初始化项目，由ModelHub XC社区提供模型

Model: laion/exp-swd-r2egym-wo-docker_glm_4_7_traces
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: apache-2.0
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: exp-swd-r2egym-wo-docker_glm_4_7_traces
+  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. -->
+
+# exp-swd-r2egym-wo-docker_glm_4_7_traces
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/exp-swd-r2egym-wo-docker_glm_4.7_traces dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 64
+- 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 4.57.3
+- Pytorch 2.9.0+cu128
+- Datasets 4.4.1
+- 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": 6.4622163357687645,
+    "achieved_tflops_per_gpu_theoretical": 447.2034022926582,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.21355924010276794,
+    "mfu_percent": 0.6534091340514423,
+    "mfu_percent_theoretical": 45.217735317761196,
+    "total_flos": 6.986449832713912e+17,
+    "train_loss": 0.24971561980327953,
+    "train_runtime": 13514.0358,
+    "train_samples_per_second": 2.1,
+    "train_steps_per_second": 0.132,
+    "valid_targets_mean": 2789.8,
+    "valid_targets_min": 2416
+}

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": "4.57.3",
+  "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": "4.57.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f22d10d33941156f309d7129d55bc836e19718d956bea22df1f51bb297256e
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b82349cb13a6d37ec89709c65ec4d00d1ac4573d8de8dc25a7e3f1dc39e7dc
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642e9c41af7adc2fe3357eb27f5a3ab6f1f668ae892c5cc595d3426bc085bec6
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a623a00bf58688f5d63b798f43c77cd797b930c3d0b52840e1e22f7f5af0cdf3
+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": "exp-swd-r2egym-wo-docker_glm_4.7_traces",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "DCAgent/exp-swd-r2egym-wo-docker_glm_4.7_traces",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/exp-swd-r2egym-wo-docker_glm_4_7_traces/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp-swd-r2egym-wo-docker_glm_4-7_traces_Qwen3-8B",
+  "traces_location_s3": null
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 6.4622163357687645,
+    "achieved_tflops_per_gpu_theoretical": 447.2034022926582,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.21355924010276794,
+    "mfu_percent": 0.6534091340514423,
+    "mfu_percent_theoretical": 45.217735317761196,
+    "total_flos": 6.986449832713912e+17,
+    "train_loss": 0.24971561980327953,
+    "train_runtime": 13514.0358,
+    "train_samples_per_second": 2.1,
+    "train_steps_per_second": 0.132,
+    "valid_targets_mean": 2789.8,
+    "valid_targets_min": 2416
+}

trainer_log.jsonl

@@ -0,0 +1,356 @@
+{"current_steps": 5, "total_steps": 1778, "loss": 0.855, "lr": 8.98876404494382e-07, "epoch": 0.01972386587771203, "percentage": 0.28, "elapsed_time": "0:00:47", "remaining_time": "4:41:19"}
+{"current_steps": 10, "total_steps": 1778, "loss": 0.8485, "lr": 2.02247191011236e-06, "epoch": 0.03944773175542406, "percentage": 0.56, "elapsed_time": "0:01:29", "remaining_time": "4:24:00"}
+{"current_steps": 15, "total_steps": 1778, "loss": 0.7901, "lr": 3.146067415730337e-06, "epoch": 0.05917159763313609, "percentage": 0.84, "elapsed_time": "0:02:09", "remaining_time": "4:14:03"}
+{"current_steps": 20, "total_steps": 1778, "loss": 0.7372, "lr": 4.269662921348315e-06, "epoch": 0.07889546351084813, "percentage": 1.12, "elapsed_time": "0:02:50", "remaining_time": "4:09:30"}
+{"current_steps": 25, "total_steps": 1778, "loss": 0.6841, "lr": 5.393258426966292e-06, "epoch": 0.09861932938856016, "percentage": 1.41, "elapsed_time": "0:03:28", "remaining_time": "4:03:13"}
+{"current_steps": 30, "total_steps": 1778, "loss": 0.6258, "lr": 6.51685393258427e-06, "epoch": 0.11834319526627218, "percentage": 1.69, "elapsed_time": "0:04:09", "remaining_time": "4:02:28"}
+{"current_steps": 35, "total_steps": 1778, "loss": 0.575, "lr": 7.640449438202247e-06, "epoch": 0.13806706114398423, "percentage": 1.97, "elapsed_time": "0:04:52", "remaining_time": "4:02:28"}
+{"current_steps": 40, "total_steps": 1778, "loss": 0.5306, "lr": 8.764044943820226e-06, "epoch": 0.15779092702169625, "percentage": 2.25, "elapsed_time": "0:05:33", "remaining_time": "4:01:29"}
+{"current_steps": 45, "total_steps": 1778, "loss": 0.4711, "lr": 9.887640449438202e-06, "epoch": 0.17751479289940827, "percentage": 2.53, "elapsed_time": "0:06:16", "remaining_time": "4:01:26"}
+{"current_steps": 50, "total_steps": 1778, "loss": 0.4641, "lr": 1.101123595505618e-05, "epoch": 0.19723865877712032, "percentage": 2.81, "elapsed_time": "0:06:56", "remaining_time": "4:00:00"}
+{"current_steps": 55, "total_steps": 1778, "loss": 0.4218, "lr": 1.213483146067416e-05, "epoch": 0.21696252465483234, "percentage": 3.09, "elapsed_time": "0:07:31", "remaining_time": "3:55:32"}
+{"current_steps": 60, "total_steps": 1778, "loss": 0.409, "lr": 1.3258426966292135e-05, "epoch": 0.23668639053254437, "percentage": 3.37, "elapsed_time": "0:08:12", "remaining_time": "3:55:13"}
+{"current_steps": 65, "total_steps": 1778, "loss": 0.3929, "lr": 1.4382022471910113e-05, "epoch": 0.2564102564102564, "percentage": 3.66, "elapsed_time": "0:08:49", "remaining_time": "3:52:41"}
+{"current_steps": 70, "total_steps": 1778, "loss": 0.365, "lr": 1.5505617977528093e-05, "epoch": 0.27613412228796846, "percentage": 3.94, "elapsed_time": "0:09:31", "remaining_time": "3:52:18"}
+{"current_steps": 75, "total_steps": 1778, "loss": 0.3623, "lr": 1.662921348314607e-05, "epoch": 0.2958579881656805, "percentage": 4.22, "elapsed_time": "0:10:10", "remaining_time": "3:51:11"}
+{"current_steps": 80, "total_steps": 1778, "loss": 0.352, "lr": 1.7752808988764045e-05, "epoch": 0.3155818540433925, "percentage": 4.5, "elapsed_time": "0:10:47", "remaining_time": "3:49:10"}
+{"current_steps": 85, "total_steps": 1778, "loss": 0.345, "lr": 1.8876404494382024e-05, "epoch": 0.33530571992110453, "percentage": 4.78, "elapsed_time": "0:11:28", "remaining_time": "3:48:30"}
+{"current_steps": 90, "total_steps": 1778, "loss": 0.3452, "lr": 2e-05, "epoch": 0.35502958579881655, "percentage": 5.06, "elapsed_time": "0:12:08", "remaining_time": "3:47:39"}
+{"current_steps": 95, "total_steps": 1778, "loss": 0.3375, "lr": 2.1123595505617976e-05, "epoch": 0.3747534516765286, "percentage": 5.34, "elapsed_time": "0:12:48", "remaining_time": "3:46:59"}
+{"current_steps": 100, "total_steps": 1778, "loss": 0.329, "lr": 2.2247191011235958e-05, "epoch": 0.39447731755424065, "percentage": 5.62, "elapsed_time": "0:13:28", "remaining_time": "3:46:01"}
+{"current_steps": 105, "total_steps": 1778, "loss": 0.3276, "lr": 2.3370786516853933e-05, "epoch": 0.41420118343195267, "percentage": 5.91, "elapsed_time": "0:14:05", "remaining_time": "3:44:27"}
+{"current_steps": 110, "total_steps": 1778, "loss": 0.3193, "lr": 2.4494382022471914e-05, "epoch": 0.4339250493096647, "percentage": 6.19, "elapsed_time": "0:14:45", "remaining_time": "3:43:44"}
+{"current_steps": 115, "total_steps": 1778, "loss": 0.3191, "lr": 2.561797752808989e-05, "epoch": 0.4536489151873767, "percentage": 6.47, "elapsed_time": "0:15:25", "remaining_time": "3:43:08"}
+{"current_steps": 120, "total_steps": 1778, "loss": 0.3172, "lr": 2.6741573033707867e-05, "epoch": 0.47337278106508873, "percentage": 6.75, "elapsed_time": "0:16:07", "remaining_time": "3:42:50"}
+{"current_steps": 125, "total_steps": 1778, "loss": 0.3129, "lr": 2.7865168539325845e-05, "epoch": 0.4930966469428008, "percentage": 7.03, "elapsed_time": "0:16:51", "remaining_time": "3:42:55"}
+{"current_steps": 130, "total_steps": 1778, "loss": 0.316, "lr": 2.8988764044943823e-05, "epoch": 0.5128205128205128, "percentage": 7.31, "elapsed_time": "0:17:30", "remaining_time": "3:41:55"}
+{"current_steps": 135, "total_steps": 1778, "loss": 0.3114, "lr": 3.0112359550561798e-05, "epoch": 0.5325443786982249, "percentage": 7.59, "elapsed_time": "0:18:08", "remaining_time": "3:40:47"}
+{"current_steps": 140, "total_steps": 1778, "loss": 0.3181, "lr": 3.123595505617978e-05, "epoch": 0.5522682445759369, "percentage": 7.87, "elapsed_time": "0:18:45", "remaining_time": "3:39:32"}
+{"current_steps": 145, "total_steps": 1778, "loss": 0.2947, "lr": 3.235955056179776e-05, "epoch": 0.571992110453649, "percentage": 8.16, "elapsed_time": "0:19:23", "remaining_time": "3:38:26"}
+{"current_steps": 150, "total_steps": 1778, "loss": 0.2905, "lr": 3.3483146067415736e-05, "epoch": 0.591715976331361, "percentage": 8.44, "elapsed_time": "0:20:02", "remaining_time": "3:37:33"}
+{"current_steps": 155, "total_steps": 1778, "loss": 0.2919, "lr": 3.4606741573033714e-05, "epoch": 0.611439842209073, "percentage": 8.72, "elapsed_time": "0:20:43", "remaining_time": "3:37:05"}
+{"current_steps": 160, "total_steps": 1778, "loss": 0.306, "lr": 3.5730337078651685e-05, "epoch": 0.631163708086785, "percentage": 9.0, "elapsed_time": "0:21:28", "remaining_time": "3:37:09"}
