初始化项目,由ModelHub XC社区提供模型

Model: laion/exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-17 08:36:15 +08:00
commit 52aedbacc2
24 changed files with 12665 additions and 0 deletions

56
.gitattributes vendored Normal file
View File

@@ -0,0 +1,56 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
vocab.json filter=lfs diff=lfs merge=lfs -text
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
training_args.bin filter=lfs diff=lfs merge=lfs -text
merges.txt filter=lfs diff=lfs merge=lfs -text
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text

61
README.md Normal file
View File

@@ -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-uns-r2egym-16_8x_glm_4_7_traces_jupiter
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-uns-r2egym-16_8x_glm_4_7_traces_jupiter
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent--exp-uns-r2egym-16_8x_glm_4.7_traces_jupiter/snapshots/f351781469e77321a7f815f7e9f7789e9b57a34e_thinking_preprocessed dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 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 4.57.6
- Pytorch 2.9.0+cu128
- Datasets 4.4.1
- Tokenizers 0.22.2

28
added_tokens.json Normal file
View File

@@ -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
}

16
all_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 4.896264491712151,
"achieved_tflops_per_gpu_theoretical": 271.03236502585344,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.12460079044103622,
"mfu_percent": 0.4950722438536048,
"mfu_percent_theoretical": 27.40468807137042,
"total_flos": 2.3699064220633006e+18,
"train_loss": 0.2668512877930834,
"train_runtime": 60502.9208,
"train_samples_per_second": 1.273,
"train_steps_per_second": 0.08,
"valid_targets_mean": 4185.4,
"valid_targets_min": 557
}

89
chat_template.jinja Normal file
View File

@@ -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 %}

68
config.json Normal file
View File

@@ -0,0 +1,68 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.6",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

1
configuration.json Normal file
View File

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

12
generation_config.json Normal file
View File

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

BIN
merges.txt (Stored with Git LFS) Normal file

Binary file not shown.

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f62bdf6ce666a8f6ed26636b3d16faeea9fbe367e697fc4acc8d08c058076f04
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:79030adbe796f3803e82d602f8c0adccb5e107daf35c33752db6b385162ef8b1
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:65bfa8fd8cd6bcd5d1347a71dedb8006cfe5705fcc026c479778306e4d014612
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1f66c3aab293a18826974f75e5e58f6713b19bfcf0750ecda234edea11dad506
size 1580230264

View File

@@ -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"
}
}

12
run_summary.json Normal file
View File

@@ -0,0 +1,12 @@
{
"agent_name": "f351781469e77321a7f815f7e9f7789e9b57a34e_thinking_preprocessed",
"training_start": null,
"training_end": null,
"created_by": "DCAgent",
"base_model_name": "Qwen/Qwen3-8B",
"dataset_name": "/data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent--exp-uns-r2egym-16_8x_glm_4.7_traces_jupiter/snapshots/f351781469e77321a7f815f7e9f7789e9b57a34e_thinking_preprocessed",
"training_type": "SFT",
"training_parameters": "https://huggingface.co/laion/exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter/blob/main/config.json",
"wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp-uns-r2egym-16_8x_glm_4-7_traces_jupiter_Qwen3-8B",
"traces_location_s3": null
}

31
special_tokens_map.json Normal file
View File

@@ -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
}
}

BIN
tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

240
tokenizer_config.json Normal file
View File

@@ -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
}

16
train_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 4.896264491712151,
"achieved_tflops_per_gpu_theoretical": 271.03236502585344,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.12460079044103622,
"mfu_percent": 0.4950722438536048,
"mfu_percent_theoretical": 27.40468807137042,
"total_flos": 2.3699064220633006e+18,
"train_loss": 0.2668512877930834,
"train_runtime": 60502.9208,
"train_samples_per_second": 1.273,
"train_steps_per_second": 0.08,
"valid_targets_mean": 4185.4,
"valid_targets_min": 557
}

