4:14:39", "remaining_time": "5:40:38"}
+{"current_steps": 550, "total_steps": 1274, "loss": 0.4762, "lr": 2.8094643694890947e-05, "epoch": 3.0220588235294117, "percentage": 43.17, "elapsed_time": "4:16:36", "remaining_time": "5:37:47"}
+{"current_steps": 555, "total_steps": 1274, "loss": 0.4829, "lr": 2.784321200765326e-05, "epoch": 3.0496323529411766, "percentage": 43.56, "elapsed_time": "4:18:48", "remaining_time": "5:35:17"}
+{"current_steps": 560, "total_steps": 1274, "loss": 0.4862, "lr": 2.7590306794854853e-05, "epoch": 3.077205882352941, "percentage": 43.96, "elapsed_time": "4:20:59", "remaining_time": "5:32:45"}
+{"current_steps": 565, "total_steps": 1274, "loss": 0.4809, "lr": 2.7335975570485552e-05, "epoch": 3.104779411764706, "percentage": 44.35, "elapsed_time": "4:23:11", "remaining_time": "5:30:16"}
+{"current_steps": 570, "total_steps": 1274, "loss": 0.4784, "lr": 2.7080266116443855e-05, "epoch": 3.1323529411764706, "percentage": 44.74, "elapsed_time": "4:25:25", "remaining_time": "5:27:49"}
+{"current_steps": 575, "total_steps": 1274, "loss": 0.4783, "lr": 2.6823226473559992e-05, "epoch": 3.1599264705882355, "percentage": 45.13, "elapsed_time": "4:27:35", "remaining_time": "5:25:18"}
+{"current_steps": 580, "total_steps": 1274, "loss": 0.4725, "lr": 2.656490493257042e-05, "epoch": 3.1875, "percentage": 45.53, "elapsed_time": "4:29:50", "remaining_time": "5:22:53"}
+{"current_steps": 585, "total_steps": 1274, "loss": 0.478, "lr": 2.6305350025045257e-05, "epoch": 3.2150735294117645, "percentage": 45.92, "elapsed_time": "4:32:07", "remaining_time": "5:20:29"}
+{"current_steps": 590, "total_steps": 1274, "loss": 0.4767, "lr": 2.604461051427054e-05, "epoch": 3.2426470588235294, "percentage": 46.31, "elapsed_time": "4:34:23", "remaining_time": "5:18:06"}
+{"current_steps": 595, "total_steps": 1274, "loss": 0.478, "lr": 2.5782735386086954e-05, "epoch": 3.270220588235294, "percentage": 46.7, "elapsed_time": "4:36:36", "remaining_time": "5:15:39"}
+{"current_steps": 600, "total_steps": 1274, "loss": 0.4792, "lr": 2.5519773839686707e-05, "epoch": 3.297794117647059, "percentage": 47.1, "elapsed_time": "4:38:51", "remaining_time": "5:13:15"}
+{"current_steps": 605, "total_steps": 1274, "loss": 0.4755, "lr": 2.525577527837036e-05, "epoch": 3.3253676470588234, "percentage": 47.49, "elapsed_time": "4:41:15", "remaining_time": "5:11:01"}
+{"current_steps": 610, "total_steps": 1274, "loss": 0.4742, "lr": 2.4990789300265256e-05, "epoch": 3.3529411764705883, "percentage": 47.88, "elapsed_time": "4:43:34", "remaining_time": "5:08:40"}
+{"current_steps": 615, "total_steps": 1274, "loss": 0.4695, "lr": 2.472486568900745e-05, "epoch": 3.380514705882353, "percentage": 48.27, "elapsed_time": "4:45:49", "remaining_time": "5:06:16"}
+{"current_steps": 620, "total_steps": 1274, "loss": 0.4796, "lr": 2.445805440438866e-05, "epoch": 3.4080882352941178, "percentage": 48.67, "elapsed_time": "4:48:05", "remaining_time": "5:03:53"}
+{"current_steps": 625, "total_steps": 1274, "loss": 0.4784, "lr": 2.419040557297024e-05, "epoch": 3.4356617647058822, "percentage": 49.06, "elapsed_time": "4:50:15", "remaining_time": "5:01:24"}
+{"current_steps": 630, "total_steps": 1274, "loss": 0.4742, "lr": 2.3921969478665702e-05, "epoch": 3.463235294117647, "percentage": 49.45, "elapsed_time": "4:52:31", "remaining_time": "4:59:01"}
+{"current_steps": 635, "total_steps": 1274, "loss": 0.4707, "lr": 2.3652796553293794e-05, "epoch": 3.4908088235294117, "percentage": 49.84, "elapsed_time": "4:54:51", "remaining_time": "4:56:42"}