+{"current_steps": 165, "total_steps": 1778, "loss": 0.2975, "lr": 3.685393258426967e-05, "epoch": 0.650887573964497, "percentage": 9.28, "elapsed_time": "0:22:07", "remaining_time": "3:36:13"}
+{"current_steps": 170, "total_steps": 1778, "loss": 0.3027, "lr": 3.797752808988764e-05, "epoch": 0.6706114398422091, "percentage": 9.56, "elapsed_time": "0:22:47", "remaining_time": "3:35:36"}
+{"current_steps": 175, "total_steps": 1778, "loss": 0.3027, "lr": 3.910112359550562e-05, "epoch": 0.6903353057199211, "percentage": 9.84, "elapsed_time": "0:23:22", "remaining_time": "3:34:09"}
+{"current_steps": 180, "total_steps": 1778, "loss": 0.2877, "lr": 3.999996144687019e-05, "epoch": 0.7100591715976331, "percentage": 10.12, "elapsed_time": "0:24:01", "remaining_time": "3:33:13"}
+{"current_steps": 185, "total_steps": 1778, "loss": 0.2916, "lr": 3.9998612102933544e-05, "epoch": 0.7297830374753451, "percentage": 10.4, "elapsed_time": "0:24:38", "remaining_time": "3:32:09"}
+{"current_steps": 190, "total_steps": 1778, "loss": 0.2937, "lr": 3.999533525113843e-05, "epoch": 0.7495069033530573, "percentage": 10.69, "elapsed_time": "0:25:16", "remaining_time": "3:31:13"}
+{"current_steps": 195, "total_steps": 1778, "loss": 0.2977, "lr": 3.9990131207314634e-05, "epoch": 0.7692307692307693, "percentage": 10.97, "elapsed_time": "0:25:54", "remaining_time": "3:30:15"}
+{"current_steps": 200, "total_steps": 1778, "loss": 0.2814, "lr": 3.998300047303874e-05, "epoch": 0.7889546351084813, "percentage": 11.25, "elapsed_time": "0:26:34", "remaining_time": "3:29:43"}
+{"current_steps": 205, "total_steps": 1778, "loss": 0.2811, "lr": 3.997394373558576e-05, "epoch": 0.8086785009861933, "percentage": 11.53, "elapsed_time": "0:27:12", "remaining_time": "3:28:48"}
+{"current_steps": 210, "total_steps": 1778, "loss": 0.2869, "lr": 3.9962961867862894e-05, "epoch": 0.8284023668639053, "percentage": 11.81, "elapsed_time": "0:27:48", "remaining_time": "3:27:37"}
+{"current_steps": 215, "total_steps": 1778, "loss": 0.271, "lr": 3.995005592832541e-05, "epoch": 0.8481262327416174, "percentage": 12.09, "elapsed_time": "0:28:26", "remaining_time": "3:26:45"}
+{"current_steps": 220, "total_steps": 1778, "loss": 0.2969, "lr": 3.993522716087462e-05, "epoch": 0.8678500986193294, "percentage": 12.37, "elapsed_time": "0:29:06", "remaining_time": "3:26:05"}
+{"current_steps": 225, "total_steps": 1778, "loss": 0.2757, "lr": 3.991847699473801e-05, "epoch": 0.8875739644970414, "percentage": 12.65, "elapsed_time": "0:29:45", "remaining_time": "3:25:27"}
+{"current_steps": 230, "total_steps": 1778, "loss": 0.2824, "lr": 3.989980704433144e-05, "epoch": 0.9072978303747534, "percentage": 12.94, "elapsed_time": "0:30:24", "remaining_time": "3:24:37"}
+{"current_steps": 235, "total_steps": 1778, "loss": 0.2826, "lr": 3.98792191091036e-05, "epoch": 0.9270216962524654, "percentage": 13.22, "elapsed_time": "0:31:01", "remaining_time": "3:23:42"}
+{"current_steps": 240, "total_steps": 1778, "loss": 0.2732, "lr": 3.9856715173362527e-05, "epoch": 0.9467455621301775, "percentage": 13.5, "elapsed_time": "0:31:37", "remaining_time": "3:22:40"}
+{"current_steps": 245, "total_steps": 1778, "loss": 0.2839, "lr": 3.9832297406084386e-05, "epoch": 0.9664694280078896, "percentage": 13.78, "elapsed_time": "0:32:15", "remaining_time": "3:21:49"}
+{"current_steps": 250, "total_steps": 1778, "loss": 0.2799, "lr": 3.980596816070442e-05, "epoch": 0.9861932938856016, "percentage": 14.06, "elapsed_time": "0:32:54", "remaining_time": "3:21:08"}
+{"current_steps": 255, "total_steps": 1778, "loss": 0.2848, "lr": 3.97777299748901e-05, "epoch": 1.0039447731755424, "percentage": 14.34, "elapsed_time": "0:33:25", "remaining_time": "3:19:40"}
+{"current_steps": 260, "total_steps": 1778, "loss": 0.2858, "lr": 3.974758557029653e-05, "epoch": 1.0236686390532543, "percentage": 14.62, "elapsed_time": "0:34:02", "remaining_time": "3:18:47"}
+{"current_steps": 265, "total_steps": 1778, "loss": 0.2767, "lr": 3.971553785230418e-05, "epoch": 1.0433925049309665, "percentage": 14.9, "elapsed_time": "0:34:40", "remaining_time": "3:17:59"}
+{"current_steps": 270, "total_steps": 1778, "loss": 0.273, "lr": 3.968158990973881e-05, "epoch": 1.0631163708086786, "percentage": 15.19, "elapsed_time": "0:35:18", "remaining_time": "3:17:10"}
+{"current_steps": 275, "total_steps": 1778, "loss": 0.2679, "lr": 3.964574501457378e-05, "epoch": 1.0828402366863905, "percentage": 15.47, "elapsed_time": "0:35:56", "remaining_time": "3:16:28"}
+{"current_steps": 280, "total_steps": 1778, "loss": 0.2701, "lr": 3.960800662161469e-05, "epoch": 1.1025641025641026, "percentage": 15.75, "elapsed_time": "0:36:32", "remaining_time": "3:15:27"}
+{"current_steps": 285, "total_steps": 1778, "loss": 0.2671, "lr": 3.9568378368166406e-05, "epoch": 1.1222879684418146, "percentage": 16.03, "elapsed_time": "0:37:08", "remaining_time": "3:14:33"}
+{"current_steps": 290, "total_steps": 1778, "loss": 0.2664, "lr": 3.952686407368247e-05, "epoch": 1.1420118343195267, "percentage": 16.31, "elapsed_time": "0:37:44", "remaining_time": "3:13:41"}
+{"current_steps": 295, "total_steps": 1778, "loss": 0.2827, "lr": 3.948346773939699e-05, "epoch": 1.1617357001972386, "percentage": 16.59, "elapsed_time": "0:38:23", "remaining_time": "3:12:59"}
+{"current_steps": 300, "total_steps": 1778, "loss": 0.2644, "lr": 3.943819354793899e-05, "epoch": 1.1814595660749507, "percentage": 16.87, "elapsed_time": "0:39:00", "remaining_time": "3:12:10"}
+{"current_steps": 305, "total_steps": 1778, "loss": 0.2634, "lr": 3.9391045862929275e-05, "epoch": 1.2011834319526626, "percentage": 17.15, "elapsed_time": "0:39:40", "remaining_time": "3:11:35"}
+{"current_steps": 310, "total_steps": 1778, "loss": 0.2665, "lr": 3.934202922855985e-05, "epoch": 1.2209072978303748, "percentage": 17.44, "elapsed_time": "0:40:16", "remaining_time": "3:10:43"}
+{"current_steps": 315, "total_steps": 1778, "loss": 0.2636, "lr": 3.9291148369155964e-05, "epoch": 1.2406311637080867, "percentage": 17.72, "elapsed_time": "0:40:56", "remaining_time": "3:10:08"}
+{"current_steps": 320, "total_steps": 1778, "loss": 0.2697, "lr": 3.9238408188720745e-05, "epoch": 1.2603550295857988, "percentage": 18.0, "elapsed_time": "0:41:36", "remaining_time": "3:09:36"}
+{"current_steps": 325, "total_steps": 1778, "loss": 0.2671, "lr": 3.918381377046255e-05, "epoch": 1.280078895463511, "percentage": 18.28, "elapsed_time": "0:42:11", "remaining_time": "3:08:37"}
+{"current_steps": 330, "total_steps": 1778, "loss": 0.2647, "lr": 3.9127370376305045e-05, "epoch": 1.2998027613412229, "percentage": 18.56, "elapsed_time": "0:42:49", "remaining_time": "3:07:52"}
+{"current_steps": 335, "total_steps": 1778, "loss": 0.2691, "lr": 3.906908344638002e-05, "epoch": 1.319526627218935, "percentage": 18.84, "elapsed_time": "0:43:22", "remaining_time": "3:06:48"}
+{"current_steps": 340, "total_steps": 1778, "loss": 0.2606, "lr": 3.900895859850313e-05, "epoch": 1.339250493096647, "percentage": 19.12, "elapsed_time": "0:43:58", "remaining_time": "3:05:58"}
+{"current_steps": 345, "total_steps": 1778, "loss": 0.2617, "lr": 3.8947001627632326e-05, "epoch": 1.358974358974359, "percentage": 19.4, "elapsed_time": "0:44:40", "remaining_time": "3:05:34"}
+{"current_steps": 350, "total_steps": 1778, "loss": 0.2723, "lr": 3.888321850530943e-05, "epoch": 1.378698224852071, "percentage": 19.69, "elapsed_time": "0:45:20", "remaining_time": "3:04:58"}
+{"current_steps": 355, "total_steps": 1778, "loss": 0.2639, "lr": 3.8817615379084514e-05, "epoch": 1.398422090729783, "percentage": 19.97, "elapsed_time": "0:45:59", "remaining_time": "3:04:19"}
+{"current_steps": 360, "total_steps": 1778, "loss": 0.2661, "lr": 3.875019857192343e-05, "epoch": 1.418145956607495, "percentage": 20.25, "elapsed_time": "0:46:37", "remaining_time": "3:03:37"}
+{"current_steps": 365, "total_steps": 1778, "loss": 0.2713, "lr": 3.8680974581598375e-05, "epoch": 1.4378698224852071, "percentage": 20.53, "elapsed_time": "0:47:11", "remaining_time": "3:02:43"}
+{"current_steps": 370, "total_steps": 1778, "loss": 0.2798, "lr": 3.860995008006161e-05, "epoch": 1.4575936883629192, "percentage": 20.81, "elapsed_time": "0:47:51", "remaining_time": "3:02:06"}
+{"current_steps": 375, "total_steps": 1778, "loss": 0.2575, "lr": 3.853713191280242e-05, "epoch": 1.4773175542406312, "percentage": 21.09, "elapsed_time": "0:48:30", "remaining_time": "3:01:29"}
+{"current_steps": 380, "total_steps": 1778, "loss": 0.2563, "lr": 3.846252709818733e-05, "epoch": 1.497041420118343, "percentage": 21.37, "elapsed_time": "0:49:10", "remaining_time": "3:00:54"}
+{"current_steps": 385, "total_steps": 1778, "loss": 0.2643, "lr": 3.8386142826783645e-05, "epoch": 1.5167652859960552, "percentage": 21.65, "elapsed_time": "0:49:47", "remaining_time": "3:00:10"}
+{"current_steps": 390, "total_steps": 1778, "loss": 0.2619, "lr": 3.830798646066642e-05, "epoch": 1.5364891518737673, "percentage": 21.93, "elapsed_time": "0:50:22", "remaining_time": "2:59:16"}
+{"current_steps": 395, "total_steps": 1778, "loss": 0.265, "lr": 3.8228065532708905e-05, "epoch": 1.5562130177514792, "percentage": 22.22, "elapsed_time": "0:50:58", "remaining_time": "2:58:27"}