964
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,964 @@
{"current_steps": 5, "total_steps": 4816, "loss": 0.8619, "lr": 3.319502074688797e-07, "epoch": 0.007267441860465116, "percentage": 0.1, "elapsed_time": "0:01:11", "remaining_time": "19:10:15"}
{"current_steps": 10, "total_steps": 4816, "loss": 0.88, "lr": 7.468879668049793e-07, "epoch": 0.014534883720930232, "percentage": 0.21, "elapsed_time": "0:02:19", "remaining_time": "18:35:21"}
{"current_steps": 15, "total_steps": 4816, "loss": 0.8461, "lr": 1.161825726141079e-06, "epoch": 0.02180232558139535, "percentage": 0.31, "elapsed_time": "0:03:22", "remaining_time": "17:57:44"}
{"current_steps": 20, "total_steps": 4816, "loss": 0.7898, "lr": 1.5767634854771784e-06, "epoch": 0.029069767441860465, "percentage": 0.42, "elapsed_time": "0:04:34", "remaining_time": "18:15:13"}
{"current_steps": 25, "total_steps": 4816, "loss": 0.7522, "lr": 1.991701244813278e-06, "epoch": 0.036337209302325583, "percentage": 0.52, "elapsed_time": "0:05:37", "remaining_time": "17:57:43"}
{"current_steps": 30, "total_steps": 4816, "loss": 0.6776, "lr": 2.4066390041493776e-06, "epoch": 0.0436046511627907, "percentage": 0.62, "elapsed_time": "0:06:43", "remaining_time": "17:53:00"}
{"current_steps": 35, "total_steps": 4816, "loss": 0.647, "lr": 2.8215767634854773e-06, "epoch": 0.050872093023255814, "percentage": 0.73, "elapsed_time": "0:07:49", "remaining_time": "17:48:13"}
{"current_steps": 40, "total_steps": 4816, "loss": 0.6368, "lr": 3.2365145228215773e-06, "epoch": 0.05813953488372093, "percentage": 0.83, "elapsed_time": "0:08:59", "remaining_time": "17:52:52"}
{"current_steps": 45, "total_steps": 4816, "loss": 0.6042, "lr": 3.6514522821576765e-06, "epoch": 0.06540697674418605, "percentage": 0.93, "elapsed_time": "0:10:02", "remaining_time": "17:45:28"}
{"current_steps": 50, "total_steps": 4816, "loss": 0.6092, "lr": 4.0663900414937765e-06, "epoch": 0.07267441860465117, "percentage": 1.04, "elapsed_time": "0:11:03", "remaining_time": "17:33:45"}
{"current_steps": 55, "total_steps": 4816, "loss": 0.5623, "lr": 4.481327800829876e-06, "epoch": 0.07994186046511628, "percentage": 1.14, "elapsed_time": "0:12:14", "remaining_time": "17:40:12"}
{"current_steps": 60, "total_steps": 4816, "loss": 0.5582, "lr": 4.896265560165976e-06, "epoch": 0.0872093023255814, "percentage": 1.25, "elapsed_time": "0:13:16", "remaining_time": "17:31:42"}
{"current_steps": 65, "total_steps": 4816, "loss": 0.5279, "lr": 5.311203319502075e-06, "epoch": 0.09447674418604651, "percentage": 1.35, "elapsed_time": "0:14:26", "remaining_time": "17:35:44"}
{"current_steps": 70, "total_steps": 4816, "loss": 0.5329, "lr": 5.726141078838174e-06, "epoch": 0.10174418604651163, "percentage": 1.45, "elapsed_time": "0:15:28", "remaining_time": "17:29:29"}
{"current_steps": 75, "total_steps": 4816, "loss": 0.4821, "lr": 6.1410788381742745e-06, "epoch": 0.10901162790697674, "percentage": 1.56, "elapsed_time": "0:16:40", "remaining_time": "17:34:07"}
{"current_steps": 80, "total_steps": 4816, "loss": 0.4768, "lr": 6.556016597510374e-06, "epoch": 0.11627906976744186, "percentage": 1.66, "elapsed_time": "0:17:47", "remaining_time": "17:32:52"}
{"current_steps": 85, "total_steps": 4816, "loss": 0.4808, "lr": 6.970954356846473e-06, "epoch": 0.12354651162790697, "percentage": 1.76, "elapsed_time": "0:18:57", "remaining_time": "17:34:56"}
{"current_steps": 90, "total_steps": 4816, "loss": 0.4469, "lr": 7.385892116182573e-06, "epoch": 0.1308139534883721, "percentage": 1.87, "elapsed_time": "0:20:02", "remaining_time": "17:32:48"}
{"current_steps": 95, "total_steps": 4816, "loss": 0.4533, "lr": 7.800829875518673e-06, "epoch": 0.1380813953488372, "percentage": 1.97, "elapsed_time": "0:21:01", "remaining_time": "17:25:12"}
{"current_steps": 100, "total_steps": 4816, "loss": 0.4457, "lr": 8.215767634854772e-06, "epoch": 0.14534883720930233, "percentage": 2.08, "elapsed_time": "0:22:02", "remaining_time": "17:19:19"}
{"current_steps": 105, "total_steps": 4816, "loss": 0.4474, "lr": 8.630705394190872e-06, "epoch": 0.15261627906976744, "percentage": 2.18, "elapsed_time": "0:23:07", "remaining_time": "17:17:44"}
{"current_steps": 110, "total_steps": 4816, "loss": 0.4288, "lr": 9.045643153526971e-06, "epoch": 0.15988372093023256, "percentage": 2.28, "elapsed_time": "0:24:13", "remaining_time": "17:16:25"}
{"current_steps": 115, "total_steps": 4816, "loss": 0.4541, "lr": 9.460580912863071e-06, "epoch": 0.16715116279069767, "percentage": 2.39, "elapsed_time": "0:25:16", "remaining_time": "17:13:11"}
{"current_steps": 120, "total_steps": 4816, "loss": 0.4304, "lr": 9.875518672199172e-06, "epoch": 0.1744186046511628, "percentage": 2.49, "elapsed_time": "0:26:19", "remaining_time": "17:10:20"}
{"current_steps": 125, "total_steps": 4816, "loss": 0.41, "lr": 1.0290456431535269e-05, "epoch": 0.1816860465116279, "percentage": 2.6, "elapsed_time": "0:27:24", "remaining_time": "17:08:22"}
{"current_steps": 130, "total_steps": 4816, "loss": 0.4158, "lr": 1.070539419087137e-05, "epoch": 0.18895348837209303, "percentage": 2.7, "elapsed_time": "0:28:26", "remaining_time": "17:04:56"}
{"current_steps": 135, "total_steps": 4816, "loss": 0.3866, "lr": 1.112033195020747e-05, "epoch": 0.19622093023255813, "percentage": 2.8, "elapsed_time": "0:29:35", "remaining_time": "17:06:10"}
{"current_steps": 140, "total_steps": 4816, "loss": 0.3935, "lr": 1.1535269709543569e-05, "epoch": 0.20348837209302326, "percentage": 2.91, "elapsed_time": "0:30:40", "remaining_time": "17:04:45"}
{"current_steps": 145, "total_steps": 4816, "loss": 0.3836, "lr": 1.1950207468879669e-05, "epoch": 0.21075581395348839, "percentage": 3.01, "elapsed_time": "0:31:48", "remaining_time": "17:04:47"}
{"current_steps": 150, "total_steps": 4816, "loss": 0.3918, "lr": 1.236514522821577e-05, "epoch": 0.2180232558139535, "percentage": 3.11, "elapsed_time": "0:32:58", "remaining_time": "17:05:50"}
{"current_steps": 155, "total_steps": 4816, "loss": 0.3847, "lr": 1.2780082987551867e-05, "epoch": 0.22529069767441862, "percentage": 3.22, "elapsed_time": "0:34:00", "remaining_time": "17:02:29"}
{"current_steps": 160, "total_steps": 4816, "loss": 0.387, "lr": 1.3195020746887967e-05, "epoch": 0.23255813953488372, "percentage": 3.32, "elapsed_time": "0:34:58", "remaining_time": "16:57:40"}
{"current_steps": 165, "total_steps": 4816, "loss": 0.3834, "lr": 1.3609958506224067e-05, "epoch": 0.23982558139534885, "percentage": 3.43, "elapsed_time": "0:36:04", "remaining_time": "16:56:43"}
{"current_steps": 170, "total_steps": 4816, "loss": 0.3975, "lr": 1.4024896265560166e-05, "epoch": 0.24709302325581395, "percentage": 3.53, "elapsed_time": "0:37:09", "remaining_time": "16:55:25"}
{"current_steps": 175, "total_steps": 4816, "loss": 0.3808, "lr": 1.4439834024896267e-05, "epoch": 0.2543604651162791, "percentage": 3.63, "elapsed_time": "0:38:15", "remaining_time": "16:54:27"}
{"current_steps": 180, "total_steps": 4816, "loss": 0.3775, "lr": 1.4854771784232367e-05, "epoch": 0.2616279069767442, "percentage": 3.74, "elapsed_time": "0:39:19", "remaining_time": "16:52:52"}
{"current_steps": 185, "total_steps": 4816, "loss": 0.3938, "lr": 1.5269709543568464e-05, "epoch": 0.2688953488372093, "percentage": 3.84, "elapsed_time": "0:40:19", "remaining_time": "16:49:20"}
{"current_steps": 190, "total_steps": 4816, "loss": 0.383, "lr": 1.5684647302904566e-05, "epoch": 0.2761627906976744, "percentage": 3.95, "elapsed_time": "0:41:20", "remaining_time": "16:46:39"}
{"current_steps": 195, "total_steps": 4816, "loss": 0.3812, "lr": 1.6099585062240665e-05, "epoch": 0.28343023255813954, "percentage": 4.05, "elapsed_time": "0:42:26", "remaining_time": "16:45:42"}
{"current_steps": 200, "total_steps": 4816, "loss": 0.3761, "lr": 1.6514522821576764e-05, "epoch": 0.29069767441860467, "percentage": 4.15, "elapsed_time": "0:43:36", "remaining_time": "16:46:36"}