+{"current_steps": 640, "total_steps": 1274, "loss": 0.4748, "lr": 2.338293736710373e-05, "epoch": 3.5183823529411766, "percentage": 50.24, "elapsed_time": "4:57:09", "remaining_time": "4:54:22"}
+{"current_steps": 645, "total_steps": 1274, "loss": 0.4756, "lr": 2.3112442619274408e-05, "epoch": 3.545955882352941, "percentage": 50.63, "elapsed_time": "4:59:23", "remaining_time": "4:51:58"}
+{"current_steps": 650, "total_steps": 1274, "loss": 0.4839, "lr": 2.2841363128389388e-05, "epoch": 3.5735294117647056, "percentage": 51.02, "elapsed_time": "5:01:38", "remaining_time": "4:49:34"}
+{"current_steps": 655, "total_steps": 1274, "loss": 0.4758, "lr": 2.2569749822889526e-05, "epoch": 3.6011029411764706, "percentage": 51.41, "elapsed_time": "5:03:52", "remaining_time": "4:47:10"}
+{"current_steps": 660, "total_steps": 1274, "loss": 0.4719, "lr": 2.229765373150489e-05, "epoch": 3.6286764705882355, "percentage": 51.81, "elapsed_time": "5:06:06", "remaining_time": "4:44:46"}
+{"current_steps": 665, "total_steps": 1274, "loss": 0.4679, "lr": 2.2025125973667817e-05, "epoch": 3.65625, "percentage": 52.2, "elapsed_time": "5:08:21", "remaining_time": "4:42:23"}
+{"current_steps": 670, "total_steps": 1274, "loss": 0.4714, "lr": 2.1752217749908997e-05, "epoch": 3.6838235294117645, "percentage": 52.59, "elapsed_time": "5:10:39", "remaining_time": "4:40:03"}
+{"current_steps": 675, "total_steps": 1274, "loss": 0.4709, "lr": 2.147898033223831e-05, "epoch": 3.7113970588235294, "percentage": 52.98, "elapsed_time": "5:12:51", "remaining_time": "4:37:37"}
+{"current_steps": 680, "total_steps": 1274, "loss": 0.4716, "lr": 2.120546505451218e-05, "epoch": 3.7389705882352944, "percentage": 53.38, "elapsed_time": "5:15:07", "remaining_time": "4:35:16"}
+{"current_steps": 685, "total_steps": 1274, "loss": 0.4739, "lr": 2.0931723302789346e-05, "epoch": 3.766544117647059, "percentage": 53.77, "elapsed_time": "5:17:25", "remaining_time": "4:32:56"}
+{"current_steps": 690, "total_steps": 1274, "loss": 0.474, "lr": 2.065780650567683e-05, "epoch": 3.7941176470588234, "percentage": 54.16, "elapsed_time": "5:19:41", "remaining_time": "4:30:34"}
+{"current_steps": 695, "total_steps": 1274, "loss": 0.4742, "lr": 2.038376612466793e-05, "epoch": 3.8216911764705883, "percentage": 54.55, "elapsed_time": "5:22:01", "remaining_time": "4:28:16"}
+{"current_steps": 700, "total_steps": 1274, "loss": 0.471, "lr": 2.0109653644473966e-05, "epoch": 3.849264705882353, "percentage": 54.95, "elapsed_time": "5:24:20", "remaining_time": "4:25:57"}
+{"current_steps": 705, "total_steps": 1274, "loss": 0.468, "lr": 1.9835520563351735e-05, "epoch": 3.8768382352941178, "percentage": 55.34, "elapsed_time": "5:26:36", "remaining_time": "4:23:36"}
+{"current_steps": 710, "total_steps": 1274, "loss": 0.4752, "lr": 1.9561418383428374e-05, "epoch": 3.9044117647058822, "percentage": 55.73, "elapsed_time": "5:28:54", "remaining_time": "4:21:16"}
+{"current_steps": 715, "total_steps": 1274, "loss": 0.4705, "lr": 1.9287398601025562e-05, "epoch": 3.931985294117647, "percentage": 56.12, "elapsed_time": "5:31:14", "remaining_time": "4:18:58"}
+{"current_steps": 720, "total_steps": 1274, "loss": 0.4689, "lr": 1.9013512696984696e-05, "epoch": 3.9595588235294117, "percentage": 56.51, "elapsed_time": "5:33:28", "remaining_time": "4:16:35"}
+{"current_steps": 725, "total_steps": 1274, "loss": 0.4722, "lr": 1.8739812126995093e-05, "epoch": 3.9871323529411766, "percentage": 56.91, "elapsed_time": "5:35:48", "remaining_time": "4:14:17"}
+{"current_steps": 730, "total_steps": 1274, "loss": 0.466, "lr": 1.8466348311926863e-05, "epoch": 4.011029411764706, "percentage": 57.3, "elapsed_time": "5:37:42", "remaining_time": "4:11:40"}