+{"current_steps": 400, "total_steps": 1778, "loss": 0.2565, "lr": 3.814638774585648e-05, "epoch": 1.5759368836291914, "percentage": 22.5, "elapsed_time": "0:51:33", "remaining_time": "2:57:35"}
+{"current_steps": 405, "total_steps": 1778, "loss": 0.2552, "lr": 3.8062960972384223e-05, "epoch": 1.5956607495069033, "percentage": 22.78, "elapsed_time": "0:52:10", "remaining_time": "2:56:53"}
+{"current_steps": 410, "total_steps": 1778, "loss": 0.259, "lr": 3.797779325313822e-05, "epoch": 1.6153846153846154, "percentage": 23.06, "elapsed_time": "0:52:49", "remaining_time": "2:56:14"}
+{"current_steps": 415, "total_steps": 1778, "loss": 0.261, "lr": 3.78908927967605e-05, "epoch": 1.6351084812623276, "percentage": 23.34, "elapsed_time": "0:53:21", "remaining_time": "2:55:15"}
+{"current_steps": 420, "total_steps": 1778, "loss": 0.2551, "lr": 3.780226797889794e-05, "epoch": 1.6548323471400395, "percentage": 23.62, "elapsed_time": "0:53:59", "remaining_time": "2:54:34"}
+{"current_steps": 425, "total_steps": 1778, "loss": 0.2623, "lr": 3.7711927341394916e-05, "epoch": 1.6745562130177514, "percentage": 23.9, "elapsed_time": "0:54:38", "remaining_time": "2:53:57"}
+{"current_steps": 430, "total_steps": 1778, "loss": 0.2659, "lr": 3.761987959147012e-05, "epoch": 1.6942800788954635, "percentage": 24.18, "elapsed_time": "0:55:15", "remaining_time": "2:53:13"}
+{"current_steps": 435, "total_steps": 1778, "loss": 0.2624, "lr": 3.7526133600877275e-05, "epoch": 1.7140039447731756, "percentage": 24.47, "elapsed_time": "0:55:51", "remaining_time": "2:52:28"}
+{"current_steps": 440, "total_steps": 1778, "loss": 0.2561, "lr": 3.743069840505006e-05, "epoch": 1.7337278106508875, "percentage": 24.75, "elapsed_time": "0:56:30", "remaining_time": "2:51:51"}
+{"current_steps": 445, "total_steps": 1778, "loss": 0.2555, "lr": 3.733358320223128e-05, "epoch": 1.7534516765285995, "percentage": 25.03, "elapsed_time": "0:57:09", "remaining_time": "2:51:12"}
+{"current_steps": 450, "total_steps": 1778, "loss": 0.2527, "lr": 3.723479735258633e-05, "epoch": 1.7731755424063116, "percentage": 25.31, "elapsed_time": "0:57:50", "remaining_time": "2:50:41"}
+{"current_steps": 455, "total_steps": 1778, "loss": 0.2542, "lr": 3.7134350377301e-05, "epoch": 1.7928994082840237, "percentage": 25.59, "elapsed_time": "0:58:28", "remaining_time": "2:50:00"}
+{"current_steps": 460, "total_steps": 1778, "loss": 0.2688, "lr": 3.703225195766382e-05, "epoch": 1.8126232741617359, "percentage": 25.87, "elapsed_time": "0:59:07", "remaining_time": "2:49:23"}
+{"current_steps": 465, "total_steps": 1778, "loss": 0.2556, "lr": 3.692851193413299e-05, "epoch": 1.8323471400394478, "percentage": 26.15, "elapsed_time": "0:59:44", "remaining_time": "2:48:41"}
+{"current_steps": 470, "total_steps": 1778, "loss": 0.2518, "lr": 3.682314030538788e-05, "epoch": 1.8520710059171597, "percentage": 26.43, "elapsed_time": "1:00:22", "remaining_time": "2:48:02"}
+{"current_steps": 475, "total_steps": 1778, "loss": 0.2529, "lr": 3.671614722736541e-05, "epoch": 1.8717948717948718, "percentage": 26.72, "elapsed_time": "1:00:59", "remaining_time": "2:47:18"}
+{"current_steps": 480, "total_steps": 1778, "loss": 0.251, "lr": 3.6607543012281106e-05, "epoch": 1.891518737672584, "percentage": 27.0, "elapsed_time": "1:01:39", "remaining_time": "2:46:43"}
+{"current_steps": 485, "total_steps": 1778, "loss": 0.2598, "lr": 3.649733812763527e-05, "epoch": 1.9112426035502958, "percentage": 27.28, "elapsed_time": "1:02:19", "remaining_time": "2:46:09"}
+{"current_steps": 490, "total_steps": 1778, "loss": 0.2648, "lr": 3.638554319520406e-05, "epoch": 1.9309664694280078, "percentage": 27.56, "elapsed_time": "1:02:58", "remaining_time": "2:45:31"}
+{"current_steps": 495, "total_steps": 1778, "loss": 0.2617, "lr": 3.627216899001575e-05, "epoch": 1.95069033530572, "percentage": 27.84, "elapsed_time": "1:03:37", "remaining_time": "2:44:54"}
+{"current_steps": 500, "total_steps": 1778, "loss": 0.2519, "lr": 3.6157226439312186e-05, "epoch": 1.970414201183432, "percentage": 28.12, "elapsed_time": "1:04:16", "remaining_time": "2:44:17"}
+{"current_steps": 505, "total_steps": 1778, "loss": 0.261, "lr": 3.604072662149567e-05, "epoch": 1.990138067061144, "percentage": 28.4, "elapsed_time": "1:04:56", "remaining_time": "2:43:41"}
+{"current_steps": 510, "total_steps": 1778, "loss": 0.2585, "lr": 3.5922680765061096e-05, "epoch": 2.007889546351085, "percentage": 28.68, "elapsed_time": "1:05:27", "remaining_time": "2:42:45"}
+{"current_steps": 515, "total_steps": 1778, "loss": 0.2458, "lr": 3.580310024751381e-05, "epoch": 2.027613412228797, "percentage": 28.97, "elapsed_time": "1:06:07", "remaining_time": "2:42:09"}
+{"current_steps": 520, "total_steps": 1778, "loss": 0.2454, "lr": 3.568199659427298e-05, "epoch": 2.0473372781065087, "percentage": 29.25, "elapsed_time": "1:06:47", "remaining_time": "2:41:35"}
+{"current_steps": 525, "total_steps": 1778, "loss": 0.2447, "lr": 3.555938147756077e-05, "epoch": 2.067061143984221, "percentage": 29.53, "elapsed_time": "1:07:26", "remaining_time": "2:40:58"}
+{"current_steps": 530, "total_steps": 1778, "loss": 0.2428, "lr": 3.543526671527733e-05, "epoch": 2.086785009861933, "percentage": 29.81, "elapsed_time": "1:08:05", "remaining_time": "2:40:20"}
+{"current_steps": 535, "total_steps": 1778, "loss": 0.24, "lr": 3.530966426986177e-05, "epoch": 2.106508875739645, "percentage": 30.09, "elapsed_time": "1:08:39", "remaining_time": "2:39:32"}
+{"current_steps": 540, "total_steps": 1778, "loss": 0.2463, "lr": 3.51825862471392e-05, "epoch": 2.126232741617357, "percentage": 30.37, "elapsed_time": "1:09:16", "remaining_time": "2:38:49"}
+{"current_steps": 545, "total_steps": 1778, "loss": 0.2469, "lr": 3.505404489515394e-05, "epoch": 2.145956607495069, "percentage": 30.65, "elapsed_time": "1:09:54", "remaining_time": "2:38:08"}
+{"current_steps": 550, "total_steps": 1778, "loss": 0.2438, "lr": 3.492405260298905e-05, "epoch": 2.165680473372781, "percentage": 30.93, "elapsed_time": "1:10:30", "remaining_time": "2:37:25"}
+{"current_steps": 555, "total_steps": 1778, "loss": 0.2426, "lr": 3.47926218995722e-05, "epoch": 2.185404339250493, "percentage": 31.21, "elapsed_time": "1:11:08", "remaining_time": "2:36:45"}
+{"current_steps": 560, "total_steps": 1778, "loss": 0.2395, "lr": 3.465976545246813e-05, "epoch": 2.2051282051282053, "percentage": 31.5, "elapsed_time": "1:11:43", "remaining_time": "2:36:00"}
+{"current_steps": 565, "total_steps": 1778, "loss": 0.2452, "lr": 3.4525496066657735e-05, "epoch": 2.224852071005917, "percentage": 31.78, "elapsed_time": "1:12:22", "remaining_time": "2:35:23"}
+{"current_steps": 570, "total_steps": 1778, "loss": 0.249, "lr": 3.438982668330388e-05, "epoch": 2.244575936883629, "percentage": 32.06, "elapsed_time": "1:13:01", "remaining_time": "2:34:46"}
+{"current_steps": 575, "total_steps": 1778, "loss": 0.2425, "lr": 3.425277037850411e-05, "epoch": 2.2642998027613412, "percentage": 32.34, "elapsed_time": "1:13:42", "remaining_time": "2:34:12"}
+{"current_steps": 580, "total_steps": 1778, "loss": 0.2432, "lr": 3.411434036203035e-05, "epoch": 2.2840236686390534, "percentage": 32.62, "elapsed_time": "1:14:19", "remaining_time": "2:33:31"}
+{"current_steps": 585, "total_steps": 1778, "loss": 0.2552, "lr": 3.397454997605569e-05, "epoch": 2.3037475345167655, "percentage": 32.9, "elapsed_time": "1:15:03", "remaining_time": "2:33:03"}
+{"current_steps": 590, "total_steps": 1778, "loss": 0.2494, "lr": 3.38334126938685e-05, "epoch": 2.323471400394477, "percentage": 33.18, "elapsed_time": "1:15:38", "remaining_time": "2:32:18"}
+{"current_steps": 595, "total_steps": 1778, "loss": 0.2524, "lr": 3.369094211857378e-05, "epoch": 2.3431952662721893, "percentage": 33.46, "elapsed_time": "1:16:18", "remaining_time": "2:31:42"}
+{"current_steps": 600, "total_steps": 1778, "loss": 0.2347, "lr": 3.354715198178211e-05, "epoch": 2.3629191321499015, "percentage": 33.75, "elapsed_time": "1:16:57", "remaining_time": "2:31:06"}
+{"current_steps": 605, "total_steps": 1778, "loss": 0.2522, "lr": 3.3402056142286156e-05, "epoch": 2.3826429980276136, "percentage": 34.03, "elapsed_time": "1:17:32", "remaining_time": "2:30:20"}
+{"current_steps": 610, "total_steps": 1778, "loss": 0.2431, "lr": 3.3255668584724916e-05, "epoch": 2.4023668639053253, "percentage": 34.31, "elapsed_time": "1:18:07", "remaining_time": "2:29:36"}
+{"current_steps": 615, "total_steps": 1778, "loss": 0.2425, "lr": 3.310800341823588e-05, "epoch": 2.4220907297830374, "percentage": 34.59, "elapsed_time": "1:18:42", "remaining_time": "2:28:49"}
+{"current_steps": 620, "total_steps": 1778, "loss": 0.2394, "lr": 3.2959074875095125e-05, "epoch": 2.4418145956607495, "percentage": 34.87, "elapsed_time": "1:19:19", "remaining_time": "2:28:09"}
+{"current_steps": 625, "total_steps": 1778, "loss": 0.2472, "lr": 3.280889730934562e-05, "epoch": 2.4615384615384617, "percentage": 35.15, "elapsed_time": "1:19:57", "remaining_time": "2:27:30"}