{"current_steps": 205, "total_steps": 4816, "loss": 0.3862, "lr": 1.6929460580912863e-05, "epoch": 0.29796511627906974, "percentage": 4.26, "elapsed_time": "0:44:41", "remaining_time": "16:45:12"}
{"current_steps": 210, "total_steps": 4816, "loss": 0.373, "lr": 1.7344398340248965e-05, "epoch": 0.30523255813953487, "percentage": 4.36, "elapsed_time": "0:45:41", "remaining_time": "16:42:06"}
{"current_steps": 215, "total_steps": 4816, "loss": 0.3787, "lr": 1.7759336099585064e-05, "epoch": 0.3125, "percentage": 4.46, "elapsed_time": "0:46:40", "remaining_time": "16:39:00"}
{"current_steps": 220, "total_steps": 4816, "loss": 0.3952, "lr": 1.8174273858921162e-05, "epoch": 0.31976744186046513, "percentage": 4.57, "elapsed_time": "0:47:45", "remaining_time": "16:37:33"}
{"current_steps": 225, "total_steps": 4816, "loss": 0.3555, "lr": 1.8589211618257264e-05, "epoch": 0.32703488372093026, "percentage": 4.67, "elapsed_time": "0:48:53", "remaining_time": "16:37:39"}
{"current_steps": 230, "total_steps": 4816, "loss": 0.3649, "lr": 1.9004149377593363e-05, "epoch": 0.33430232558139533, "percentage": 4.78, "elapsed_time": "0:49:55", "remaining_time": "16:35:21"}
{"current_steps": 235, "total_steps": 4816, "loss": 0.3644, "lr": 1.9419087136929462e-05, "epoch": 0.34156976744186046, "percentage": 4.88, "elapsed_time": "0:50:57", "remaining_time": "16:33:29"}
{"current_steps": 240, "total_steps": 4816, "loss": 0.3588, "lr": 1.983402489626556e-05, "epoch": 0.3488372093023256, "percentage": 4.98, "elapsed_time": "0:52:10", "remaining_time": "16:34:46"}
{"current_steps": 245, "total_steps": 4816, "loss": 0.3635, "lr": 2.024896265560166e-05, "epoch": 0.3561046511627907, "percentage": 5.09, "elapsed_time": "0:53:10", "remaining_time": "16:32:02"}
{"current_steps": 250, "total_steps": 4816, "loss": 0.3641, "lr": 2.066390041493776e-05, "epoch": 0.3633720930232558, "percentage": 5.19, "elapsed_time": "0:54:16", "remaining_time": "16:31:18"}
{"current_steps": 255, "total_steps": 4816, "loss": 0.3509, "lr": 2.107883817427386e-05, "epoch": 0.3706395348837209, "percentage": 5.29, "elapsed_time": "0:55:20", "remaining_time": "16:29:52"}
{"current_steps": 260, "total_steps": 4816, "loss": 0.3543, "lr": 2.149377593360996e-05, "epoch": 0.37790697674418605, "percentage": 5.4, "elapsed_time": "0:56:26", "remaining_time": "16:28:57"}
{"current_steps": 265, "total_steps": 4816, "loss": 0.3378, "lr": 2.190871369294606e-05, "epoch": 0.3851744186046512, "percentage": 5.5, "elapsed_time": "0:57:29", "remaining_time": "16:27:12"}
{"current_steps": 270, "total_steps": 4816, "loss": 0.3526, "lr": 2.232365145228216e-05, "epoch": 0.39244186046511625, "percentage": 5.61, "elapsed_time": "0:58:34", "remaining_time": "16:26:19"}
{"current_steps": 275, "total_steps": 4816, "loss": 0.3786, "lr": 2.273858921161826e-05, "epoch": 0.3997093023255814, "percentage": 5.71, "elapsed_time": "0:59:38", "remaining_time": "16:24:46"}
{"current_steps": 280, "total_steps": 4816, "loss": 0.3594, "lr": 2.315352697095436e-05, "epoch": 0.4069767441860465, "percentage": 5.81, "elapsed_time": "1:00:35", "remaining_time": "16:21:31"}
{"current_steps": 285, "total_steps": 4816, "loss": 0.3452, "lr": 2.356846473029046e-05, "epoch": 0.41424418604651164, "percentage": 5.92, "elapsed_time": "1:01:42", "remaining_time": "16:20:58"}
{"current_steps": 290, "total_steps": 4816, "loss": 0.3384, "lr": 2.398340248962656e-05, "epoch": 0.42151162790697677, "percentage": 6.02, "elapsed_time": "1:02:47", "remaining_time": "16:19:56"}
{"current_steps": 295, "total_steps": 4816, "loss": 0.3506, "lr": 2.439834024896266e-05, "epoch": 0.42877906976744184, "percentage": 6.13, "elapsed_time": "1:03:44", "remaining_time": "16:16:50"}
{"current_steps": 300, "total_steps": 4816, "loss": 0.3305, "lr": 2.481327800829876e-05, "epoch": 0.436046511627907, "percentage": 6.23, "elapsed_time": "1:04:50", "remaining_time": "16:16:01"}
{"current_steps": 305, "total_steps": 4816, "loss": 0.3556, "lr": 2.5228215767634855e-05, "epoch": 0.4433139534883721, "percentage": 6.33, "elapsed_time": "1:05:53", "remaining_time": "16:14:39"}
{"current_steps": 310, "total_steps": 4816, "loss": 0.3537, "lr": 2.5643153526970957e-05, "epoch": 0.45058139534883723, "percentage": 6.44, "elapsed_time": "1:06:54", "remaining_time": "16:12:37"}
{"current_steps": 315, "total_steps": 4816, "loss": 0.3433, "lr": 2.6058091286307056e-05, "epoch": 0.4578488372093023, "percentage": 6.54, "elapsed_time": "1:07:57", "remaining_time": "16:10:56"}
{"current_steps": 320, "total_steps": 4816, "loss": 0.3346, "lr": 2.6473029045643155e-05, "epoch": 0.46511627906976744, "percentage": 6.64, "elapsed_time": "1:08:54", "remaining_time": "16:08:08"}
{"current_steps": 325, "total_steps": 4816, "loss": 0.3331, "lr": 2.6887966804979257e-05, "epoch": 0.47238372093023256, "percentage": 6.75, "elapsed_time": "1:09:53", "remaining_time": "16:05:49"}
{"current_steps": 330, "total_steps": 4816, "loss": 0.3464, "lr": 2.7302904564315355e-05, "epoch": 0.4796511627906977, "percentage": 6.85, "elapsed_time": "1:10:58", "remaining_time": "16:04:53"}
{"current_steps": 335, "total_steps": 4816, "loss": 0.3464, "lr": 2.7717842323651454e-05, "epoch": 0.48691860465116277, "percentage": 6.96, "elapsed_time": "1:12:01", "remaining_time": "16:03:22"}
{"current_steps": 340, "total_steps": 4816, "loss": 0.3426, "lr": 2.8132780082987556e-05, "epoch": 0.4941860465116279, "percentage": 7.06, "elapsed_time": "1:13:08", "remaining_time": "16:02:47"}
{"current_steps": 345, "total_steps": 4816, "loss": 0.3435, "lr": 2.8547717842323655e-05, "epoch": 0.501453488372093, "percentage": 7.16, "elapsed_time": "1:14:08", "remaining_time": "16:00:49"}
{"current_steps": 350, "total_steps": 4816, "loss": 0.3442, "lr": 2.8962655601659754e-05, "epoch": 0.5087209302325582, "percentage": 7.27, "elapsed_time": "1:15:18", "remaining_time": "16:00:49"}
{"current_steps": 355, "total_steps": 4816, "loss": 0.3168, "lr": 2.9377593360995856e-05, "epoch": 0.5159883720930233, "percentage": 7.37, "elapsed_time": "1:16:15", "remaining_time": "15:58:14"}
{"current_steps": 360, "total_steps": 4816, "loss": 0.3223, "lr": 2.9792531120331955e-05, "epoch": 0.5232558139534884, "percentage": 7.48, "elapsed_time": "1:17:20", "remaining_time": "15:57:23"}
{"current_steps": 365, "total_steps": 4816, "loss": 0.3301, "lr": 3.020746887966805e-05, "epoch": 0.5305232558139535, "percentage": 7.58, "elapsed_time": "1:18:20", "remaining_time": "15:55:20"}
{"current_steps": 370, "total_steps": 4816, "loss": 0.3372, "lr": 3.062240663900415e-05, "epoch": 0.5377906976744186, "percentage": 7.68, "elapsed_time": "1:19:24", "remaining_time": "15:54:06"}
{"current_steps": 375, "total_steps": 4816, "loss": 0.3402, "lr": 3.103734439834025e-05, "epoch": 0.5450581395348837, "percentage": 7.79, "elapsed_time": "1:20:28", "remaining_time": "15:53:07"}
{"current_steps": 380, "total_steps": 4816, "loss": 0.3012, "lr": 3.145228215767635e-05, "epoch": 0.5523255813953488, "percentage": 7.89, "elapsed_time": "1:21:27", "remaining_time": "15:50:52"}
{"current_steps": 385, "total_steps": 4816, "loss": 0.3193, "lr": 3.186721991701245e-05, "epoch": 0.559593023255814, "percentage": 7.99, "elapsed_time": "1:22:28", "remaining_time": "15:49:14"}
{"current_steps": 390, "total_steps": 4816, "loss": 0.3267, "lr": 3.2282157676348554e-05, "epoch": 0.5668604651162791, "percentage": 8.1, "elapsed_time": "1:23:29", "remaining_time": "15:47:36"}
{"current_steps": 395, "total_steps": 4816, "loss": 0.3223, "lr": 3.2697095435684646e-05, "epoch": 0.5741279069767442, "percentage": 8.2, "elapsed_time": "1:24:34", "remaining_time": "15:46:36"}
{"current_steps": 400, "total_steps": 4816, "loss": 0.3517, "lr": 3.3112033195020745e-05, "epoch": 0.5813953488372093, "percentage": 8.31, "elapsed_time": "1:25:42", "remaining_time": "15:46:08"}
{"current_steps": 405, "total_steps": 4816, "loss": 0.3137, "lr": 3.352697095435685e-05, "epoch": 0.5886627906976745, "percentage": 8.41, "elapsed_time": "1:26:50", "remaining_time": "15:45:48"}