+{"current_steps": 735, "total_steps": 1274, "loss": 0.4682, "lr": 1.8193172628170324e-05, "epoch": 4.038602941176471, "percentage": 57.69, "elapsed_time": "5:39:57", "remaining_time": "4:09:18"}
+{"current_steps": 740, "total_steps": 1274, "loss": 0.4703, "lr": 1.792033639798377e-05, "epoch": 4.0661764705882355, "percentage": 58.08, "elapsed_time": "5:42:10", "remaining_time": "4:06:55"}
+{"current_steps": 745, "total_steps": 1274, "loss": 0.465, "lr": 1.764789087985145e-05, "epoch": 4.09375, "percentage": 58.48, "elapsed_time": "5:44:23", "remaining_time": "4:04:32"}
+{"current_steps": 750, "total_steps": 1274, "loss": 0.4625, "lr": 1.737588725885345e-05, "epoch": 4.1213235294117645, "percentage": 58.87, "elapsed_time": "5:46:38", "remaining_time": "4:02:11"}
+{"current_steps": 755, "total_steps": 1274, "loss": 0.4647, "lr": 1.7104376637049474e-05, "epoch": 4.148897058823529, "percentage": 59.26, "elapsed_time": "5:48:59", "remaining_time": "3:59:54"}
+{"current_steps": 760, "total_steps": 1274, "loss": 0.4711, "lr": 1.6833410023878104e-05, "epoch": 4.176470588235294, "percentage": 59.65, "elapsed_time": "5:51:13", "remaining_time": "3:57:32"}
+{"current_steps": 765, "total_steps": 1274, "loss": 0.4664, "lr": 1.6563038326573544e-05, "epoch": 4.204044117647059, "percentage": 60.05, "elapsed_time": "5:53:32", "remaining_time": "3:55:13"}
+{"current_steps": 770, "total_steps": 1274, "loss": 0.4675, "lr": 1.6293312340601545e-05, "epoch": 4.231617647058823, "percentage": 60.44, "elapsed_time": "5:55:45", "remaining_time": "3:52:51"}
+{"current_steps": 775, "total_steps": 1274, "loss": 0.4629, "lr": 1.60242827401163e-05, "epoch": 4.259191176470588, "percentage": 60.83, "elapsed_time": "5:58:03", "remaining_time": "3:50:32"}
+{"current_steps": 780, "total_steps": 1274, "loss": 0.4595, "lr": 1.5756000068440184e-05, "epoch": 4.286764705882353, "percentage": 61.22, "elapsed_time": "6:00:15", "remaining_time": "3:48:09"}
+{"current_steps": 785, "total_steps": 1274, "loss": 0.4659, "lr": 1.548851472856802e-05, "epoch": 4.314338235294118, "percentage": 61.62, "elapsed_time": "6:02:27", "remaining_time": "3:45:47"}
+{"current_steps": 790, "total_steps": 1274, "loss": 0.4675, "lr": 1.5221876973697729e-05, "epoch": 4.341911764705882, "percentage": 62.01, "elapsed_time": "6:04:39", "remaining_time": "3:43:24"}
+{"current_steps": 795, "total_steps": 1274, "loss": 0.4682, "lr": 1.4956136897789155e-05, "epoch": 4.369485294117647, "percentage": 62.4, "elapsed_time": "6:06:53", "remaining_time": "3:41:03"}
+{"current_steps": 800, "total_steps": 1274, "loss": 0.4684, "lr": 1.4691344426152733e-05, "epoch": 4.397058823529412, "percentage": 62.79, "elapsed_time": "6:09:11", "remaining_time": "3:38:44"}
+{"current_steps": 805, "total_steps": 1274, "loss": 0.468, "lr": 1.4427549306069915e-05, "epoch": 4.424632352941177, "percentage": 63.19, "elapsed_time": "6:11:24", "remaining_time": "3:36:23"}
+{"current_steps": 810, "total_steps": 1274, "loss": 0.4658, "lr": 1.416480109744701e-05, "epoch": 4.452205882352941, "percentage": 63.58, "elapsed_time": "6:13:43", "remaining_time": "3:34:05"}
+{"current_steps": 815, "total_steps": 1274, "loss": 0.4733, "lr": 1.3903149163504221e-05, "epoch": 4.479779411764706, "percentage": 63.97, "elapsed_time": "6:15:57", "remaining_time": "3:31:44"}
+{"current_steps": 820, "total_steps": 1274, "loss": 0.4637, "lr": 1.3642642661501641e-05, "epoch": 4.507352941176471, "percentage": 64.36, "elapsed_time": "6:18:13", "remaining_time": "3:29:24"}