+{"current_steps": 630, "total_steps": 1778, "loss": 0.2382, "lr": 3.265748519541372e-05, "epoch": 2.4812623274161734, "percentage": 35.43, "elapsed_time": "1:20:32", "remaining_time": "2:26:46"}
+{"current_steps": 635, "total_steps": 1778, "loss": 0.2441, "lr": 3.250485312671411e-05, "epoch": 2.5009861932938855, "percentage": 35.71, "elapsed_time": "1:21:12", "remaining_time": "2:26:10"}
+{"current_steps": 640, "total_steps": 1778, "loss": 0.2472, "lr": 3.2351015814243235e-05, "epoch": 2.5207100591715976, "percentage": 36.0, "elapsed_time": "1:21:52", "remaining_time": "2:25:35"}
+{"current_steps": 645, "total_steps": 1778, "loss": 0.2422, "lr": 3.219598808516148e-05, "epoch": 2.5404339250493098, "percentage": 36.28, "elapsed_time": "1:22:29", "remaining_time": "2:24:54"}
+{"current_steps": 650, "total_steps": 1778, "loss": 0.2446, "lr": 3.203978488136403e-05, "epoch": 2.560157790927022, "percentage": 36.56, "elapsed_time": "1:23:08", "remaining_time": "2:24:17"}
+{"current_steps": 655, "total_steps": 1778, "loss": 0.2387, "lr": 3.188242125804078e-05, "epoch": 2.5798816568047336, "percentage": 36.84, "elapsed_time": "1:23:46", "remaining_time": "2:23:38"}
+{"current_steps": 660, "total_steps": 1778, "loss": 0.241, "lr": 3.1723912382225267e-05, "epoch": 2.5996055226824457, "percentage": 37.12, "elapsed_time": "1:24:26", "remaining_time": "2:23:01"}
+{"current_steps": 665, "total_steps": 1778, "loss": 0.238, "lr": 3.156427353133286e-05, "epoch": 2.619329388560158, "percentage": 37.4, "elapsed_time": "1:25:01", "remaining_time": "2:22:18"}
+{"current_steps": 670, "total_steps": 1778, "loss": 0.2448, "lr": 3.140352009168828e-05, "epoch": 2.63905325443787, "percentage": 37.68, "elapsed_time": "1:25:38", "remaining_time": "2:21:37"}
+{"current_steps": 675, "total_steps": 1778, "loss": 0.2351, "lr": 3.124166755704261e-05, "epoch": 2.658777120315582, "percentage": 37.96, "elapsed_time": "1:26:14", "remaining_time": "2:20:54"}
+{"current_steps": 680, "total_steps": 1778, "loss": 0.251, "lr": 3.1078731527080023e-05, "epoch": 2.678500986193294, "percentage": 38.25, "elapsed_time": "1:26:55", "remaining_time": "2:20:21"}
+{"current_steps": 685, "total_steps": 1778, "loss": 0.251, "lr": 3.09147277059142e-05, "epoch": 2.698224852071006, "percentage": 38.53, "elapsed_time": "1:27:28", "remaining_time": "2:19:34"}
+{"current_steps": 690, "total_steps": 1778, "loss": 0.2392, "lr": 3.074967190057478e-05, "epoch": 2.717948717948718, "percentage": 38.81, "elapsed_time": "1:28:07", "remaining_time": "2:18:56"}
+{"current_steps": 695, "total_steps": 1778, "loss": 0.2501, "lr": 3.058358001948381e-05, "epoch": 2.7376725838264298, "percentage": 39.09, "elapsed_time": "1:28:46", "remaining_time": "2:18:19"}
+{"current_steps": 700, "total_steps": 1778, "loss": 0.2396, "lr": 3.0416468070922504e-05, "epoch": 2.757396449704142, "percentage": 39.37, "elapsed_time": "1:29:25", "remaining_time": "2:17:43"}
+{"current_steps": 705, "total_steps": 1778, "loss": 0.2343, "lr": 3.0248352161488267e-05, "epoch": 2.777120315581854, "percentage": 39.65, "elapsed_time": "1:30:02", "remaining_time": "2:17:02"}
+{"current_steps": 710, "total_steps": 1778, "loss": 0.2439, "lr": 3.007924849454235e-05, "epoch": 2.796844181459566, "percentage": 39.93, "elapsed_time": "1:30:43", "remaining_time": "2:16:27"}
+{"current_steps": 715, "total_steps": 1778, "loss": 0.2367, "lr": 2.9909173368648154e-05, "epoch": 2.8165680473372783, "percentage": 40.21, "elapsed_time": "1:31:19", "remaining_time": "2:15:45"}
+{"current_steps": 720, "total_steps": 1778, "loss": 0.2516, "lr": 2.9738143176000287e-05, "epoch": 2.83629191321499, "percentage": 40.49, "elapsed_time": "1:31:54", "remaining_time": "2:15:03"}
+{"current_steps": 725, "total_steps": 1778, "loss": 0.2587, "lr": 2.9566174400844692e-05, "epoch": 2.856015779092702, "percentage": 40.78, "elapsed_time": "1:32:30", "remaining_time": "2:14:21"}
+{"current_steps": 730, "total_steps": 1778, "loss": 0.2449, "lr": 2.9393283617889846e-05, "epoch": 2.8757396449704142, "percentage": 41.06, "elapsed_time": "1:33:07", "remaining_time": "2:13:41"}
+{"current_steps": 735, "total_steps": 1778, "loss": 0.2386, "lr": 2.921948749070925e-05, "epoch": 2.8954635108481264, "percentage": 41.34, "elapsed_time": "1:33:46", "remaining_time": "2:13:04"}
+{"current_steps": 740, "total_steps": 1778, "loss": 0.241, "lr": 2.9044802770135375e-05, "epoch": 2.9151873767258385, "percentage": 41.62, "elapsed_time": "1:34:23", "remaining_time": "2:12:23"}
+{"current_steps": 745, "total_steps": 1778, "loss": 0.2385, "lr": 2.886924629264517e-05, "epoch": 2.93491124260355, "percentage": 41.9, "elapsed_time": "1:35:01", "remaining_time": "2:11:45"}
+{"current_steps": 750, "total_steps": 1778, "loss": 0.2317, "lr": 2.8692834978737328e-05, "epoch": 2.9546351084812623, "percentage": 42.18, "elapsed_time": "1:35:39", "remaining_time": "2:11:06"}
+{"current_steps": 755, "total_steps": 1778, "loss": 0.2539, "lr": 2.8515585831301456e-05, "epoch": 2.9743589743589745, "percentage": 42.46, "elapsed_time": "1:36:18", "remaining_time": "2:10:29"}
+{"current_steps": 760, "total_steps": 1778, "loss": 0.2424, "lr": 2.83375159339793e-05, "epoch": 2.994082840236686, "percentage": 42.74, "elapsed_time": "1:36:57", "remaining_time": "2:09:52"}
+{"current_steps": 765, "total_steps": 1778, "loss": 0.2358, "lr": 2.8158642449518186e-05, "epoch": 3.0118343195266273, "percentage": 43.03, "elapsed_time": "1:37:35", "remaining_time": "2:09:13"}
+{"current_steps": 770, "total_steps": 1778, "loss": 0.2283, "lr": 2.797898261811685e-05, "epoch": 3.0315581854043394, "percentage": 43.31, "elapsed_time": "1:38:16", "remaining_time": "2:08:38"}
+{"current_steps": 775, "total_steps": 1778, "loss": 0.2274, "lr": 2.7798553755763768e-05, "epoch": 3.051282051282051, "percentage": 43.59, "elapsed_time": "1:38:54", "remaining_time": "2:08:00"}
+{"current_steps": 780, "total_steps": 1778, "loss": 0.2293, "lr": 2.7617373252568237e-05, "epoch": 3.0710059171597632, "percentage": 43.87, "elapsed_time": "1:39:33", "remaining_time": "2:07:22"}
+{"current_steps": 785, "total_steps": 1778, "loss": 0.2276, "lr": 2.7435458571084247e-05, "epoch": 3.0907297830374754, "percentage": 44.15, "elapsed_time": "1:40:13", "remaining_time": "2:06:46"}
+{"current_steps": 790, "total_steps": 1778, "loss": 0.2243, "lr": 2.725282724462743e-05, "epoch": 3.1104536489151875, "percentage": 44.43, "elapsed_time": "1:40:48", "remaining_time": "2:06:04"}
+{"current_steps": 795, "total_steps": 1778, "loss": 0.2306, "lr": 2.7069496875585145e-05, "epoch": 3.1301775147928996, "percentage": 44.71, "elapsed_time": "1:41:24", "remaining_time": "2:05:23"}
+{"current_steps": 800, "total_steps": 1778, "loss": 0.2308, "lr": 2.688548513371994e-05, "epoch": 3.1499013806706113, "percentage": 44.99, "elapsed_time": "1:42:03", "remaining_time": "2:04:45"}
+{"current_steps": 805, "total_steps": 1778, "loss": 0.2294, "lr": 2.670080975446648e-05, "epoch": 3.1696252465483234, "percentage": 45.28, "elapsed_time": "1:42:39", "remaining_time": "2:04:04"}
+{"current_steps": 810, "total_steps": 1778, "loss": 0.2246, "lr": 2.6515488537222198e-05, "epoch": 3.1893491124260356, "percentage": 45.56, "elapsed_time": "1:43:13", "remaining_time": "2:03:21"}
+{"current_steps": 815, "total_steps": 1778, "loss": 0.2249, "lr": 2.6329539343631725e-05, "epoch": 3.2090729783037477, "percentage": 45.84, "elapsed_time": "1:43:52", "remaining_time": "2:02:44"}
+{"current_steps": 820, "total_steps": 1778, "loss": 0.2345, "lr": 2.614298009586536e-05, "epoch": 3.2287968441814594, "percentage": 46.12, "elapsed_time": "1:44:31", "remaining_time": "2:02:06"}
+{"current_steps": 825, "total_steps": 1778, "loss": 0.2322, "lr": 2.595582877489171e-05, "epoch": 3.2485207100591715, "percentage": 46.4, "elapsed_time": "1:45:10", "remaining_time": "2:01:29"}
+{"current_steps": 830, "total_steps": 1778, "loss": 0.2253, "lr": 2.57681034187446e-05, "epoch": 3.2682445759368837, "percentage": 46.68, "elapsed_time": "1:45:47", "remaining_time": "2:00:49"}
+{"current_steps": 835, "total_steps": 1778, "loss": 0.2255, "lr": 2.557982212078459e-05, "epoch": 3.287968441814596, "percentage": 46.96, "elapsed_time": "1:46:25", "remaining_time": "2:00:11"}
+{"current_steps": 840, "total_steps": 1778, "loss": 0.2336, "lr": 2.5391003027955045e-05, "epoch": 3.3076923076923075, "percentage": 47.24, "elapsed_time": "1:46:59", "remaining_time": "1:59:28"}
+{"current_steps": 845, "total_steps": 1778, "loss": 0.2356, "lr": 2.5201664339033138e-05, "epoch": 3.3274161735700196, "percentage": 47.53, "elapsed_time": "1:47:35", "remaining_time": "1:58:48"}
+{"current_steps": 850, "total_steps": 1778, "loss": 0.2301, "lr": 2.501182430287578e-05, "epoch": 3.3471400394477318, "percentage": 47.81, "elapsed_time": "1:48:12", "remaining_time": "1:58:08"}
+{"current_steps": 855, "total_steps": 1778, "loss": 0.2354, "lr": 2.4821501216660778e-05, "epoch": 3.366863905325444, "percentage": 48.09, "elapsed_time": "1:48:52", "remaining_time": "1:57:31"}