{"current_steps": 410, "total_steps": 4816, "loss": 0.326, "lr": 3.394190871369295e-05, "epoch": 0.5959302325581395, "percentage": 8.51, "elapsed_time": "1:27:48", "remaining_time": "15:43:37"}
{"current_steps": 415, "total_steps": 4816, "loss": 0.3415, "lr": 3.435684647302905e-05, "epoch": 0.6031976744186046, "percentage": 8.62, "elapsed_time": "1:28:51", "remaining_time": "15:42:16"}
{"current_steps": 420, "total_steps": 4816, "loss": 0.3226, "lr": 3.477178423236515e-05, "epoch": 0.6104651162790697, "percentage": 8.72, "elapsed_time": "1:29:47", "remaining_time": "15:39:49"}
{"current_steps": 425, "total_steps": 4816, "loss": 0.3392, "lr": 3.5186721991701245e-05, "epoch": 0.6177325581395349, "percentage": 8.82, "elapsed_time": "1:30:47", "remaining_time": "15:37:59"}
{"current_steps": 430, "total_steps": 4816, "loss": 0.3293, "lr": 3.5601659751037344e-05, "epoch": 0.625, "percentage": 8.93, "elapsed_time": "1:31:46", "remaining_time": "15:36:10"}
{"current_steps": 435, "total_steps": 4816, "loss": 0.3198, "lr": 3.601659751037345e-05, "epoch": 0.6322674418604651, "percentage": 9.03, "elapsed_time": "1:32:47", "remaining_time": "15:34:30"}
{"current_steps": 440, "total_steps": 4816, "loss": 0.3107, "lr": 3.643153526970955e-05, "epoch": 0.6395348837209303, "percentage": 9.14, "elapsed_time": "1:33:49", "remaining_time": "15:33:05"}
{"current_steps": 445, "total_steps": 4816, "loss": 0.3209, "lr": 3.684647302904565e-05, "epoch": 0.6468023255813954, "percentage": 9.24, "elapsed_time": "1:34:51", "remaining_time": "15:31:43"}
{"current_steps": 450, "total_steps": 4816, "loss": 0.3323, "lr": 3.7261410788381746e-05, "epoch": 0.6540697674418605, "percentage": 9.34, "elapsed_time": "1:35:55", "remaining_time": "15:30:37"}
{"current_steps": 455, "total_steps": 4816, "loss": 0.3105, "lr": 3.7676348547717845e-05, "epoch": 0.6613372093023255, "percentage": 9.45, "elapsed_time": "1:37:00", "remaining_time": "15:29:51"}
{"current_steps": 460, "total_steps": 4816, "loss": 0.3301, "lr": 3.8091286307053944e-05, "epoch": 0.6686046511627907, "percentage": 9.55, "elapsed_time": "1:38:01", "remaining_time": "15:28:18"}
{"current_steps": 465, "total_steps": 4816, "loss": 0.3154, "lr": 3.850622406639004e-05, "epoch": 0.6758720930232558, "percentage": 9.66, "elapsed_time": "1:39:05", "remaining_time": "15:27:09"}
{"current_steps": 470, "total_steps": 4816, "loss": 0.3254, "lr": 3.892116182572614e-05, "epoch": 0.6831395348837209, "percentage": 9.76, "elapsed_time": "1:40:04", "remaining_time": "15:25:18"}
{"current_steps": 475, "total_steps": 4816, "loss": 0.3074, "lr": 3.933609958506224e-05, "epoch": 0.690406976744186, "percentage": 9.86, "elapsed_time": "1:41:10", "remaining_time": "15:24:42"}
{"current_steps": 480, "total_steps": 4816, "loss": 0.3266, "lr": 3.9751037344398345e-05, "epoch": 0.6976744186046512, "percentage": 9.97, "elapsed_time": "1:42:16", "remaining_time": "15:23:52"}
{"current_steps": 485, "total_steps": 4816, "loss": 0.3114, "lr": 3.999997898246174e-05, "epoch": 0.7049418604651163, "percentage": 10.07, "elapsed_time": "1:43:19", "remaining_time": "15:22:37"}
{"current_steps": 490, "total_steps": 4816, "loss": 0.3187, "lr": 3.999974253566362e-05, "epoch": 0.7122093023255814, "percentage": 10.17, "elapsed_time": "1:44:21", "remaining_time": "15:21:24"}
{"current_steps": 495, "total_steps": 4816, "loss": 0.3126, "lr": 3.999924337326085e-05, "epoch": 0.7194767441860465, "percentage": 10.28, "elapsed_time": "1:45:24", "remaining_time": "15:20:07"}
{"current_steps": 500, "total_steps": 4816, "loss": 0.3149, "lr": 3.9998481501810414e-05, "epoch": 0.7267441860465116, "percentage": 10.38, "elapsed_time": "1:46:28", "remaining_time": "15:19:09"}
{"current_steps": 505, "total_steps": 4816, "loss": 0.2994, "lr": 3.999745693132021e-05, "epoch": 0.7340116279069767, "percentage": 10.49, "elapsed_time": "1:47:33", "remaining_time": "15:18:07"}
{"current_steps": 510, "total_steps": 4816, "loss": 0.318, "lr": 3.999616967524894e-05, "epoch": 0.7412790697674418, "percentage": 10.59, "elapsed_time": "1:48:39", "remaining_time": "15:17:27"}
{"current_steps": 515, "total_steps": 4816, "loss": 0.3382, "lr": 3.999461975050595e-05, "epoch": 0.748546511627907, "percentage": 10.69, "elapsed_time": "1:49:39", "remaining_time": "15:15:49"}
{"current_steps": 520, "total_steps": 4816, "loss": 0.3091, "lr": 3.9992807177450956e-05, "epoch": 0.7558139534883721, "percentage": 10.8, "elapsed_time": "1:50:36", "remaining_time": "15:13:47"}
{"current_steps": 525, "total_steps": 4816, "loss": 0.323, "lr": 3.9990731979893834e-05, "epoch": 0.7630813953488372, "percentage": 10.9, "elapsed_time": "1:51:40", "remaining_time": "15:12:46"}
{"current_steps": 530, "total_steps": 4816, "loss": 0.3152, "lr": 3.998839418509428e-05, "epoch": 0.7703488372093024, "percentage": 11.0, "elapsed_time": "1:52:42", "remaining_time": "15:11:26"}
{"current_steps": 535, "total_steps": 4816, "loss": 0.3181, "lr": 3.998579382376143e-05, "epoch": 0.7776162790697675, "percentage": 11.11, "elapsed_time": "1:53:47", "remaining_time": "15:10:35"}
{"current_steps": 540, "total_steps": 4816, "loss": 0.3197, "lr": 3.9982930930053515e-05, "epoch": 0.7848837209302325, "percentage": 11.21, "elapsed_time": "1:54:51", "remaining_time": "15:09:29"}
{"current_steps": 545, "total_steps": 4816, "loss": 0.3189, "lr": 3.9979805541577356e-05, "epoch": 0.7921511627906976, "percentage": 11.32, "elapsed_time": "1:55:53", "remaining_time": "15:08:16"}
{"current_steps": 550, "total_steps": 4816, "loss": 0.3178, "lr": 3.99764176993879e-05, "epoch": 0.7994186046511628, "percentage": 11.42, "elapsed_time": "1:56:55", "remaining_time": "15:06:52"}
{"current_steps": 555, "total_steps": 4816, "loss": 0.3121, "lr": 3.997276744798766e-05, "epoch": 0.8066860465116279, "percentage": 11.52, "elapsed_time": "1:57:54", "remaining_time": "15:05:12"}
{"current_steps": 560, "total_steps": 4816, "loss": 0.3126, "lr": 3.996885483532617e-05, "epoch": 0.813953488372093, "percentage": 11.63, "elapsed_time": "1:58:54", "remaining_time": "15:03:39"}
{"current_steps": 565, "total_steps": 4816, "loss": 0.3127, "lr": 3.9964679912799306e-05, "epoch": 0.8212209302325582, "percentage": 11.73, "elapsed_time": "1:59:55", "remaining_time": "15:02:20"}
{"current_steps": 570, "total_steps": 4816, "loss": 0.3341, "lr": 3.9960242735248626e-05, "epoch": 0.8284883720930233, "percentage": 11.84, "elapsed_time": "2:00:55", "remaining_time": "15:00:49"}
{"current_steps": 575, "total_steps": 4816, "loss": 0.3386, "lr": 3.995554336096069e-05, "epoch": 0.8357558139534884, "percentage": 11.94, "elapsed_time": "2:01:57", "remaining_time": "14:59:29"}
{"current_steps": 580, "total_steps": 4816, "loss": 0.3014, "lr": 3.995058185166623e-05, "epoch": 0.8430232558139535, "percentage": 12.04, "elapsed_time": "2:02:57", "remaining_time": "14:58:00"}
{"current_steps": 585, "total_steps": 4816, "loss": 0.3036, "lr": 3.9945358272539373e-05, "epoch": 0.8502906976744186, "percentage": 12.15, "elapsed_time": "2:04:01", "remaining_time": "14:56:59"}
{"current_steps": 590, "total_steps": 4816, "loss": 0.3081, "lr": 3.9939872692196805e-05, "epoch": 0.8575581395348837, "percentage": 12.25, "elapsed_time": "2:05:02", "remaining_time": "14:55:38"}
{"current_steps": 595, "total_steps": 4816, "loss": 0.3211, "lr": 3.993412518269682e-05, "epoch": 0.8648255813953488, "percentage": 12.35, "elapsed_time": "2:06:03", "remaining_time": "14:54:12"}
{"current_steps": 600, "total_steps": 4816, "loss": 0.3141, "lr": 3.9928115819538416e-05, "epoch": 0.872093023255814, "percentage": 12.46, "elapsed_time": "2:07:11", "remaining_time": "14:53:45"}
{"current_steps": 605, "total_steps": 4816, "loss": 0.3158, "lr": 3.992184468166028e-05, "epoch": 0.8793604651162791, "percentage": 12.56, "elapsed_time": "2:08:13", "remaining_time": "14:52:25"}
{"current_steps": 610, "total_steps": 4816, "loss": 0.2911, "lr": 3.991531185143977e-05, "epoch": 0.8866279069767442, "percentage": 12.67, "elapsed_time": "2:09:15", "remaining_time": "14:51:13"}