+{"current_steps": 825, "total_steps": 1274, "loss": 0.4705, "lr": 1.3383330533503971e-05, "epoch": 4.5349264705882355, "percentage": 64.76, "elapsed_time": "6:20:30", "remaining_time": "3:27:05"}
+{"current_steps": 830, "total_steps": 1274, "loss": 0.4646, "lr": 1.3125261497185588e-05, "epoch": 4.5625, "percentage": 65.15, "elapsed_time": "6:22:49", "remaining_time": "3:24:47"}
+{"current_steps": 835, "total_steps": 1274, "loss": 0.4676, "lr": 1.2868484036677896e-05, "epoch": 4.5900735294117645, "percentage": 65.54, "elapsed_time": "6:25:04", "remaining_time": "3:22:27"}
+{"current_steps": 840, "total_steps": 1274, "loss": 0.4694, "lr": 1.2613046393460411e-05, "epoch": 4.617647058823529, "percentage": 65.93, "elapsed_time": "6:27:23", "remaining_time": "3:20:09"}
+{"current_steps": 845, "total_steps": 1274, "loss": 0.4685, "lr": 1.2358996557297532e-05, "epoch": 4.645220588235294, "percentage": 66.33, "elapsed_time": "6:29:38", "remaining_time": "3:17:49"}
+{"current_steps": 850, "total_steps": 1274, "loss": 0.4657, "lr": 1.2106382257222595e-05, "epoch": 4.672794117647059, "percentage": 66.72, "elapsed_time": "6:31:57", "remaining_time": "3:15:30"}
+{"current_steps": 855, "total_steps": 1274, "loss": 0.4632, "lr": 1.1855250952570852e-05, "epoch": 4.700367647058823, "percentage": 67.11, "elapsed_time": "6:34:08", "remaining_time": "3:13:09"}
+{"current_steps": 860, "total_steps": 1274, "loss": 0.4704, "lr": 1.1605649824063176e-05, "epoch": 4.727941176470588, "percentage": 67.5, "elapsed_time": "6:36:22", "remaining_time": "3:10:49"}
+{"current_steps": 865, "total_steps": 1274, "loss": 0.4646, "lr": 1.1357625764942095e-05, "epoch": 4.755514705882353, "percentage": 67.9, "elapsed_time": "6:38:36", "remaining_time": "3:08:28"}
+{"current_steps": 870, "total_steps": 1274, "loss": 0.463, "lr": 1.1111225372161818e-05, "epoch": 4.783088235294118, "percentage": 68.29, "elapsed_time": "6:40:52", "remaining_time": "3:06:09"}
+{"current_steps": 875, "total_steps": 1274, "loss": 0.4616, "lr": 1.0866494937633953e-05, "epoch": 4.810661764705882, "percentage": 68.68, "elapsed_time": "6:43:08", "remaining_time": "3:03:49"}
+{"current_steps": 880, "total_steps": 1274, "loss": 0.468, "lr": 1.0623480439530493e-05, "epoch": 4.838235294117647, "percentage": 69.07, "elapsed_time": "6:45:25", "remaining_time": "3:01:31"}
+{"current_steps": 885, "total_steps": 1274, "loss": 0.4693, "lr": 1.038222753364581e-05, "epoch": 4.865808823529412, "percentage": 69.47, "elapsed_time": "6:47:40", "remaining_time": "2:59:11"}
+{"current_steps": 890, "total_steps": 1274, "loss": 0.4669, "lr": 1.0142781544819158e-05, "epoch": 4.893382352941177, "percentage": 69.86, "elapsed_time": "6:49:59", "remaining_time": "2:56:53"}
+{"current_steps": 895, "total_steps": 1274, "loss": 0.4628, "lr": 9.905187458419343e-06, "epoch": 4.920955882352941, "percentage": 70.25, "elapsed_time": "6:52:16", "remaining_time": "2:54:35"}
+{"current_steps": 900, "total_steps": 1274, "loss": 0.4679, "lr": 9.669489911893261e-06, "epoch": 4.948529411764706, "percentage": 70.64, "elapsed_time": "6:54:32", "remaining_time": "2:52:15"}
+{"current_steps": 905, "total_steps": 1274, "loss": 0.4591, "lr": 9.435733186379694e-06, "epoch": 4.976102941176471, "percentage": 71.04, "elapsed_time": "6:57:03", "remaining_time": "2:50:03"}
+{"current_steps": 910, "total_steps": 1274, "loss": 0.4665, "lr": 9.2039611983901e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "6:59:01", "remaining_time": "2:47:36"}
+{"current_steps": 915, "total_steps": 1274, "loss": 0.4582, "lr": 8.974217491557916e-06, "epoch": 5.0275735294117645, "percentage": 71.82, "elapsed_time": "7:01:16", "remaining_time": "2:45:17"}