+{"current_steps": 860, "total_steps": 1778, "loss": 0.2349, "lr": 2.4630713424123315e-05, "epoch": 3.386587771203156, "percentage": 48.37, "elapsed_time": "1:49:28", "remaining_time": "1:56:51"}
+{"current_steps": 865, "total_steps": 1778, "loss": 0.2352, "lr": 2.443947931378792e-05, "epoch": 3.4063116370808677, "percentage": 48.65, "elapsed_time": "1:50:05", "remaining_time": "1:56:11"}
+{"current_steps": 870, "total_steps": 1778, "loss": 0.2259, "lr": 2.4247817317196188e-05, "epoch": 3.42603550295858, "percentage": 48.93, "elapsed_time": "1:50:41", "remaining_time": "1:55:31"}
+{"current_steps": 875, "total_steps": 1778, "loss": 0.2315, "lr": 2.405574590713025e-05, "epoch": 3.445759368836292, "percentage": 49.21, "elapsed_time": "1:51:16", "remaining_time": "1:54:50"}
+{"current_steps": 880, "total_steps": 1778, "loss": 0.2377, "lr": 2.3863283595832387e-05, "epoch": 3.465483234714004, "percentage": 49.49, "elapsed_time": "1:51:54", "remaining_time": "1:54:11"}
+{"current_steps": 885, "total_steps": 1778, "loss": 0.2314, "lr": 2.3670448933220732e-05, "epoch": 3.485207100591716, "percentage": 49.78, "elapsed_time": "1:52:29", "remaining_time": "1:53:30"}
+{"current_steps": 890, "total_steps": 1778, "loss": 0.2392, "lr": 2.3477260505101427e-05, "epoch": 3.504930966469428, "percentage": 50.06, "elapsed_time": "1:53:07", "remaining_time": "1:52:51"}
+{"current_steps": 895, "total_steps": 1778, "loss": 0.2393, "lr": 2.328373693137726e-05, "epoch": 3.52465483234714, "percentage": 50.34, "elapsed_time": "1:53:50", "remaining_time": "1:52:18"}
+{"current_steps": 900, "total_steps": 1778, "loss": 0.233, "lr": 2.3089896864253066e-05, "epoch": 3.544378698224852, "percentage": 50.62, "elapsed_time": "1:54:29", "remaining_time": "1:51:41"}
+{"current_steps": 905, "total_steps": 1778, "loss": 0.2285, "lr": 2.289575898643796e-05, "epoch": 3.564102564102564, "percentage": 50.9, "elapsed_time": "1:55:02", "remaining_time": "1:50:58"}
+{"current_steps": 910, "total_steps": 1778, "loss": 0.227, "lr": 2.270134200934466e-05, "epoch": 3.583826429980276, "percentage": 51.18, "elapsed_time": "1:55:37", "remaining_time": "1:50:17"}
+{"current_steps": 915, "total_steps": 1778, "loss": 0.2304, "lr": 2.2506664671286087e-05, "epoch": 3.603550295857988, "percentage": 51.46, "elapsed_time": "1:56:15", "remaining_time": "1:49:38"}
+{"current_steps": 920, "total_steps": 1778, "loss": 0.2307, "lr": 2.2311745735669258e-05, "epoch": 3.6232741617357003, "percentage": 51.74, "elapsed_time": "1:56:54", "remaining_time": "1:49:01"}
+{"current_steps": 925, "total_steps": 1778, "loss": 0.2261, "lr": 2.2116603989186895e-05, "epoch": 3.6429980276134124, "percentage": 52.02, "elapsed_time": "1:57:31", "remaining_time": "1:48:22"}
+{"current_steps": 930, "total_steps": 1778, "loss": 0.2301, "lr": 2.192125824000667e-05, "epoch": 3.662721893491124, "percentage": 52.31, "elapsed_time": "1:58:09", "remaining_time": "1:47:44"}
+{"current_steps": 935, "total_steps": 1778, "loss": 0.223, "lr": 2.1725727315958473e-05, "epoch": 3.6824457593688362, "percentage": 52.59, "elapsed_time": "1:58:43", "remaining_time": "1:47:02"}
+{"current_steps": 940, "total_steps": 1778, "loss": 0.2291, "lr": 2.1530030062719724e-05, "epoch": 3.7021696252465484, "percentage": 52.87, "elapsed_time": "1:59:20", "remaining_time": "1:46:23"}
+{"current_steps": 945, "total_steps": 1778, "loss": 0.23, "lr": 2.1334185341999024e-05, "epoch": 3.7218934911242605, "percentage": 53.15, "elapsed_time": "1:59:58", "remaining_time": "1:45:45"}
+{"current_steps": 950, "total_steps": 1778, "loss": 0.2239, "lr": 2.1138212029718158e-05, "epoch": 3.7416173570019726, "percentage": 53.43, "elapsed_time": "2:00:37", "remaining_time": "1:45:08"}
+{"current_steps": 955, "total_steps": 1778, "loss": 0.2318, "lr": 2.0942129014192854e-05, "epoch": 3.7613412228796843, "percentage": 53.71, "elapsed_time": "2:01:14", "remaining_time": "1:44:28"}
+{"current_steps": 960, "total_steps": 1778, "loss": 0.2269, "lr": 2.0745955194312276e-05, "epoch": 3.7810650887573964, "percentage": 53.99, "elapsed_time": "2:01:53", "remaining_time": "1:43:52"}
+{"current_steps": 965, "total_steps": 1778, "loss": 0.2226, "lr": 2.054970947771747e-05, "epoch": 3.8007889546351086, "percentage": 54.27, "elapsed_time": "2:02:31", "remaining_time": "1:43:13"}
+{"current_steps": 970, "total_steps": 1778, "loss": 0.2323, "lr": 2.0353410778979076e-05, "epoch": 3.8205128205128203, "percentage": 54.56, "elapsed_time": "2:03:11", "remaining_time": "1:42:37"}
+{"current_steps": 975, "total_steps": 1778, "loss": 0.2304, "lr": 2.0157078017774228e-05, "epoch": 3.8402366863905324, "percentage": 54.84, "elapsed_time": "2:03:51", "remaining_time": "1:42:00"}
+{"current_steps": 980, "total_steps": 1778, "loss": 0.2267, "lr": 1.99607301170631e-05, "epoch": 3.8599605522682445, "percentage": 55.12, "elapsed_time": "2:04:31", "remaining_time": "1:41:23"}
+{"current_steps": 985, "total_steps": 1778, "loss": 0.226, "lr": 1.9764386001265015e-05, "epoch": 3.8796844181459567, "percentage": 55.4, "elapsed_time": "2:05:05", "remaining_time": "1:40:42"}
+{"current_steps": 990, "total_steps": 1778, "loss": 0.2238, "lr": 1.956806459443453e-05, "epoch": 3.899408284023669, "percentage": 55.68, "elapsed_time": "2:05:45", "remaining_time": "1:40:05"}
+{"current_steps": 995, "total_steps": 1778, "loss": 0.2322, "lr": 1.9371784818437436e-05, "epoch": 3.9191321499013805, "percentage": 55.96, "elapsed_time": "2:06:24", "remaining_time": "1:39:28"}
+{"current_steps": 1000, "total_steps": 1778, "loss": 0.2264, "lr": 1.9175565591127073e-05, "epoch": 3.9388560157790926, "percentage": 56.24, "elapsed_time": "2:06:59", "remaining_time": "1:38:47"}
+{"current_steps": 1005, "total_steps": 1778, "loss": 0.2236, "lr": 1.897942582452097e-05, "epoch": 3.9585798816568047, "percentage": 56.52, "elapsed_time": "2:07:38", "remaining_time": "1:38:10"}
+{"current_steps": 1010, "total_steps": 1778, "loss": 0.2296, "lr": 1.8783384422978066e-05, "epoch": 3.978303747534517, "percentage": 56.81, "elapsed_time": "2:08:16", "remaining_time": "1:37:32"}
+{"current_steps": 1015, "total_steps": 1778, "loss": 0.2276, "lr": 1.8587460281376673e-05, "epoch": 3.998027613412229, "percentage": 57.09, "elapsed_time": "2:08:51", "remaining_time": "1:36:52"}
+{"current_steps": 1020, "total_steps": 1778, "loss": 0.2155, "lr": 1.8391672283293333e-05, "epoch": 4.01577909270217, "percentage": 57.37, "elapsed_time": "2:09:23", "remaining_time": "1:36:09"}
+{"current_steps": 1025, "total_steps": 1778, "loss": 0.2192, "lr": 1.8196039299182818e-05, "epoch": 4.035502958579881, "percentage": 57.65, "elapsed_time": "2:10:02", "remaining_time": "1:35:31"}
+{"current_steps": 1030, "total_steps": 1778, "loss": 0.2131, "lr": 1.8000580184559315e-05, "epoch": 4.055226824457594, "percentage": 57.93, "elapsed_time": "2:10:37", "remaining_time": "1:34:51"}
+{"current_steps": 1035, "total_steps": 1778, "loss": 0.2107, "lr": 1.7805313778179095e-05, "epoch": 4.074950690335306, "percentage": 58.21, "elapsed_time": "2:11:13", "remaining_time": "1:34:12"}
+{"current_steps": 1040, "total_steps": 1778, "loss": 0.2119, "lr": 1.7610258900224843e-05, "epoch": 4.094674556213017, "percentage": 58.49, "elapsed_time": "2:11:56", "remaining_time": "1:33:37"}
+{"current_steps": 1045, "total_steps": 1778, "loss": 0.225, "lr": 1.741543435049165e-05, "epoch": 4.11439842209073, "percentage": 58.77, "elapsed_time": "2:12:32", "remaining_time": "1:32:58"}
+{"current_steps": 1050, "total_steps": 1778, "loss": 0.2297, "lr": 1.7220858906575126e-05, "epoch": 4.134122287968442, "percentage": 59.06, "elapsed_time": "2:13:12", "remaining_time": "1:32:21"}
+{"current_steps": 1055, "total_steps": 1778, "loss": 0.2153, "lr": 1.702655132206154e-05, "epoch": 4.153846153846154, "percentage": 59.34, "elapsed_time": "2:13:51", "remaining_time": "1:31:43"}
+{"current_steps": 1060, "total_steps": 1778, "loss": 0.2193, "lr": 1.6832530324720303e-05, "epoch": 4.173570019723866, "percentage": 59.62, "elapsed_time": "2:14:30", "remaining_time": "1:31:06"}
+{"current_steps": 1065, "total_steps": 1778, "loss": 0.2188, "lr": 1.6638814614698965e-05, "epoch": 4.193293885601578, "percentage": 59.9, "elapsed_time": "2:15:08", "remaining_time": "1:30:28"}
+{"current_steps": 1070, "total_steps": 1778, "loss": 0.2223, "lr": 1.6445422862720845e-05, "epoch": 4.21301775147929, "percentage": 60.18, "elapsed_time": "2:15:51", "remaining_time": "1:29:53"}
+{"current_steps": 1075, "total_steps": 1778, "loss": 0.2104, "lr": 1.6252373708285505e-05, "epoch": 4.232741617357002, "percentage": 60.46, "elapsed_time": "2:16:30", "remaining_time": "1:29:16"}
+{"current_steps": 1080, "total_steps": 1778, "loss": 0.2195, "lr": 1.6059685757872274e-05, "epoch": 4.252465483234714, "percentage": 60.74, "elapsed_time": "2:17:06", "remaining_time": "1:28:36"}
+{"current_steps": 1085, "total_steps": 1778, "loss": 0.213, "lr": 1.5867377583146836e-05, "epoch": 4.272189349112426, "percentage": 61.02, "elapsed_time": "2:17:45", "remaining_time": "1:27:59"}