{"current_steps": 615, "total_steps": 4816, "loss": 0.3, "lr": 3.9908517414691806e-05, "epoch": 0.8938953488372093, "percentage": 12.77, "elapsed_time": "2:10:14", "remaining_time": "14:49:42"}
{"current_steps": 620, "total_steps": 4816, "loss": 0.3123, "lr": 3.990146146066776e-05, "epoch": 0.9011627906976745, "percentage": 12.87, "elapsed_time": "2:11:14", "remaining_time": "14:48:14"}
{"current_steps": 625, "total_steps": 4816, "loss": 0.3146, "lr": 3.98941440820543e-05, "epoch": 0.9084302325581395, "percentage": 12.98, "elapsed_time": "2:12:17", "remaining_time": "14:47:04"}
{"current_steps": 630, "total_steps": 4816, "loss": 0.3188, "lr": 3.988656537497213e-05, "epoch": 0.9156976744186046, "percentage": 13.08, "elapsed_time": "2:13:24", "remaining_time": "14:46:23"}
{"current_steps": 635, "total_steps": 4816, "loss": 0.3121, "lr": 3.987872543897477e-05, "epoch": 0.9229651162790697, "percentage": 13.19, "elapsed_time": "2:14:21", "remaining_time": "14:44:40"}
{"current_steps": 640, "total_steps": 4816, "loss": 0.3225, "lr": 3.9870624377047206e-05, "epoch": 0.9302325581395349, "percentage": 13.29, "elapsed_time": "2:15:29", "remaining_time": "14:44:04"}
{"current_steps": 645, "total_steps": 4816, "loss": 0.3029, "lr": 3.9862262295604594e-05, "epoch": 0.9375, "percentage": 13.39, "elapsed_time": "2:16:33", "remaining_time": "14:43:04"}
{"current_steps": 650, "total_steps": 4816, "loss": 0.2946, "lr": 3.9853639304490815e-05, "epoch": 0.9447674418604651, "percentage": 13.5, "elapsed_time": "2:17:29", "remaining_time": "14:41:13"}
{"current_steps": 655, "total_steps": 4816, "loss": 0.3185, "lr": 3.984475551697703e-05, "epoch": 0.9520348837209303, "percentage": 13.6, "elapsed_time": "2:18:28", "remaining_time": "14:39:39"}
{"current_steps": 660, "total_steps": 4816, "loss": 0.3232, "lr": 3.9835611049760216e-05, "epoch": 0.9593023255813954, "percentage": 13.7, "elapsed_time": "2:19:33", "remaining_time": "14:38:47"}
{"current_steps": 665, "total_steps": 4816, "loss": 0.3122, "lr": 3.982620602296166e-05, "epoch": 0.9665697674418605, "percentage": 13.81, "elapsed_time": "2:20:39", "remaining_time": "14:37:59"}
{"current_steps": 670, "total_steps": 4816, "loss": 0.3094, "lr": 3.981654056012529e-05, "epoch": 0.9738372093023255, "percentage": 13.91, "elapsed_time": "2:21:38", "remaining_time": "14:36:30"}
{"current_steps": 675, "total_steps": 4816, "loss": 0.3454, "lr": 3.980661478821614e-05, "epoch": 0.9811046511627907, "percentage": 14.02, "elapsed_time": "2:22:37", "remaining_time": "14:34:59"}
{"current_steps": 680, "total_steps": 4816, "loss": 0.2994, "lr": 3.979642883761866e-05, "epoch": 0.9883720930232558, "percentage": 14.12, "elapsed_time": "2:23:43", "remaining_time": "14:34:09"}
{"current_steps": 685, "total_steps": 4816, "loss": 0.2988, "lr": 3.978598284213497e-05, "epoch": 0.9956395348837209, "percentage": 14.22, "elapsed_time": "2:24:48", "remaining_time": "14:33:17"}
{"current_steps": 690, "total_steps": 4816, "loss": 0.3086, "lr": 3.9775276938983144e-05, "epoch": 1.002906976744186, "percentage": 14.33, "elapsed_time": "2:25:51", "remaining_time": "14:32:09"}
{"current_steps": 695, "total_steps": 4816, "loss": 0.2837, "lr": 3.9764311268795374e-05, "epoch": 1.010174418604651, "percentage": 14.43, "elapsed_time": "2:26:50", "remaining_time": "14:30:43"}
{"current_steps": 700, "total_steps": 4816, "loss": 0.3015, "lr": 3.9753085975616157e-05, "epoch": 1.0174418604651163, "percentage": 14.53, "elapsed_time": "2:27:48", "remaining_time": "14:29:08"}
{"current_steps": 705, "total_steps": 4816, "loss": 0.294, "lr": 3.9741601206900376e-05, "epoch": 1.0247093023255813, "percentage": 14.64, "elapsed_time": "2:28:49", "remaining_time": "14:27:52"}
{"current_steps": 710, "total_steps": 4816, "loss": 0.3069, "lr": 3.972985711351136e-05, "epoch": 1.0319767441860466, "percentage": 14.74, "elapsed_time": "2:29:52", "remaining_time": "14:26:44"}
{"current_steps": 715, "total_steps": 4816, "loss": 0.2876, "lr": 3.971785384971894e-05, "epoch": 1.0392441860465116, "percentage": 14.85, "elapsed_time": "2:30:57", "remaining_time": "14:25:49"}
{"current_steps": 720, "total_steps": 4816, "loss": 0.2858, "lr": 3.970559157319737e-05, "epoch": 1.0465116279069768, "percentage": 14.95, "elapsed_time": "2:32:00", "remaining_time": "14:24:44"}
{"current_steps": 725, "total_steps": 4816, "loss": 0.3006, "lr": 3.9693070445023297e-05, "epoch": 1.0537790697674418, "percentage": 15.05, "elapsed_time": "2:33:03", "remaining_time": "14:23:38"}
{"current_steps": 730, "total_steps": 4816, "loss": 0.3136, "lr": 3.968029062967363e-05, "epoch": 1.0610465116279069, "percentage": 15.16, "elapsed_time": "2:34:04", "remaining_time": "14:22:22"}
{"current_steps": 735, "total_steps": 4816, "loss": 0.2906, "lr": 3.966725229502336e-05, "epoch": 1.068313953488372, "percentage": 15.26, "elapsed_time": "2:35:14", "remaining_time": "14:21:55"}
{"current_steps": 740, "total_steps": 4816, "loss": 0.2918, "lr": 3.965395561234341e-05, "epoch": 1.0755813953488371, "percentage": 15.37, "elapsed_time": "2:36:22", "remaining_time": "14:21:20"}
{"current_steps": 745, "total_steps": 4816, "loss": 0.2938, "lr": 3.9640400756298325e-05, "epoch": 1.0828488372093024, "percentage": 15.47, "elapsed_time": "2:37:26", "remaining_time": "14:20:21"}
{"current_steps": 750, "total_steps": 4816, "loss": 0.2932, "lr": 3.9626587904943996e-05, "epoch": 1.0901162790697674, "percentage": 15.57, "elapsed_time": "2:38:31", "remaining_time": "14:19:23"}
{"current_steps": 755, "total_steps": 4816, "loss": 0.2966, "lr": 3.961251723972535e-05, "epoch": 1.0973837209302326, "percentage": 15.68, "elapsed_time": "2:39:37", "remaining_time": "14:18:34"}
{"current_steps": 760, "total_steps": 4816, "loss": 0.288, "lr": 3.959818894547393e-05, "epoch": 1.1046511627906976, "percentage": 15.78, "elapsed_time": "2:40:40", "remaining_time": "14:17:28"}
{"current_steps": 765, "total_steps": 4816, "loss": 0.2866, "lr": 3.9583603210405484e-05, "epoch": 1.1119186046511629, "percentage": 15.88, "elapsed_time": "2:41:49", "remaining_time": "14:16:56"}
{"current_steps": 770, "total_steps": 4816, "loss": 0.2917, "lr": 3.956876022611748e-05, "epoch": 1.119186046511628, "percentage": 15.99, "elapsed_time": "2:42:51", "remaining_time": "14:15:46"}
{"current_steps": 775, "total_steps": 4816, "loss": 0.2948, "lr": 3.9553660187586625e-05, "epoch": 1.1264534883720931, "percentage": 16.09, "elapsed_time": "2:43:58", "remaining_time": "14:15:00"}
{"current_steps": 780, "total_steps": 4816, "loss": 0.2819, "lr": 3.9538303293166243e-05, "epoch": 1.1337209302325582, "percentage": 16.2, "elapsed_time": "2:44:58", "remaining_time": "14:13:37"}
{"current_steps": 785, "total_steps": 4816, "loss": 0.3074, "lr": 3.952268974458373e-05, "epoch": 1.1409883720930232, "percentage": 16.3, "elapsed_time": "2:45:59", "remaining_time": "14:12:24"}
{"current_steps": 790, "total_steps": 4816, "loss": 0.2931, "lr": 3.950681974693787e-05, "epoch": 1.1482558139534884, "percentage": 16.4, "elapsed_time": "2:47:00", "remaining_time": "14:11:05"}
{"current_steps": 795, "total_steps": 4816, "loss": 0.3147, "lr": 3.949069350869614e-05, "epoch": 1.1555232558139534, "percentage": 16.51, "elapsed_time": "2:47:59", "remaining_time": "14:09:39"}
{"current_steps": 800, "total_steps": 4816, "loss": 0.3049, "lr": 3.9474311241691994e-05, "epoch": 1.1627906976744187, "percentage": 16.61, "elapsed_time": "2:49:09", "remaining_time": "14:09:08"}
{"current_steps": 805, "total_steps": 4816, "loss": 0.3073, "lr": 3.945767316112206e-05, "epoch": 1.1700581395348837, "percentage": 16.72, "elapsed_time": "2:50:11", "remaining_time": "14:08:01"}
{"current_steps": 810, "total_steps": 4816, "loss": 0.302, "lr": 3.944077948554333e-05, "epoch": 1.177325581395349, "percentage": 16.82, "elapsed_time": "2:51:12", "remaining_time": "14:06:44"}
{"current_steps": 815, "total_steps": 4816, "loss": 0.2843, "lr": 3.9423630436870255e-05, "epoch": 1.184593023255814, "percentage": 16.92, "elapsed_time": "2:52:13", "remaining_time": "14:05:29"}