+{"current_steps": 920, "total_steps": 1274, "loss": 0.4627, "lr": 8.746545228457864e-06, "epoch": 5.055147058823529, "percentage": 72.21, "elapsed_time": "7:03:32", "remaining_time": "2:42:58"}
+{"current_steps": 925, "total_steps": 1274, "loss": 0.4615, "lr": 8.520987182496916e-06, "epoch": 5.082720588235294, "percentage": 72.61, "elapsed_time": "7:05:47", "remaining_time": "2:40:39"}
+{"current_steps": 930, "total_steps": 1274, "loss": 0.4605, "lr": 8.297585729878328e-06, "epoch": 5.110294117647059, "percentage": 73.0, "elapsed_time": "7:08:06", "remaining_time": "2:38:21"}
+{"current_steps": 935, "total_steps": 1274, "loss": 0.4595, "lr": 8.076382841640278e-06, "epoch": 5.137867647058823, "percentage": 73.39, "elapsed_time": "7:10:18", "remaining_time": "2:36:01"}
+{"current_steps": 940, "total_steps": 1274, "loss": 0.4691, "lr": 7.8574200757707e-06, "epoch": 5.165441176470588, "percentage": 73.78, "elapsed_time": "7:12:33", "remaining_time": "2:33:41"}
+{"current_steps": 945, "total_steps": 1274, "loss": 0.4627, "lr": 7.640738569399645e-06, "epoch": 5.193014705882353, "percentage": 74.18, "elapsed_time": "7:14:44", "remaining_time": "2:31:21"}
+{"current_steps": 950, "total_steps": 1274, "loss": 0.4653, "lr": 7.426379031070736e-06, "epoch": 5.220588235294118, "percentage": 74.57, "elapsed_time": "7:16:58", "remaining_time": "2:29:02"}
+{"current_steps": 955, "total_steps": 1274, "loss": 0.4623, "lr": 7.214381733093156e-06, "epoch": 5.248161764705882, "percentage": 74.96, "elapsed_time": "7:19:13", "remaining_time": "2:26:42"}
+{"current_steps": 960, "total_steps": 1274, "loss": 0.464, "lr": 7.004786503975552e-06, "epoch": 5.275735294117647, "percentage": 75.35, "elapsed_time": "7:21:25", "remaining_time": "2:24:22"}
+{"current_steps": 965, "total_steps": 1274, "loss": 0.4604, "lr": 6.7976327209433855e-06, "epoch": 5.303308823529412, "percentage": 75.75, "elapsed_time": "7:23:42", "remaining_time": "2:22:04"}
+{"current_steps": 970, "total_steps": 1274, "loss": 0.4589, "lr": 6.592959302541004e-06, "epoch": 5.330882352941177, "percentage": 76.14, "elapsed_time": "7:26:00", "remaining_time": "2:19:46"}
+{"current_steps": 975, "total_steps": 1274, "loss": 0.4609, "lr": 6.39080470131989e-06, "epoch": 5.358455882352941, "percentage": 76.53, "elapsed_time": "7:28:15", "remaining_time": "2:17:27"}
+{"current_steps": 980, "total_steps": 1274, "loss": 0.4565, "lr": 6.1912068966145145e-06, "epoch": 5.386029411764706, "percentage": 76.92, "elapsed_time": "7:30:27", "remaining_time": "2:15:08"}
+{"current_steps": 985, "total_steps": 1274, "loss": 0.4629, "lr": 5.994203387407036e-06, "epoch": 5.413602941176471, "percentage": 77.32, "elapsed_time": "7:32:43", "remaining_time": "2:12:49"}
+{"current_steps": 990, "total_steps": 1274, "loss": 0.4633, "lr": 5.7998311852822406e-06, "epoch": 5.4411764705882355, "percentage": 77.71, "elapsed_time": "7:35:01", "remaining_time": "2:10:32"}
+{"current_steps": 995, "total_steps": 1274, "loss": 0.4622, "lr": 5.608126807474145e-06, "epoch": 5.46875, "percentage": 78.1, "elapsed_time": "7:37:24", "remaining_time": "2:08:15"}
+{"current_steps": 1000, "total_steps": 1274, "loss": 0.4626, "lr": 5.419126270005317e-06, "epoch": 5.4963235294117645, "percentage": 78.49, "elapsed_time": "7:39:42", "remaining_time": "2:05:57"}
+{"current_steps": 1005, "total_steps": 1274, "loss": 0.4557, "lr": 5.23286508092051e-06, "epoch": 5.523897058823529, "percentage": 78.89, "elapsed_time": "7:42:01", "remaining_time": "2:03:39"}
+{"current_steps": 1010, "total_steps": 1274, "loss": 0.4656, "lr": 5.049378233615652e-06, "epoch": 5.551470588235294, "percentage": 79.28, "elapsed_time": "7:44:17", "remaining_time": "2:01:21"}