+{"current_steps": 1090, "total_steps": 1778, "loss": 0.2219, "lr": 1.567546771917135e-05, "epoch": 4.291913214990138, "percentage": 61.3, "elapsed_time": "2:18:24", "remaining_time": "1:27:21"}
+{"current_steps": 1095, "total_steps": 1778, "loss": 0.2208, "lr": 1.548397466261793e-05, "epoch": 4.31163708086785, "percentage": 61.59, "elapsed_time": "2:19:01", "remaining_time": "1:26:42"}
+{"current_steps": 1100, "total_steps": 1778, "loss": 0.2083, "lr": 1.529291686998592e-05, "epoch": 4.331360946745562, "percentage": 61.87, "elapsed_time": "2:19:36", "remaining_time": "1:26:03"}
+{"current_steps": 1105, "total_steps": 1778, "loss": 0.2126, "lr": 1.5102312755823053e-05, "epoch": 4.351084812623274, "percentage": 62.15, "elapsed_time": "2:20:13", "remaining_time": "1:25:24"}
+{"current_steps": 1110, "total_steps": 1778, "loss": 0.2171, "lr": 1.4912180690950545e-05, "epoch": 4.370808678500986, "percentage": 62.43, "elapsed_time": "2:20:48", "remaining_time": "1:24:44"}
+{"current_steps": 1115, "total_steps": 1778, "loss": 0.2252, "lr": 1.4722539000692548e-05, "epoch": 4.390532544378698, "percentage": 62.71, "elapsed_time": "2:21:26", "remaining_time": "1:24:06"}
+{"current_steps": 1120, "total_steps": 1778, "loss": 0.219, "lr": 1.4533405963109867e-05, "epoch": 4.410256410256411, "percentage": 62.99, "elapsed_time": "2:22:07", "remaining_time": "1:23:29"}
+{"current_steps": 1125, "total_steps": 1778, "loss": 0.2151, "lr": 1.434479980723833e-05, "epoch": 4.429980276134122, "percentage": 63.27, "elapsed_time": "2:22:45", "remaining_time": "1:22:51"}
+{"current_steps": 1130, "total_steps": 1778, "loss": 0.22, "lr": 1.4156738711331793e-05, "epoch": 4.449704142011834, "percentage": 63.55, "elapsed_time": "2:23:24", "remaining_time": "1:22:14"}
+{"current_steps": 1135, "total_steps": 1778, "loss": 0.2184, "lr": 1.3969240801110088e-05, "epoch": 4.4694280078895465, "percentage": 63.84, "elapsed_time": "2:24:02", "remaining_time": "1:21:36"}
+{"current_steps": 1140, "total_steps": 1778, "loss": 0.2061, "lr": 1.3782324148012061e-05, "epoch": 4.489151873767258, "percentage": 64.12, "elapsed_time": "2:24:41", "remaining_time": "1:20:58"}
+{"current_steps": 1145, "total_steps": 1778, "loss": 0.2097, "lr": 1.3596006767453766e-05, "epoch": 4.508875739644971, "percentage": 64.4, "elapsed_time": "2:25:19", "remaining_time": "1:20:20"}
+{"current_steps": 1150, "total_steps": 1778, "loss": 0.2208, "lr": 1.3410306617092134e-05, "epoch": 4.5285996055226825, "percentage": 64.68, "elapsed_time": "2:25:56", "remaining_time": "1:19:41"}
+{"current_steps": 1155, "total_steps": 1778, "loss": 0.2194, "lr": 1.3225241595094173e-05, "epoch": 4.548323471400394, "percentage": 64.96, "elapsed_time": "2:26:34", "remaining_time": "1:19:03"}
+{"current_steps": 1160, "total_steps": 1778, "loss": 0.2252, "lr": 1.3040829538411876e-05, "epoch": 4.568047337278107, "percentage": 65.24, "elapsed_time": "2:27:10", "remaining_time": "1:18:24"}
+{"current_steps": 1165, "total_steps": 1778, "loss": 0.2233, "lr": 1.2857088221063099e-05, "epoch": 4.587771203155818, "percentage": 65.52, "elapsed_time": "2:27:46", "remaining_time": "1:17:45"}
+{"current_steps": 1170, "total_steps": 1778, "loss": 0.2157, "lr": 1.2674035352418425e-05, "epoch": 4.607495069033531, "percentage": 65.8, "elapsed_time": "2:28:22", "remaining_time": "1:17:06"}
+{"current_steps": 1175, "total_steps": 1778, "loss": 0.2181, "lr": 1.2491688575494337e-05, "epoch": 4.627218934911243, "percentage": 66.09, "elapsed_time": "2:28:57", "remaining_time": "1:16:26"}
+{"current_steps": 1180, "total_steps": 1778, "loss": 0.2184, "lr": 1.231006546525273e-05, "epoch": 4.646942800788954, "percentage": 66.37, "elapsed_time": "2:29:28", "remaining_time": "1:15:45"}
+{"current_steps": 1185, "total_steps": 1778, "loss": 0.2193, "lr": 1.2129183526906971e-05, "epoch": 4.666666666666667, "percentage": 66.65, "elapsed_time": "2:30:09", "remaining_time": "1:15:08"}
+{"current_steps": 1190, "total_steps": 1778, "loss": 0.2176, "lr": 1.1949060194234775e-05, "epoch": 4.686390532544379, "percentage": 66.93, "elapsed_time": "2:30:43", "remaining_time": "1:14:28"}
+{"current_steps": 1195, "total_steps": 1778, "loss": 0.2158, "lr": 1.1769712827897825e-05, "epoch": 4.706114398422091, "percentage": 67.21, "elapsed_time": "2:31:19", "remaining_time": "1:13:49"}
+{"current_steps": 1200, "total_steps": 1778, "loss": 0.2259, "lr": 1.159115871376858e-05, "epoch": 4.725838264299803, "percentage": 67.49, "elapsed_time": "2:31:59", "remaining_time": "1:13:12"}
+{"current_steps": 1205, "total_steps": 1778, "loss": 0.2151, "lr": 1.1413415061264205e-05, "epoch": 4.745562130177515, "percentage": 67.77, "elapsed_time": "2:32:33", "remaining_time": "1:12:32"}
+{"current_steps": 1210, "total_steps": 1778, "loss": 0.2149, "lr": 1.1236499001687853e-05, "epoch": 4.765285996055227, "percentage": 68.05, "elapsed_time": "2:33:08", "remaining_time": "1:11:53"}
+{"current_steps": 1215, "total_steps": 1778, "loss": 0.2255, "lr": 1.106042758657758e-05, "epoch": 4.785009861932939, "percentage": 68.34, "elapsed_time": "2:33:41", "remaining_time": "1:11:12"}
+{"current_steps": 1220, "total_steps": 1778, "loss": 0.2142, "lr": 1.0885217786062837e-05, "epoch": 4.804733727810651, "percentage": 68.62, "elapsed_time": "2:34:15", "remaining_time": "1:10:33"}
+{"current_steps": 1225, "total_steps": 1778, "loss": 0.2196, "lr": 1.0710886487228868e-05, "epoch": 4.824457593688363, "percentage": 68.9, "elapsed_time": "2:34:54", "remaining_time": "1:09:55"}
+{"current_steps": 1230, "total_steps": 1778, "loss": 0.2187, "lr": 1.053745049248911e-05, "epoch": 4.844181459566075, "percentage": 69.18, "elapsed_time": "2:35:34", "remaining_time": "1:09:19"}
+{"current_steps": 1235, "total_steps": 1778, "loss": 0.2169, "lr": 1.0364926517965693e-05, "epoch": 4.8639053254437865, "percentage": 69.46, "elapsed_time": "2:36:12", "remaining_time": "1:08:40"}
+{"current_steps": 1240, "total_steps": 1778, "loss": 0.2271, "lr": 1.0193331191878388e-05, "epoch": 4.883629191321499, "percentage": 69.74, "elapsed_time": "2:36:48", "remaining_time": "1:08:02"}
+{"current_steps": 1245, "total_steps": 1778, "loss": 0.2081, "lr": 1.0022681052941856e-05, "epoch": 4.903353057199211, "percentage": 70.02, "elapsed_time": "2:37:25", "remaining_time": "1:07:23"}
+{"current_steps": 1250, "total_steps": 1778, "loss": 0.2158, "lr": 9.852992548771674e-06, "epoch": 4.923076923076923, "percentage": 70.3, "elapsed_time": "2:38:04", "remaining_time": "1:06:46"}
+{"current_steps": 1255, "total_steps": 1778, "loss": 0.2174, "lr": 9.684282034299053e-06, "epoch": 4.942800788954635, "percentage": 70.58, "elapsed_time": "2:38:40", "remaining_time": "1:06:07"}
+{"current_steps": 1260, "total_steps": 1778, "loss": 0.2173, "lr": 9.516565770194523e-06, "epoch": 4.962524654832347, "percentage": 70.87, "elapsed_time": "2:39:19", "remaining_time": "1:05:29"}
+{"current_steps": 1265, "total_steps": 1778, "loss": 0.2138, "lr": 9.349859921300704e-06, "epoch": 4.982248520710059, "percentage": 71.15, "elapsed_time": "2:39:59", "remaining_time": "1:04:52"}
+{"current_steps": 1270, "total_steps": 1778, "loss": 0.2158, "lr": 9.184180555074258e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "2:40:32", "remaining_time": "1:04:12"}
+{"current_steps": 1275, "total_steps": 1778, "loss": 0.203, "lr": 9.019543640037363e-06, "epoch": 5.019723865877712, "percentage": 71.71, "elapsed_time": "2:41:11", "remaining_time": "1:03:35"}
+{"current_steps": 1280, "total_steps": 1778, "loss": 0.2054, "lr": 8.855965044238554e-06, "epoch": 5.039447731755424, "percentage": 71.99, "elapsed_time": "2:41:53", "remaining_time": "1:02:58"}
+{"current_steps": 1285, "total_steps": 1778, "loss": 0.2057, "lr": 8.693460533723346e-06, "epoch": 5.059171597633136, "percentage": 72.27, "elapsed_time": "2:42:31", "remaining_time": "1:02:21"}
+{"current_steps": 1290, "total_steps": 1778, "loss": 0.2028, "lr": 8.532045771014693e-06, "epoch": 5.0788954635108485, "percentage": 72.55, "elapsed_time": "2:43:09", "remaining_time": "1:01:43"}
+{"current_steps": 1295, "total_steps": 1778, "loss": 0.2084, "lr": 8.37173631360339e-06, "epoch": 5.09861932938856, "percentage": 72.83, "elapsed_time": "2:43:46", "remaining_time": "1:01:04"}
+{"current_steps": 1300, "total_steps": 1778, "loss": 0.215, "lr": 8.212547612448595e-06, "epoch": 5.118343195266272, "percentage": 73.12, "elapsed_time": "2:44:27", "remaining_time": "1:00:28"}
+{"current_steps": 1305, "total_steps": 1778, "loss": 0.2095, "lr": 8.054495010488658e-06, "epoch": 5.1380670611439845, "percentage": 73.4, "elapsed_time": "2:45:08", "remaining_time": "0:59:51"}
+{"current_steps": 1310, "total_steps": 1778, "loss": 0.2069, "lr": 7.897593741162316e-06, "epoch": 5.157790927021696, "percentage": 73.68, "elapsed_time": "2:45:50", "remaining_time": "0:59:14"}
+{"current_steps": 1315, "total_steps": 1778, "loss": 0.21, "lr": 7.741858926940475e-06, "epoch": 5.177514792899408, "percentage": 73.96, "elapsed_time": "2:46:26", "remaining_time": "0:58:36"}
+{"current_steps": 1320, "total_steps": 1778, "loss": 0.2136, "lr": 7.587305577868658e-06, "epoch": 5.19723865877712, "percentage": 74.24, "elapsed_time": "2:47:03", "remaining_time": "0:57:57"}