{"current_steps": 820, "total_steps": 4816, "loss": 0.3015, "lr": 3.940622624037188e-05, "epoch": 1.191860465116279, "percentage": 17.03, "elapsed_time": "2:53:12", "remaining_time": "14:04:02"}
{"current_steps": 825, "total_steps": 4816, "loss": 0.2788, "lr": 3.938856712466885e-05, "epoch": 1.1991279069767442, "percentage": 17.13, "elapsed_time": "2:54:14", "remaining_time": "14:02:56"}
{"current_steps": 830, "total_steps": 4816, "loss": 0.29, "lr": 3.93706533217304e-05, "epoch": 1.2063953488372092, "percentage": 17.23, "elapsed_time": "2:55:13", "remaining_time": "14:01:30"}
{"current_steps": 835, "total_steps": 4816, "loss": 0.302, "lr": 3.935248506687136e-05, "epoch": 1.2136627906976745, "percentage": 17.34, "elapsed_time": "2:56:15", "remaining_time": "14:00:20"}
{"current_steps": 840, "total_steps": 4816, "loss": 0.2899, "lr": 3.9334062598748986e-05, "epoch": 1.2209302325581395, "percentage": 17.44, "elapsed_time": "2:57:20", "remaining_time": "13:59:24"}
{"current_steps": 845, "total_steps": 4816, "loss": 0.2746, "lr": 3.931538615935989e-05, "epoch": 1.2281976744186047, "percentage": 17.55, "elapsed_time": "2:58:20", "remaining_time": "13:58:04"}
{"current_steps": 850, "total_steps": 4816, "loss": 0.2905, "lr": 3.929645599403684e-05, "epoch": 1.2354651162790697, "percentage": 17.65, "elapsed_time": "2:59:21", "remaining_time": "13:56:53"}
{"current_steps": 855, "total_steps": 4816, "loss": 0.2858, "lr": 3.9277272351445524e-05, "epoch": 1.2427325581395348, "percentage": 17.75, "elapsed_time": "3:00:19", "remaining_time": "13:55:23"}
{"current_steps": 860, "total_steps": 4816, "loss": 0.2965, "lr": 3.9257835483581306e-05, "epoch": 1.25, "percentage": 17.86, "elapsed_time": "3:01:22", "remaining_time": "13:54:17"}
{"current_steps": 865, "total_steps": 4816, "loss": 0.287, "lr": 3.923814564576589e-05, "epoch": 1.2572674418604652, "percentage": 17.96, "elapsed_time": "3:02:20", "remaining_time": "13:52:50"}
{"current_steps": 870, "total_steps": 4816, "loss": 0.2969, "lr": 3.921820309664398e-05, "epoch": 1.2645348837209303, "percentage": 18.06, "elapsed_time": "3:03:19", "remaining_time": "13:51:28"}
{"current_steps": 875, "total_steps": 4816, "loss": 0.2987, "lr": 3.91980080981799e-05, "epoch": 1.2718023255813953, "percentage": 18.17, "elapsed_time": "3:04:21", "remaining_time": "13:50:19"}
{"current_steps": 880, "total_steps": 4816, "loss": 0.2951, "lr": 3.917756091565414e-05, "epoch": 1.2790697674418605, "percentage": 18.27, "elapsed_time": "3:05:22", "remaining_time": "13:49:05"}
{"current_steps": 885, "total_steps": 4816, "loss": 0.2985, "lr": 3.915686181765983e-05, "epoch": 1.2863372093023255, "percentage": 18.38, "elapsed_time": "3:06:25", "remaining_time": "13:48:04"}
{"current_steps": 890, "total_steps": 4816, "loss": 0.2912, "lr": 3.9135911076099286e-05, "epoch": 1.2936046511627908, "percentage": 18.48, "elapsed_time": "3:07:29", "remaining_time": "13:47:04"}
{"current_steps": 895, "total_steps": 4816, "loss": 0.2869, "lr": 3.9114708966180385e-05, "epoch": 1.3008720930232558, "percentage": 18.58, "elapsed_time": "3:08:34", "remaining_time": "13:46:10"}
{"current_steps": 900, "total_steps": 4816, "loss": 0.293, "lr": 3.909325576641298e-05, "epoch": 1.308139534883721, "percentage": 18.69, "elapsed_time": "3:09:36", "remaining_time": "13:45:00"}
{"current_steps": 905, "total_steps": 4816, "loss": 0.2764, "lr": 3.907155175860519e-05, "epoch": 1.315406976744186, "percentage": 18.79, "elapsed_time": "3:10:40", "remaining_time": "13:44:01"}
{"current_steps": 910, "total_steps": 4816, "loss": 0.2991, "lr": 3.904959722785978e-05, "epoch": 1.322674418604651, "percentage": 18.9, "elapsed_time": "3:11:46", "remaining_time": "13:43:11"}
{"current_steps": 915, "total_steps": 4816, "loss": 0.3012, "lr": 3.902739246257035e-05, "epoch": 1.3299418604651163, "percentage": 19.0, "elapsed_time": "3:12:42", "remaining_time": "13:41:36"}
{"current_steps": 920, "total_steps": 4816, "loss": 0.2879, "lr": 3.9004937754417576e-05, "epoch": 1.3372093023255813, "percentage": 19.1, "elapsed_time": "3:13:51", "remaining_time": "13:40:56"}
{"current_steps": 925, "total_steps": 4816, "loss": 0.2905, "lr": 3.898223339836535e-05, "epoch": 1.3444767441860466, "percentage": 19.21, "elapsed_time": "3:14:58", "remaining_time": "13:40:10"}
{"current_steps": 930, "total_steps": 4816, "loss": 0.2739, "lr": 3.8959279692656965e-05, "epoch": 1.3517441860465116, "percentage": 19.31, "elapsed_time": "3:16:03", "remaining_time": "13:39:14"}
{"current_steps": 935, "total_steps": 4816, "loss": 0.2888, "lr": 3.893607693881113e-05, "epoch": 1.3590116279069768, "percentage": 19.41, "elapsed_time": "3:17:04", "remaining_time": "13:38:01"}
{"current_steps": 940, "total_steps": 4816, "loss": 0.3246, "lr": 3.8912625441618034e-05, "epoch": 1.3662790697674418, "percentage": 19.52, "elapsed_time": "3:18:04", "remaining_time": "13:36:44"}
{"current_steps": 945, "total_steps": 4816, "loss": 0.2873, "lr": 3.8888925509135365e-05, "epoch": 1.3735465116279069, "percentage": 19.62, "elapsed_time": "3:19:09", "remaining_time": "13:35:47"}
{"current_steps": 950, "total_steps": 4816, "loss": 0.2943, "lr": 3.8864977452684235e-05, "epoch": 1.380813953488372, "percentage": 19.73, "elapsed_time": "3:20:12", "remaining_time": "13:34:46"}
{"current_steps": 955, "total_steps": 4816, "loss": 0.2838, "lr": 3.88407815868451e-05, "epoch": 1.3880813953488373, "percentage": 19.83, "elapsed_time": "3:21:10", "remaining_time": "13:33:18"}
{"current_steps": 960, "total_steps": 4816, "loss": 0.2948, "lr": 3.8816338229453616e-05, "epoch": 1.3953488372093024, "percentage": 19.93, "elapsed_time": "3:22:07", "remaining_time": "13:31:54"}
{"current_steps": 965, "total_steps": 4816, "loss": 0.2839, "lr": 3.879164770159651e-05, "epoch": 1.4026162790697674, "percentage": 20.04, "elapsed_time": "3:23:08", "remaining_time": "13:30:39"}
{"current_steps": 970, "total_steps": 4816, "loss": 0.291, "lr": 3.8766710327607275e-05, "epoch": 1.4098837209302326, "percentage": 20.14, "elapsed_time": "3:24:11", "remaining_time": "13:29:38"}
{"current_steps": 975, "total_steps": 4816, "loss": 0.2785, "lr": 3.874152643506202e-05, "epoch": 1.4171511627906976, "percentage": 20.25, "elapsed_time": "3:25:13", "remaining_time": "13:28:30"}
{"current_steps": 980, "total_steps": 4816, "loss": 0.3037, "lr": 3.871609635477507e-05, "epoch": 1.4244186046511627, "percentage": 20.35, "elapsed_time": "3:26:14", "remaining_time": "13:27:18"}
{"current_steps": 985, "total_steps": 4816, "loss": 0.2765, "lr": 3.869042042079467e-05, "epoch": 1.431686046511628, "percentage": 20.45, "elapsed_time": "3:27:18", "remaining_time": "13:26:17"}
{"current_steps": 990, "total_steps": 4816, "loss": 0.3149, "lr": 3.866449897039859e-05, "epoch": 1.4389534883720931, "percentage": 20.56, "elapsed_time": "3:28:25", "remaining_time": "13:25:28"}
{"current_steps": 995, "total_steps": 4816, "loss": 0.2817, "lr": 3.863833234408969e-05, "epoch": 1.4462209302325582, "percentage": 20.66, "elapsed_time": "3:29:22", "remaining_time": "13:24:02"}
{"current_steps": 1000, "total_steps": 4816, "loss": 0.2881, "lr": 3.861192088559144e-05, "epoch": 1.4534883720930232, "percentage": 20.76, "elapsed_time": "3:30:23", "remaining_time": "13:22:50"}
{"current_steps": 1005, "total_steps": 4816, "loss": 0.3142, "lr": 3.858526494184344e-05, "epoch": 1.4607558139534884, "percentage": 20.87, "elapsed_time": "3:31:25", "remaining_time": "13:21:43"}
{"current_steps": 1010, "total_steps": 4816, "loss": 0.2925, "lr": 3.8558364862996796e-05, "epoch": 1.4680232558139534, "percentage": 20.97, "elapsed_time": "3:32:26", "remaining_time": "13:20:34"}
{"current_steps": 1015, "total_steps": 4816, "loss": 0.3007, "lr": 3.853122100240959e-05, "epoch": 1.4752906976744187, "percentage": 21.08, "elapsed_time": "3:33:29", "remaining_time": "13:19:28"}
{"current_steps": 1020, "total_steps": 4816, "loss": 0.2846, "lr": 3.850383371664219e-05, "epoch": 1.4825581395348837, "percentage": 21.18, "elapsed_time": "3:34:34", "remaining_time": "13:18:33"}