+{"current_steps": 1015, "total_steps": 1274, "loss": 0.4624, "lr": 4.868700200263521e-06, "epoch": 5.579044117647059, "percentage": 79.67, "elapsed_time": "7:46:29", "remaining_time": "1:59:02"}
+{"current_steps": 1020, "total_steps": 1274, "loss": 0.459, "lr": 4.690864925337404e-06, "epoch": 5.606617647058823, "percentage": 80.06, "elapsed_time": "7:48:48", "remaining_time": "1:56:44"}
+{"current_steps": 1025, "total_steps": 1274, "loss": 0.4587, "lr": 4.515905819233828e-06, "epoch": 5.634191176470588, "percentage": 80.46, "elapsed_time": "7:51:03", "remaining_time": "1:54:25"}
+{"current_steps": 1030, "total_steps": 1274, "loss": 0.463, "lr": 4.343855751995645e-06, "epoch": 5.661764705882353, "percentage": 80.85, "elapsed_time": "7:53:18", "remaining_time": "1:52:07"}
+{"current_steps": 1035, "total_steps": 1274, "loss": 0.4629, "lr": 4.174747047136707e-06, "epoch": 5.689338235294118, "percentage": 81.24, "elapsed_time": "7:55:32", "remaining_time": "1:49:48"}
+{"current_steps": 1040, "total_steps": 1274, "loss": 0.4623, "lr": 4.008611475569082e-06, "epoch": 5.716911764705882, "percentage": 81.63, "elapsed_time": "7:57:49", "remaining_time": "1:47:30"}
+{"current_steps": 1045, "total_steps": 1274, "loss": 0.4664, "lr": 3.845480249634226e-06, "epoch": 5.744485294117647, "percentage": 82.03, "elapsed_time": "7:59:58", "remaining_time": "1:45:10"}
+{"current_steps": 1050, "total_steps": 1274, "loss": 0.4563, "lr": 3.685384017239013e-06, "epoch": 5.772058823529412, "percentage": 82.42, "elapsed_time": "8:02:18", "remaining_time": "1:42:53"}
+{"current_steps": 1055, "total_steps": 1274, "loss": 0.4606, "lr": 3.5283528560978163e-06, "epoch": 5.799632352941177, "percentage": 82.81, "elapsed_time": "8:04:34", "remaining_time": "1:40:35"}
+{"current_steps": 1060, "total_steps": 1274, "loss": 0.463, "lr": 3.3744162680817526e-06, "epoch": 5.827205882352941, "percentage": 83.2, "elapsed_time": "8:06:56", "remaining_time": "1:38:18"}
+{"current_steps": 1065, "total_steps": 1274, "loss": 0.4628, "lr": 3.2236031736760775e-06, "epoch": 5.854779411764706, "percentage": 83.59, "elapsed_time": "8:09:12", "remaining_time": "1:36:00"}
+{"current_steps": 1070, "total_steps": 1274, "loss": 0.4643, "lr": 3.075941906546789e-06, "epoch": 5.882352941176471, "percentage": 83.99, "elapsed_time": "8:11:24", "remaining_time": "1:33:41"}
+{"current_steps": 1075, "total_steps": 1274, "loss": 0.4634, "lr": 2.9314602082175624e-06, "epoch": 5.9099264705882355, "percentage": 84.38, "elapsed_time": "8:13:45", "remaining_time": "1:31:24"}
+{"current_steps": 1080, "total_steps": 1274, "loss": 0.4581, "lr": 2.790185222857804e-06, "epoch": 5.9375, "percentage": 84.77, "elapsed_time": "8:16:02", "remaining_time": "1:29:06"}
+{"current_steps": 1085, "total_steps": 1274, "loss": 0.4602, "lr": 2.6521434921830593e-06, "epoch": 5.9650735294117645, "percentage": 85.16, "elapsed_time": "8:18:20", "remaining_time": "1:26:48"}
+{"current_steps": 1090, "total_steps": 1274, "loss": 0.4564, "lr": 2.517360950468519e-06, "epoch": 5.992647058823529, "percentage": 85.56, "elapsed_time": "8:20:40", "remaining_time": "1:24:31"}
+{"current_steps": 1095, "total_steps": 1274, "loss": 0.4622, "lr": 2.3858629196766846e-06, "epoch": 6.016544117647059, "percentage": 85.95, "elapsed_time": "8:22:37", "remaining_time": "1:22:09"}
+{"current_steps": 1100, "total_steps": 1274, "loss": 0.4634, "lr": 2.2576741047000605e-06, "epoch": 6.044117647058823, "percentage": 86.34, "elapsed_time": "8:24:53", "remaining_time": "1:19:51"}