+{"current_steps": 1325, "total_steps": 1778, "loss": 0.2021, "lr": 7.433948590120326e-06, "epoch": 5.216962524654832, "percentage": 74.52, "elapsed_time": "2:47:39", "remaining_time": "0:57:19"}
+{"current_steps": 1330, "total_steps": 1778, "loss": 0.2056, "lr": 7.281802744561166e-06, "epoch": 5.236686390532545, "percentage": 74.8, "elapsed_time": "2:48:15", "remaining_time": "0:56:40"}
+{"current_steps": 1335, "total_steps": 1778, "loss": 0.2071, "lr": 7.130882705324422e-06, "epoch": 5.256410256410256, "percentage": 75.08, "elapsed_time": "2:48:50", "remaining_time": "0:56:01"}
+{"current_steps": 1340, "total_steps": 1778, "loss": 0.2118, "lr": 6.9812030183976e-06, "epoch": 5.276134122287968, "percentage": 75.37, "elapsed_time": "2:49:27", "remaining_time": "0:55:23"}
+{"current_steps": 1345, "total_steps": 1778, "loss": 0.2038, "lr": 6.832778110220457e-06, "epoch": 5.295857988165681, "percentage": 75.65, "elapsed_time": "2:50:03", "remaining_time": "0:54:44"}
+{"current_steps": 1350, "total_steps": 1778, "loss": 0.2094, "lr": 6.685622286294571e-06, "epoch": 5.315581854043392, "percentage": 75.93, "elapsed_time": "2:50:36", "remaining_time": "0:54:05"}
+{"current_steps": 1355, "total_steps": 1778, "loss": 0.2221, "lr": 6.539749729804539e-06, "epoch": 5.335305719921105, "percentage": 76.21, "elapsed_time": "2:51:17", "remaining_time": "0:53:28"}
+{"current_steps": 1360, "total_steps": 1778, "loss": 0.208, "lr": 6.395174500250949e-06, "epoch": 5.355029585798817, "percentage": 76.49, "elapsed_time": "2:51:54", "remaining_time": "0:52:50"}
+{"current_steps": 1365, "total_steps": 1778, "loss": 0.2137, "lr": 6.251910532095349e-06, "epoch": 5.374753451676528, "percentage": 76.77, "elapsed_time": "2:52:32", "remaining_time": "0:52:12"}
+{"current_steps": 1370, "total_steps": 1778, "loss": 0.2002, "lr": 6.109971633417169e-06, "epoch": 5.394477317554241, "percentage": 77.05, "elapsed_time": "2:53:09", "remaining_time": "0:51:34"}
+{"current_steps": 1375, "total_steps": 1778, "loss": 0.2134, "lr": 5.969371484582887e-06, "epoch": 5.414201183431953, "percentage": 77.33, "elapsed_time": "2:53:51", "remaining_time": "0:50:57"}
+{"current_steps": 1380, "total_steps": 1778, "loss": 0.2076, "lr": 5.830123636927485e-06, "epoch": 5.433925049309664, "percentage": 77.62, "elapsed_time": "2:54:27", "remaining_time": "0:50:18"}
+{"current_steps": 1385, "total_steps": 1778, "loss": 0.2101, "lr": 5.692241511448342e-06, "epoch": 5.453648915187377, "percentage": 77.9, "elapsed_time": "2:55:02", "remaining_time": "0:49:40"}
+{"current_steps": 1390, "total_steps": 1778, "loss": 0.2133, "lr": 5.555738397511699e-06, "epoch": 5.4733727810650885, "percentage": 78.18, "elapsed_time": "2:55:37", "remaining_time": "0:49:01"}
+{"current_steps": 1395, "total_steps": 1778, "loss": 0.2063, "lr": 5.4206274515717735e-06, "epoch": 5.493096646942801, "percentage": 78.46, "elapsed_time": "2:56:14", "remaining_time": "0:48:23"}
+{"current_steps": 1400, "total_steps": 1778, "loss": 0.2064, "lr": 5.286921695902749e-06, "epoch": 5.512820512820513, "percentage": 78.74, "elapsed_time": "2:56:55", "remaining_time": "0:47:46"}
+{"current_steps": 1405, "total_steps": 1778, "loss": 0.2072, "lr": 5.154634017343662e-06, "epoch": 5.5325443786982245, "percentage": 79.02, "elapsed_time": "2:57:28", "remaining_time": "0:47:06"}
+{"current_steps": 1410, "total_steps": 1778, "loss": 0.2012, "lr": 5.023777166056294e-06, "epoch": 5.552268244575937, "percentage": 79.3, "elapsed_time": "2:58:06", "remaining_time": "0:46:29"}
+{"current_steps": 1415, "total_steps": 1778, "loss": 0.202, "lr": 4.89436375429633e-06, "epoch": 5.571992110453649, "percentage": 79.58, "elapsed_time": "2:58:43", "remaining_time": "0:45:50"}
+{"current_steps": 1420, "total_steps": 1778, "loss": 0.2091, "lr": 4.766406255197751e-06, "epoch": 5.591715976331361, "percentage": 79.87, "elapsed_time": "2:59:16", "remaining_time": "0:45:11"}
+{"current_steps": 1425, "total_steps": 1778, "loss": 0.2105, "lr": 4.639917001570644e-06, "epoch": 5.611439842209073, "percentage": 80.15, "elapsed_time": "2:59:55", "remaining_time": "0:44:34"}
+{"current_steps": 1430, "total_steps": 1778, "loss": 0.2087, "lr": 4.51490818471255e-06, "epoch": 5.631163708086785, "percentage": 80.43, "elapsed_time": "3:00:33", "remaining_time": "0:43:56"}
+{"current_steps": 1435, "total_steps": 1778, "loss": 0.207, "lr": 4.391391853233404e-06, "epoch": 5.650887573964497, "percentage": 80.71, "elapsed_time": "3:01:12", "remaining_time": "0:43:18"}
+{"current_steps": 1440, "total_steps": 1778, "loss": 0.203, "lr": 4.269379911894336e-06, "epoch": 5.670611439842209, "percentage": 80.99, "elapsed_time": "3:01:45", "remaining_time": "0:42:39"}
+{"current_steps": 1445, "total_steps": 1778, "loss": 0.2063, "lr": 4.148884120460186e-06, "epoch": 5.6903353057199215, "percentage": 81.27, "elapsed_time": "3:02:24", "remaining_time": "0:42:02"}
+{"current_steps": 1450, "total_steps": 1778, "loss": 0.2152, "lr": 4.029916092566131e-06, "epoch": 5.710059171597633, "percentage": 81.55, "elapsed_time": "3:03:01", "remaining_time": "0:41:24"}
+{"current_steps": 1455, "total_steps": 1778, "loss": 0.2033, "lr": 3.91248729459831e-06, "epoch": 5.729783037475345, "percentage": 81.83, "elapsed_time": "3:03:40", "remaining_time": "0:40:46"}
+{"current_steps": 1460, "total_steps": 1778, "loss": 0.2123, "lr": 3.796609044588686e-06, "epoch": 5.7495069033530575, "percentage": 82.11, "elapsed_time": "3:04:15", "remaining_time": "0:40:07"}
+{"current_steps": 1465, "total_steps": 1778, "loss": 0.2088, "lr": 3.682292511124179e-06, "epoch": 5.769230769230769, "percentage": 82.4, "elapsed_time": "3:04:52", "remaining_time": "0:39:29"}
+{"current_steps": 1470, "total_steps": 1778, "loss": 0.2113, "lr": 3.569548712270201e-06, "epoch": 5.788954635108482, "percentage": 82.68, "elapsed_time": "3:05:32", "remaining_time": "0:38:52"}
+{"current_steps": 1475, "total_steps": 1778, "loss": 0.2213, "lr": 3.4583885145087613e-06, "epoch": 5.808678500986193, "percentage": 82.96, "elapsed_time": "3:06:07", "remaining_time": "0:38:14"}
+{"current_steps": 1480, "total_steps": 1778, "loss": 0.2133, "lr": 3.348822631691082e-06, "epoch": 5.828402366863905, "percentage": 83.24, "elapsed_time": "3:06:48", "remaining_time": "0:37:36"}
+{"current_steps": 1485, "total_steps": 1778, "loss": 0.2113, "lr": 3.240861624004983e-06, "epoch": 5.848126232741618, "percentage": 83.52, "elapsed_time": "3:07:26", "remaining_time": "0:36:59"}
+{"current_steps": 1490, "total_steps": 1778, "loss": 0.2085, "lr": 3.1345158969570933e-06, "epoch": 5.867850098619329, "percentage": 83.8, "elapsed_time": "3:08:06", "remaining_time": "0:36:21"}
+{"current_steps": 1495, "total_steps": 1778, "loss": 0.2038, "lr": 3.0297957003699284e-06, "epoch": 5.887573964497041, "percentage": 84.08, "elapsed_time": "3:08:42", "remaining_time": "0:35:43"}
+{"current_steps": 1500, "total_steps": 1778, "loss": 0.209, "lr": 2.926711127393993e-06, "epoch": 5.907297830374754, "percentage": 84.36, "elapsed_time": "3:09:19", "remaining_time": "0:35:05"}
+{"current_steps": 1505, "total_steps": 1778, "loss": 0.2071, "lr": 2.8252721135349892e-06, "epoch": 5.927021696252465, "percentage": 84.65, "elapsed_time": "3:10:34", "remaining_time": "0:34:34"}
+{"current_steps": 1510, "total_steps": 1778, "loss": 0.1996, "lr": 2.7254884356961976e-06, "epoch": 5.946745562130177, "percentage": 84.93, "elapsed_time": "3:11:11", "remaining_time": "0:33:55"}
+{"current_steps": 1515, "total_steps": 1778, "loss": 0.2141, "lr": 2.6273697112361786e-06, "epoch": 5.96646942800789, "percentage": 85.21, "elapsed_time": "3:11:49", "remaining_time": "0:33:18"}
+{"current_steps": 1520, "total_steps": 1778, "loss": 0.2078, "lr": 2.5309253970418056e-06, "epoch": 5.986193293885601, "percentage": 85.49, "elapsed_time": "3:12:26", "remaining_time": "0:32:39"}
+{"current_steps": 1525, "total_steps": 1778, "loss": 0.2088, "lr": 2.436164788616815e-06, "epoch": 6.003944773175542, "percentage": 85.77, "elapsed_time": "3:13:00", "remaining_time": "0:32:01"}
+{"current_steps": 1530, "total_steps": 1778, "loss": 0.2059, "lr": 2.3430970191858873e-06, "epoch": 6.023668639053255, "percentage": 86.05, "elapsed_time": "3:13:35", "remaining_time": "0:31:22"}
+{"current_steps": 1535, "total_steps": 1778, "loss": 0.2012, "lr": 2.2517310588143372e-06, "epoch": 6.043392504930966, "percentage": 86.33, "elapsed_time": "3:14:12", "remaining_time": "0:30:44"}
+{"current_steps": 1540, "total_steps": 1778, "loss": 0.1984, "lr": 2.1620757135435875e-06, "epoch": 6.063116370808679, "percentage": 86.61, "elapsed_time": "3:14:50", "remaining_time": "0:30:06"}
+{"current_steps": 1545, "total_steps": 1778, "loss": 0.2027, "lr": 2.0741396245424263e-06, "epoch": 6.0828402366863905, "percentage": 86.9, "elapsed_time": "3:15:30", "remaining_time": "0:29:29"}
+{"current_steps": 1550, "total_steps": 1778, "loss": 0.207, "lr": 1.9879312672741326e-06, "epoch": 6.102564102564102, "percentage": 87.18, "elapsed_time": "3:16:09", "remaining_time": "0:28:51"}