{"current_steps": 1025, "total_steps": 4816, "loss": 0.2943, "lr": 3.8476203365452607e-05, "epoch": 1.489825581395349, "percentage": 21.28, "elapsed_time": "3:35:31", "remaining_time": "13:17:06"}
{"current_steps": 1030, "total_steps": 4816, "loss": 0.2835, "lr": 3.8448330311791735e-05, "epoch": 1.497093023255814, "percentage": 21.39, "elapsed_time": "3:36:37", "remaining_time": "13:16:16"}
{"current_steps": 1035, "total_steps": 4816, "loss": 0.2776, "lr": 3.842021492179858e-05, "epoch": 1.504360465116279, "percentage": 21.49, "elapsed_time": "3:37:35", "remaining_time": "13:14:52"}
{"current_steps": 1040, "total_steps": 4816, "loss": 0.2699, "lr": 3.8391857564795494e-05, "epoch": 1.5116279069767442, "percentage": 21.59, "elapsed_time": "3:38:35", "remaining_time": "13:13:38"}
{"current_steps": 1045, "total_steps": 4816, "loss": 0.2993, "lr": 3.836325861328328e-05, "epoch": 1.5188953488372094, "percentage": 21.7, "elapsed_time": "3:39:36", "remaining_time": "13:12:30"}
{"current_steps": 1050, "total_steps": 4816, "loss": 0.288, "lr": 3.83344184429363e-05, "epoch": 1.5261627906976745, "percentage": 21.8, "elapsed_time": "3:40:43", "remaining_time": "13:11:40"}
{"current_steps": 1055, "total_steps": 4816, "loss": 0.2854, "lr": 3.83053374325976e-05, "epoch": 1.5334302325581395, "percentage": 21.91, "elapsed_time": "3:41:50", "remaining_time": "13:10:50"}
{"current_steps": 1060, "total_steps": 4816, "loss": 0.2798, "lr": 3.827601596427383e-05, "epoch": 1.5406976744186047, "percentage": 22.01, "elapsed_time": "3:42:54", "remaining_time": "13:09:51"}
{"current_steps": 1065, "total_steps": 4816, "loss": 0.2896, "lr": 3.824645442313033e-05, "epoch": 1.5479651162790697, "percentage": 22.11, "elapsed_time": "3:43:54", "remaining_time": "13:08:35"}
{"current_steps": 1070, "total_steps": 4816, "loss": 0.2821, "lr": 3.8216653197486004e-05, "epoch": 1.5552325581395348, "percentage": 22.22, "elapsed_time": "3:45:03", "remaining_time": "13:07:54"}
{"current_steps": 1075, "total_steps": 4816, "loss": 0.3081, "lr": 3.818661267880823e-05, "epoch": 1.5625, "percentage": 22.32, "elapsed_time": "3:46:08", "remaining_time": "13:06:58"}
{"current_steps": 1080, "total_steps": 4816, "loss": 0.2622, "lr": 3.815633326170776e-05, "epoch": 1.5697674418604652, "percentage": 22.43, "elapsed_time": "3:47:13", "remaining_time": "13:06:00"}
{"current_steps": 1085, "total_steps": 4816, "loss": 0.2884, "lr": 3.812581534393347e-05, "epoch": 1.5770348837209303, "percentage": 22.53, "elapsed_time": "3:48:18", "remaining_time": "13:05:05"}
{"current_steps": 1090, "total_steps": 4816, "loss": 0.2781, "lr": 3.809505932636717e-05, "epoch": 1.5843023255813953, "percentage": 22.63, "elapsed_time": "3:49:18", "remaining_time": "13:03:50"}
{"current_steps": 1095, "total_steps": 4816, "loss": 0.2836, "lr": 3.8064065613018376e-05, "epoch": 1.5915697674418605, "percentage": 22.74, "elapsed_time": "3:50:20", "remaining_time": "13:02:45"}
{"current_steps": 1100, "total_steps": 4816, "loss": 0.2766, "lr": 3.803283461101892e-05, "epoch": 1.5988372093023255, "percentage": 22.84, "elapsed_time": "3:51:22", "remaining_time": "13:01:38"}
{"current_steps": 1105, "total_steps": 4816, "loss": 0.2986, "lr": 3.800136673061765e-05, "epoch": 1.6061046511627906, "percentage": 22.94, "elapsed_time": "3:52:25", "remaining_time": "13:00:33"}
{"current_steps": 1110, "total_steps": 4816, "loss": 0.293, "lr": 3.796966238517508e-05, "epoch": 1.6133720930232558, "percentage": 23.05, "elapsed_time": "3:53:30", "remaining_time": "12:59:36"}
{"current_steps": 1115, "total_steps": 4816, "loss": 0.2996, "lr": 3.793772199115786e-05, "epoch": 1.620639534883721, "percentage": 23.15, "elapsed_time": "3:54:35", "remaining_time": "12:58:41"}
{"current_steps": 1120, "total_steps": 4816, "loss": 0.2827, "lr": 3.790554596813339e-05, "epoch": 1.627906976744186, "percentage": 23.26, "elapsed_time": "3:55:35", "remaining_time": "12:57:26"}
{"current_steps": 1125, "total_steps": 4816, "loss": 0.2793, "lr": 3.787313473876429e-05, "epoch": 1.635174418604651, "percentage": 23.36, "elapsed_time": "3:56:36", "remaining_time": "12:56:17"}
{"current_steps": 1130, "total_steps": 4816, "loss": 0.2726, "lr": 3.784048872880282e-05, "epoch": 1.6424418604651163, "percentage": 23.46, "elapsed_time": "3:57:35", "remaining_time": "12:55:00"}
{"current_steps": 1135, "total_steps": 4816, "loss": 0.2761, "lr": 3.780760836708531e-05, "epoch": 1.6497093023255816, "percentage": 23.57, "elapsed_time": "3:58:39", "remaining_time": "12:54:00"}
{"current_steps": 1140, "total_steps": 4816, "loss": 0.2861, "lr": 3.777449408552653e-05, "epoch": 1.6569767441860463, "percentage": 23.67, "elapsed_time": "3:59:42", "remaining_time": "12:52:57"}
{"current_steps": 1145, "total_steps": 4816, "loss": 0.2841, "lr": 3.774114631911401e-05, "epoch": 1.6642441860465116, "percentage": 23.77, "elapsed_time": "4:00:47", "remaining_time": "12:51:58"}
{"current_steps": 1150, "total_steps": 4816, "loss": 0.2746, "lr": 3.770756550590231e-05, "epoch": 1.6715116279069768, "percentage": 23.88, "elapsed_time": "4:01:50", "remaining_time": "12:50:58"}
{"current_steps": 1155, "total_steps": 4816, "loss": 0.2878, "lr": 3.767375208700729e-05, "epoch": 1.6787790697674418, "percentage": 23.98, "elapsed_time": "4:02:55", "remaining_time": "12:50:00"}
{"current_steps": 1160, "total_steps": 4816, "loss": 0.2849, "lr": 3.763970650660032e-05, "epoch": 1.6860465116279069, "percentage": 24.09, "elapsed_time": "4:03:53", "remaining_time": "12:48:42"}
{"current_steps": 1165, "total_steps": 4816, "loss": 0.2782, "lr": 3.76054292119024e-05, "epoch": 1.693313953488372, "percentage": 24.19, "elapsed_time": "4:04:54", "remaining_time": "12:47:30"}
{"current_steps": 1170, "total_steps": 4816, "loss": 0.3035, "lr": 3.7570920653178355e-05, "epoch": 1.7005813953488373, "percentage": 24.29, "elapsed_time": "4:05:49", "remaining_time": "12:46:03"}
{"current_steps": 1175, "total_steps": 4816, "loss": 0.2802, "lr": 3.753618128373086e-05, "epoch": 1.7078488372093024, "percentage": 24.4, "elapsed_time": "4:06:53", "remaining_time": "12:45:03"}
{"current_steps": 1180, "total_steps": 4816, "loss": 0.2834, "lr": 3.75012115598945e-05, "epoch": 1.7151162790697674, "percentage": 24.5, "elapsed_time": "4:08:02", "remaining_time": "12:44:17"}
{"current_steps": 1185, "total_steps": 4816, "loss": 0.2967, "lr": 3.7466011941029806e-05, "epoch": 1.7223837209302326, "percentage": 24.61, "elapsed_time": "4:09:04", "remaining_time": "12:43:11"}
{"current_steps": 1190, "total_steps": 4816, "loss": 0.2827, "lr": 3.743058288951719e-05, "epoch": 1.7296511627906976, "percentage": 24.71, "elapsed_time": "4:10:10", "remaining_time": "12:42:16"}
{"current_steps": 1195, "total_steps": 4816, "loss": 0.2999, "lr": 3.739492487075087e-05, "epoch": 1.7369186046511627, "percentage": 24.81, "elapsed_time": "4:11:19", "remaining_time": "12:41:31"}
{"current_steps": 1200, "total_steps": 4816, "loss": 0.2705, "lr": 3.735903835313278e-05, "epoch": 1.744186046511628, "percentage": 24.92, "elapsed_time": "4:12:28", "remaining_time": "12:40:47"}
{"current_steps": 1205, "total_steps": 4816, "loss": 0.3053, "lr": 3.7322923808066394e-05, "epoch": 1.7514534883720931, "percentage": 25.02, "elapsed_time": "4:13:29", "remaining_time": "12:39:37"}
{"current_steps": 1210, "total_steps": 4816, "loss": 0.2919, "lr": 3.728658170995055e-05, "epoch": 1.7587209302325582, "percentage": 25.12, "elapsed_time": "4:14:31", "remaining_time": "12:38:31"}
{"current_steps": 1215, "total_steps": 4816, "loss": 0.3008, "lr": 3.72500125361732e-05, "epoch": 1.7659883720930232, "percentage": 25.23, "elapsed_time": "4:15:35", "remaining_time": "12:37:30"}
{"current_steps": 1220, "total_steps": 4816, "loss": 0.2845, "lr": 3.7213216767105165e-05, "epoch": 1.7732558139534884, "percentage": 25.33, "elapsed_time": "4:16:40", "remaining_time": "12:36:32"}