+{"current_steps": 1105, "total_steps": 1274, "loss": 0.4583, "lr": 2.1328185887197872e-06, "epoch": 6.071691176470588, "percentage": 86.73, "elapsed_time": "8:27:13", "remaining_time": "1:17:34"}
+{"current_steps": 1110, "total_steps": 1274, "loss": 0.4545, "lr": 2.011319828681049e-06, "epoch": 6.099264705882353, "percentage": 87.13, "elapsed_time": "8:29:28", "remaining_time": "1:15:16"}
+{"current_steps": 1115, "total_steps": 1274, "loss": 0.4582, "lr": 1.8932006508861866e-06, "epoch": 6.126838235294118, "percentage": 87.52, "elapsed_time": "8:31:43", "remaining_time": "1:12:58"}
+{"current_steps": 1120, "total_steps": 1274, "loss": 0.4631, "lr": 1.7784832467062129e-06, "epoch": 6.154411764705882, "percentage": 87.91, "elapsed_time": "8:33:59", "remaining_time": "1:10:40"}
+{"current_steps": 1125, "total_steps": 1274, "loss": 0.4559, "lr": 1.6671891684117048e-06, "epoch": 6.181985294117647, "percentage": 88.3, "elapsed_time": "8:36:11", "remaining_time": "1:08:21"}
+{"current_steps": 1130, "total_steps": 1274, "loss": 0.4602, "lr": 1.55933932512369e-06, "epoch": 6.209558823529412, "percentage": 88.7, "elapsed_time": "8:38:26", "remaining_time": "1:06:04"}
+{"current_steps": 1135, "total_steps": 1274, "loss": 0.4616, "lr": 1.4549539788853984e-06, "epoch": 6.237132352941177, "percentage": 89.09, "elapsed_time": "8:40:38", "remaining_time": "1:03:45"}
+{"current_steps": 1140, "total_steps": 1274, "loss": 0.4573, "lr": 1.3540527408555915e-06, "epoch": 6.264705882352941, "percentage": 89.48, "elapsed_time": "8:42:59", "remaining_time": "1:01:28"}
+{"current_steps": 1145, "total_steps": 1274, "loss": 0.4636, "lr": 1.2566545676241494e-06, "epoch": 6.292279411764706, "percentage": 89.87, "elapsed_time": "8:45:14", "remaining_time": "0:59:10"}
+{"current_steps": 1150, "total_steps": 1274, "loss": 0.4647, "lr": 1.1627777576506306e-06, "epoch": 6.319852941176471, "percentage": 90.27, "elapsed_time": "8:47:27", "remaining_time": "0:56:52"}
+{"current_steps": 1155, "total_steps": 1274, "loss": 0.4619, "lr": 1.0724399478265312e-06, "epoch": 6.3474264705882355, "percentage": 90.66, "elapsed_time": "8:49:44", "remaining_time": "0:54:34"}
+{"current_steps": 1160, "total_steps": 1274, "loss": 0.463, "lr": 9.85658110161747e-07, "epoch": 6.375, "percentage": 91.05, "elapsed_time": "8:51:54", "remaining_time": "0:52:16"}
+{"current_steps": 1165, "total_steps": 1274, "loss": 0.4628, "lr": 9.02448548596031e-07, "epoch": 6.4025735294117645, "percentage": 91.44, "elapsed_time": "8:54:04", "remaining_time": "0:49:58"}
+{"current_steps": 1170, "total_steps": 1274, "loss": 0.4626, "lr": 8.228268959359086e-07, "epoch": 6.430147058823529, "percentage": 91.84, "elapsed_time": "8:56:19", "remaining_time": "0:47:40"}
+{"current_steps": 1175, "total_steps": 1274, "loss": 0.4574, "lr": 7.468081109177028e-07, "epoch": 6.457720588235294, "percentage": 92.23, "elapsed_time": "8:58:35", "remaining_time": "0:45:22"}
+{"current_steps": 1180, "total_steps": 1274, "loss": 0.4646, "lr": 6.744064753972068e-07, "epoch": 6.485294117647059, "percentage": 92.62, "elapsed_time": "9:00:50", "remaining_time": "0:43:05"}
+{"current_steps": 1185, "total_steps": 1274, "loss": 0.4559, "lr": 6.056355916665024e-07, "epoch": 6.512867647058823, "percentage": 93.01, "elapsed_time": "9:03:00", "remaining_time": "0:40:46"}
+{"current_steps": 1190, "total_steps": 1274, "loss": 0.4541, "lr": 5.405083798984567e-07, "epoch": 6.540441176470588, "percentage": 93.41, "elapsed_time": "9:05:14", "remaining_time": "0:38:29"}
+{"current_steps": 1195, "total_steps": 1274, "loss": 0.4566, "lr": 4.790370757193907e-07, "epoch": 6.568014705882353, "percentage": 93.8, "elapsed_time": "9:07:30", "remaining_time": "0:36:11"}