+{"current_steps": 1555, "total_steps": 1778, "loss": 0.2051, "lr": 1.903458950679613e-06, "epoch": 6.122287968441815, "percentage": 87.46, "elapsed_time": "3:16:43", "remaining_time": "0:28:12"}
+{"current_steps": 1560, "total_steps": 1778, "loss": 0.2074, "lr": 1.820730816376548e-06, "epoch": 6.1420118343195265, "percentage": 87.74, "elapsed_time": "3:17:18", "remaining_time": "0:27:34"}
+{"current_steps": 1565, "total_steps": 1778, "loss": 0.2032, "lr": 1.7397548378747142e-06, "epoch": 6.161735700197239, "percentage": 88.02, "elapsed_time": "3:17:54", "remaining_time": "0:26:56"}
+{"current_steps": 1570, "total_steps": 1778, "loss": 0.2028, "lr": 1.660538819807458e-06, "epoch": 6.181459566074951, "percentage": 88.3, "elapsed_time": "3:18:32", "remaining_time": "0:26:18"}
+{"current_steps": 1575, "total_steps": 1778, "loss": 0.2045, "lr": 1.5830903971794765e-06, "epoch": 6.201183431952662, "percentage": 88.58, "elapsed_time": "3:19:12", "remaining_time": "0:25:40"}
+{"current_steps": 1580, "total_steps": 1778, "loss": 0.2018, "lr": 1.5074170346309357e-06, "epoch": 6.220907297830375, "percentage": 88.86, "elapsed_time": "3:19:50", "remaining_time": "0:25:02"}
+{"current_steps": 1585, "total_steps": 1778, "loss": 0.1996, "lr": 1.4335260257180262e-06, "epoch": 6.240631163708087, "percentage": 89.15, "elapsed_time": "3:20:26", "remaining_time": "0:24:24"}
+{"current_steps": 1590, "total_steps": 1778, "loss": 0.2042, "lr": 1.3614244922099796e-06, "epoch": 6.260355029585799, "percentage": 89.43, "elapsed_time": "3:21:04", "remaining_time": "0:23:46"}
+{"current_steps": 1595, "total_steps": 1778, "loss": 0.2069, "lr": 1.2911193834026548e-06, "epoch": 6.280078895463511, "percentage": 89.71, "elapsed_time": "3:21:43", "remaining_time": "0:23:08"}
+{"current_steps": 1600, "total_steps": 1778, "loss": 0.1987, "lr": 1.222617475448773e-06, "epoch": 6.299802761341223, "percentage": 89.99, "elapsed_time": "3:22:15", "remaining_time": "0:22:30"}
+{"current_steps": 1605, "total_steps": 1778, "loss": 0.2056, "lr": 1.1559253707048046e-06, "epoch": 6.319526627218935, "percentage": 90.27, "elapsed_time": "3:22:51", "remaining_time": "0:21:51"}
+{"current_steps": 1610, "total_steps": 1778, "loss": 0.1965, "lr": 1.0910494970946073e-06, "epoch": 6.339250493096647, "percentage": 90.55, "elapsed_time": "3:23:28", "remaining_time": "0:21:13"}
+{"current_steps": 1615, "total_steps": 1778, "loss": 0.2018, "lr": 1.027996107489908e-06, "epoch": 6.358974358974359, "percentage": 90.83, "elapsed_time": "3:24:08", "remaining_time": "0:20:36"}
+{"current_steps": 1620, "total_steps": 1778, "loss": 0.2011, "lr": 9.667712791076345e-07, "epoch": 6.378698224852071, "percentage": 91.11, "elapsed_time": "3:24:45", "remaining_time": "0:19:58"}
+{"current_steps": 1625, "total_steps": 1778, "loss": 0.2035, "lr": 9.073809129241784e-07, "epoch": 6.398422090729783, "percentage": 91.39, "elapsed_time": "3:25:26", "remaining_time": "0:19:20"}
+{"current_steps": 1630, "total_steps": 1778, "loss": 0.2078, "lr": 8.498307331066446e-07, "epoch": 6.418145956607495, "percentage": 91.68, "elapsed_time": "3:26:03", "remaining_time": "0:18:42"}
+{"current_steps": 1635, "total_steps": 1778, "loss": 0.2014, "lr": 7.941262864611387e-07, "epoch": 6.437869822485207, "percentage": 91.96, "elapsed_time": "3:26:38", "remaining_time": "0:18:04"}
+{"current_steps": 1640, "total_steps": 1778, "loss": 0.1961, "lr": 7.402729418981769e-07, "epoch": 6.457593688362919, "percentage": 92.24, "elapsed_time": "3:27:19", "remaining_time": "0:17:26"}
+{"current_steps": 1645, "total_steps": 1778, "loss": 0.205, "lr": 6.882758899151886e-07, "epoch": 6.477317554240631, "percentage": 92.52, "elapsed_time": "3:27:58", "remaining_time": "0:16:48"}
+{"current_steps": 1650, "total_steps": 1778, "loss": 0.2123, "lr": 6.381401420962729e-07, "epoch": 6.497041420118343, "percentage": 92.8, "elapsed_time": "3:28:34", "remaining_time": "0:16:10"}
+{"current_steps": 1655, "total_steps": 1778, "loss": 0.2074, "lr": 5.898705306291508e-07, "epoch": 6.516765285996055, "percentage": 93.08, "elapsed_time": "3:29:15", "remaining_time": "0:15:33"}
+{"current_steps": 1660, "total_steps": 1778, "loss": 0.197, "lr": 5.434717078394447e-07, "epoch": 6.536489151873767, "percentage": 93.36, "elapsed_time": "3:29:51", "remaining_time": "0:14:55"}
+{"current_steps": 1665, "total_steps": 1778, "loss": 0.1963, "lr": 4.98948145742264e-07, "epoch": 6.556213017751479, "percentage": 93.64, "elapsed_time": "3:30:30", "remaining_time": "0:14:17"}
+{"current_steps": 1670, "total_steps": 1778, "loss": 0.2058, "lr": 4.563041356111919e-07, "epoch": 6.575936883629192, "percentage": 93.93, "elapsed_time": "3:31:04", "remaining_time": "0:13:39"}
+{"current_steps": 1675, "total_steps": 1778, "loss": 0.2045, "lr": 4.155437875646828e-07, "epoch": 6.595660749506903, "percentage": 94.21, "elapsed_time": "3:31:39", "remaining_time": "0:13:00"}
+{"current_steps": 1680, "total_steps": 1778, "loss": 0.206, "lr": 3.7667103016992167e-07, "epoch": 6.615384615384615, "percentage": 94.49, "elapsed_time": "3:32:20", "remaining_time": "0:12:23"}
+{"current_steps": 1685, "total_steps": 1778, "loss": 0.2045, "lr": 3.396896100641689e-07, "epoch": 6.6351084812623276, "percentage": 94.77, "elapsed_time": "3:33:01", "remaining_time": "0:11:45"}
+{"current_steps": 1690, "total_steps": 1778, "loss": 0.2048, "lr": 3.0460309159366486e-07, "epoch": 6.654832347140039, "percentage": 95.05, "elapsed_time": "3:33:39", "remaining_time": "0:11:07"}
+{"current_steps": 1695, "total_steps": 1778, "loss": 0.2032, "lr": 2.714148564700914e-07, "epoch": 6.674556213017752, "percentage": 95.33, "elapsed_time": "3:34:19", "remaining_time": "0:10:29"}
+{"current_steps": 1700, "total_steps": 1778, "loss": 0.2022, "lr": 2.401281034446212e-07, "epoch": 6.6942800788954635, "percentage": 95.61, "elapsed_time": "3:34:58", "remaining_time": "0:09:51"}
+{"current_steps": 1705, "total_steps": 1778, "loss": 0.2012, "lr": 2.107458479996316e-07, "epoch": 6.714003944773175, "percentage": 95.89, "elapsed_time": "3:35:40", "remaining_time": "0:09:14"}
+{"current_steps": 1710, "total_steps": 1778, "loss": 0.2102, "lr": 1.8327092205805641e-07, "epoch": 6.733727810650888, "percentage": 96.18, "elapsed_time": "3:36:17", "remaining_time": "0:08:36"}
+{"current_steps": 1715, "total_steps": 1778, "loss": 0.2093, "lr": 1.577059737104447e-07, "epoch": 6.7534516765285995, "percentage": 96.46, "elapsed_time": "3:36:52", "remaining_time": "0:07:58"}
+{"current_steps": 1720, "total_steps": 1778, "loss": 0.2012, "lr": 1.3405346695972265e-07, "epoch": 6.773175542406312, "percentage": 96.74, "elapsed_time": "3:37:29", "remaining_time": "0:07:20"}
+{"current_steps": 1725, "total_steps": 1778, "loss": 0.2079, "lr": 1.1231568148372562e-07, "epoch": 6.792899408284024, "percentage": 97.02, "elapsed_time": "3:38:03", "remaining_time": "0:06:41"}
+{"current_steps": 1730, "total_steps": 1778, "loss": 0.2076, "lr": 9.249471241545849e-08, "epoch": 6.812623274161735, "percentage": 97.3, "elapsed_time": "3:38:40", "remaining_time": "0:06:04"}
+{"current_steps": 1735, "total_steps": 1778, "loss": 0.204, "lr": 7.459247014117488e-08, "epoch": 6.832347140039448, "percentage": 97.58, "elapsed_time": "3:39:17", "remaining_time": "0:05:26"}
+{"current_steps": 1740, "total_steps": 1778, "loss": 0.1979, "lr": 5.861068011624449e-08, "epoch": 6.85207100591716, "percentage": 97.86, "elapsed_time": "3:39:53", "remaining_time": "0:04:48"}
+{"current_steps": 1745, "total_steps": 1778, "loss": 0.2078, "lr": 4.4550882698857214e-08, "epoch": 6.871794871794872, "percentage": 98.14, "elapsed_time": "3:40:28", "remaining_time": "0:04:10"}
+{"current_steps": 1750, "total_steps": 1778, "loss": 0.2082, "lr": 3.241443300154856e-08, "epoch": 6.891518737672584, "percentage": 98.43, "elapsed_time": "3:41:03", "remaining_time": "0:03:32"}
+{"current_steps": 1755, "total_steps": 1778, "loss": 0.2038, "lr": 2.220250076060193e-08, "epoch": 6.911242603550296, "percentage": 98.71, "elapsed_time": "3:41:42", "remaining_time": "0:02:54"}
+{"current_steps": 1760, "total_steps": 1778, "loss": 0.2015, "lr": 1.3916070223298772e-08, "epoch": 6.930966469428008, "percentage": 98.99, "elapsed_time": "3:42:22", "remaining_time": "0:02:16"}
+{"current_steps": 1765, "total_steps": 1778, "loss": 0.2045, "lr": 7.55594005306337e-09, "epoch": 6.95069033530572, "percentage": 99.27, "elapsed_time": "3:42:58", "remaining_time": "0:01:38"}
+{"current_steps": 1770, "total_steps": 1778, "loss": 0.2031, "lr": 3.122723252477755e-09, "epoch": 6.970414201183432, "percentage": 99.55, "elapsed_time": "3:43:31", "remaining_time": "0:01:00"}
+{"current_steps": 1775, "total_steps": 1778, "loss": 0.2022, "lr": 6.168471042067303e-10, "epoch": 6.990138067061144, "percentage": 99.83, "elapsed_time": "3:44:11", "remaining_time": "0:00:22"}
+{"current_steps": 1778, "total_steps": 1778, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "3:45:11", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45618668d345e28a9084d54c05473f4a16b8a940e20670a4588d5b2755c1ef7
+size 8657