+{"current_steps": 1200, "total_steps": 1274, "loss": 0.4538, "lr": 4.212332279103204e-07, "epoch": 6.595588235294118, "percentage": 94.19, "elapsed_time": "9:09:44", "remaining_time": "0:33:54"}
+{"current_steps": 1205, "total_steps": 1274, "loss": 0.4598, "lr": 3.671076962372655e-07, "epoch": 6.623161764705882, "percentage": 94.58, "elapsed_time": "9:12:08", "remaining_time": "0:31:36"}
+{"current_steps": 1210, "total_steps": 1274, "loss": 0.4568, "lr": 3.1667064941099724e-07, "epoch": 6.650735294117647, "percentage": 94.98, "elapsed_time": "9:14:24", "remaining_time": "0:29:19"}
+{"current_steps": 1215, "total_steps": 1274, "loss": 0.4632, "lr": 2.699315631766064e-07, "epoch": 6.678308823529412, "percentage": 95.37, "elapsed_time": "9:16:34", "remaining_time": "0:27:01"}
+{"current_steps": 1220, "total_steps": 1274, "loss": 0.46, "lr": 2.26899218533283e-07, "epoch": 6.705882352941177, "percentage": 95.76, "elapsed_time": "9:18:51", "remaining_time": "0:24:44"}
+{"current_steps": 1225, "total_steps": 1274, "loss": 0.4624, "lr": 1.8758170008459142e-07, "epoch": 6.733455882352941, "percentage": 96.15, "elapsed_time": "9:21:05", "remaining_time": "0:22:26"}
+{"current_steps": 1230, "total_steps": 1274, "loss": 0.4548, "lr": 1.5198639451960095e-07, "epoch": 6.761029411764706, "percentage": 96.55, "elapsed_time": "9:23:23", "remaining_time": "0:20:09"}
+{"current_steps": 1235, "total_steps": 1274, "loss": 0.4555, "lr": 1.201199892251337e-07, "epoch": 6.788602941176471, "percentage": 96.94, "elapsed_time": "9:25:45", "remaining_time": "0:17:51"}
+{"current_steps": 1240, "total_steps": 1274, "loss": 0.4552, "lr": 9.198847102937614e-08, "epoch": 6.8161764705882355, "percentage": 97.33, "elapsed_time": "9:28:00", "remaining_time": "0:15:34"}
+{"current_steps": 1245, "total_steps": 1274, "loss": 0.4622, "lr": 6.759712507711902e-08, "epoch": 6.84375, "percentage": 97.72, "elapsed_time": "9:30:14", "remaining_time": "0:13:16"}
+{"current_steps": 1250, "total_steps": 1274, "loss": 0.457, "lr": 4.695053383683812e-08, "epoch": 6.8713235294117645, "percentage": 98.12, "elapsed_time": "9:32:30", "remaining_time": "0:10:59"}
+{"current_steps": 1255, "total_steps": 1274, "loss": 0.4554, "lr": 3.0052576239749666e-08, "epoch": 6.898897058823529, "percentage": 98.51, "elapsed_time": "9:34:46", "remaining_time": "0:08:42"}
+{"current_steps": 1260, "total_steps": 1274, "loss": 0.4581, "lr": 1.6906426951086573e-08, "epoch": 6.926470588235294, "percentage": 98.9, "elapsed_time": "9:36:58", "remaining_time": "0:06:24"}
+{"current_steps": 1265, "total_steps": 1274, "loss": 0.4614, "lr": 7.514555773648901e-09, "epoch": 6.954044117647059, "percentage": 99.29, "elapsed_time": "9:39:17", "remaining_time": "0:04:07"}
+{"current_steps": 1270, "total_steps": 1274, "loss": 0.4614, "lr": 1.8787271838083263e-09, "epoch": 6.981617647058823, "percentage": 99.69, "elapsed_time": "9:41:35", "remaining_time": "0:01:49"}
+{"current_steps": 1274, "total_steps": 1274, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "9:43:16", "remaining_time": "0:00:00"}
+{"current_steps": 1274, "total_steps": 1274, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 1274, "total_steps": 1274, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 1274, "total_steps": 1274, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 1274, "total_steps": 1274, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 1274, "total_steps": 1274, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bf0d68724a68e20766dfb2e9e2f02955921c3edd6fbd9d88f4ff9a575ccb38
+size 8657