{"current_steps": 1225, "total_steps": 4816, "loss": 0.2835, "lr": 3.71761948860938e-05, "epoch": 1.7805232558139537, "percentage": 25.44, "elapsed_time": "4:17:40", "remaining_time": "12:35:21"}
{"current_steps": 1230, "total_steps": 4816, "loss": 0.2722, "lr": 3.713894737945666e-05, "epoch": 1.7877906976744184, "percentage": 25.54, "elapsed_time": "4:18:48", "remaining_time": "12:34:33"}
{"current_steps": 1235, "total_steps": 4816, "loss": 0.2866, "lr": 3.71014747364751e-05, "epoch": 1.7950581395348837, "percentage": 25.64, "elapsed_time": "4:19:55", "remaining_time": "12:33:41"}
{"current_steps": 1240, "total_steps": 4816, "loss": 0.2745, "lr": 3.7063777449387875e-05, "epoch": 1.802325581395349, "percentage": 25.75, "elapsed_time": "4:20:58", "remaining_time": "12:32:36"}
{"current_steps": 1245, "total_steps": 4816, "loss": 0.278, "lr": 3.702585601338461e-05, "epoch": 1.809593023255814, "percentage": 25.85, "elapsed_time": "4:21:59", "remaining_time": "12:31:28"}
{"current_steps": 1250, "total_steps": 4816, "loss": 0.2868, "lr": 3.698771092659939e-05, "epoch": 1.816860465116279, "percentage": 25.96, "elapsed_time": "4:23:04", "remaining_time": "12:30:30"}
{"current_steps": 1255, "total_steps": 4816, "loss": 0.2821, "lr": 3.694934269010414e-05, "epoch": 1.8241279069767442, "percentage": 26.06, "elapsed_time": "4:24:09", "remaining_time": "12:29:31"}
{"current_steps": 1260, "total_steps": 4816, "loss": 0.2845, "lr": 3.691075180790207e-05, "epoch": 1.8313953488372094, "percentage": 26.16, "elapsed_time": "4:25:13", "remaining_time": "12:28:31"}
{"current_steps": 1265, "total_steps": 4816, "loss": 0.2958, "lr": 3.6871938786921044e-05, "epoch": 1.8386627906976745, "percentage": 26.27, "elapsed_time": "4:26:13", "remaining_time": "12:27:20"}
{"current_steps": 1270, "total_steps": 4816, "loss": 0.2981, "lr": 3.683290413700695e-05, "epoch": 1.8459302325581395, "percentage": 26.37, "elapsed_time": "4:27:17", "remaining_time": "12:26:17"}
{"current_steps": 1275, "total_steps": 4816, "loss": 0.2781, "lr": 3.679364837091696e-05, "epoch": 1.8531976744186047, "percentage": 26.47, "elapsed_time": "4:28:21", "remaining_time": "12:25:18"}
{"current_steps": 1280, "total_steps": 4816, "loss": 0.2835, "lr": 3.675417200431284e-05, "epoch": 1.8604651162790697, "percentage": 26.58, "elapsed_time": "4:29:25", "remaining_time": "12:24:18"}
{"current_steps": 1285, "total_steps": 4816, "loss": 0.2816, "lr": 3.671447555575413e-05, "epoch": 1.8677325581395348, "percentage": 26.68, "elapsed_time": "4:30:28", "remaining_time": "12:23:13"}
{"current_steps": 1290, "total_steps": 4816, "loss": 0.2863, "lr": 3.667455954669138e-05, "epoch": 1.875, "percentage": 26.79, "elapsed_time": "4:31:29", "remaining_time": "12:22:04"}
{"current_steps": 1295, "total_steps": 4816, "loss": 0.2895, "lr": 3.663442450145926e-05, "epoch": 1.8822674418604652, "percentage": 26.89, "elapsed_time": "4:32:29", "remaining_time": "12:20:52"}
{"current_steps": 1300, "total_steps": 4816, "loss": 0.2821, "lr": 3.6594070947269675e-05, "epoch": 1.8895348837209303, "percentage": 26.99, "elapsed_time": "4:33:29", "remaining_time": "12:19:40"}
{"current_steps": 1305, "total_steps": 4816, "loss": 0.2722, "lr": 3.65534994142049e-05, "epoch": 1.8968023255813953, "percentage": 27.1, "elapsed_time": "4:34:31", "remaining_time": "12:18:35"}
{"current_steps": 1310, "total_steps": 4816, "loss": 0.2936, "lr": 3.6512710435210496e-05, "epoch": 1.9040697674418605, "percentage": 27.2, "elapsed_time": "4:35:34", "remaining_time": "12:17:30"}
{"current_steps": 1315, "total_steps": 4816, "loss": 0.3016, "lr": 3.647170454608846e-05, "epoch": 1.9113372093023255, "percentage": 27.3, "elapsed_time": "4:36:38", "remaining_time": "12:16:29"}
{"current_steps": 1320, "total_steps": 4816, "loss": 0.2843, "lr": 3.643048228549006e-05, "epoch": 1.9186046511627906, "percentage": 27.41, "elapsed_time": "4:37:41", "remaining_time": "12:15:26"}
{"current_steps": 1325, "total_steps": 4816, "loss": 0.3061, "lr": 3.638904419490882e-05, "epoch": 1.9258720930232558, "percentage": 27.51, "elapsed_time": "4:38:47", "remaining_time": "12:14:31"}
{"current_steps": 1330, "total_steps": 4816, "loss": 0.2964, "lr": 3.6347390818673406e-05, "epoch": 1.933139534883721, "percentage": 27.62, "elapsed_time": "4:39:50", "remaining_time": "12:13:29"}
{"current_steps": 1335, "total_steps": 4816, "loss": 0.2857, "lr": 3.6305522703940446e-05, "epoch": 1.940406976744186, "percentage": 27.72, "elapsed_time": "4:40:51", "remaining_time": "12:12:21"}
{"current_steps": 1340, "total_steps": 4816, "loss": 0.2818, "lr": 3.626344040068738e-05, "epoch": 1.947674418604651, "percentage": 27.82, "elapsed_time": "4:41:52", "remaining_time": "12:11:11"}
{"current_steps": 1345, "total_steps": 4816, "loss": 0.2838, "lr": 3.622114446170522e-05, "epoch": 1.9549418604651163, "percentage": 27.93, "elapsed_time": "4:42:56", "remaining_time": "12:10:09"}
{"current_steps": 1350, "total_steps": 4816, "loss": 0.2717, "lr": 3.617863544259127e-05, "epoch": 1.9622093023255816, "percentage": 28.03, "elapsed_time": "4:44:01", "remaining_time": "12:09:12"}
{"current_steps": 1355, "total_steps": 4816, "loss": 0.2658, "lr": 3.613591390174185e-05, "epoch": 1.9694767441860463, "percentage": 28.14, "elapsed_time": "4:45:04", "remaining_time": "12:08:08"}
{"current_steps": 1360, "total_steps": 4816, "loss": 0.2737, "lr": 3.609298040034496e-05, "epoch": 1.9767441860465116, "percentage": 28.24, "elapsed_time": "4:46:02", "remaining_time": "12:06:52"}
{"current_steps": 1365, "total_steps": 4816, "loss": 0.2996, "lr": 3.6049835502372894e-05, "epoch": 1.9840116279069768, "percentage": 28.34, "elapsed_time": "4:47:02", "remaining_time": "12:05:40"}
{"current_steps": 1370, "total_steps": 4816, "loss": 0.2752, "lr": 3.6006479774574846e-05, "epoch": 1.9912790697674418, "percentage": 28.45, "elapsed_time": "4:48:01", "remaining_time": "12:04:29"}
{"current_steps": 1375, "total_steps": 4816, "loss": 0.276, "lr": 3.596291378646947e-05, "epoch": 1.9985465116279069, "percentage": 28.55, "elapsed_time": "4:49:04", "remaining_time": "12:03:26"}
{"current_steps": 1380, "total_steps": 4816, "loss": 0.2784, "lr": 3.591913811033736e-05, "epoch": 2.005813953488372, "percentage": 28.65, "elapsed_time": "4:50:07", "remaining_time": "12:02:21"}
{"current_steps": 1385, "total_steps": 4816, "loss": 0.2654, "lr": 3.58751533212136e-05, "epoch": 2.0130813953488373, "percentage": 28.76, "elapsed_time": "4:51:10", "remaining_time": "12:01:18"}
{"current_steps": 1390, "total_steps": 4816, "loss": 0.263, "lr": 3.5830959996880134e-05, "epoch": 2.020348837209302, "percentage": 28.86, "elapsed_time": "4:52:16", "remaining_time": "12:00:23"}
{"current_steps": 1395, "total_steps": 4816, "loss": 0.2709, "lr": 3.578655871785824e-05, "epoch": 2.0276162790697674, "percentage": 28.97, "elapsed_time": "4:53:25", "remaining_time": "11:59:35"}
{"current_steps": 1400, "total_steps": 4816, "loss": 0.2538, "lr": 3.574195006740087e-05, "epoch": 2.0348837209302326, "percentage": 29.07, "elapsed_time": "4:54:28", "remaining_time": "11:58:31"}
{"current_steps": 1405, "total_steps": 4816, "loss": 0.2547, "lr": 3.5697134631485e-05, "epoch": 2.042151162790698, "percentage": 29.17, "elapsed_time": "4:55:33", "remaining_time": "11:57:31"}
{"current_steps": 1410, "total_steps": 4816, "loss": 0.2763, "lr": 3.5652112998803914e-05, "epoch": 2.0494186046511627, "percentage": 29.28, "elapsed_time": "4:56:32", "remaining_time": "11:56:19"}
{"current_steps": 1415, "total_steps": 4816, "loss": 0.2538, "lr": 3.560688576075951e-05, "epoch": 2.056686046511628, "percentage": 29.38, "elapsed_time": "4:57:36", "remaining_time": "11:55:17"}
{"current_steps": 1420, "total_steps": 4816, "loss": 0.278, "lr": 3.5561453511454485e-05, "epoch": 2.063953488372093, "percentage": 29.49, "elapsed_time": "4:58:44", "remaining_time": "11:54:27"}
{"current_steps": 1425, "total_steps": 4816, "loss": 0.2647, "lr": 3.551581684768457e-05, "epoch": 2.071220930232558, "percentage": 29.59, "elapsed_time": "4:59:46", "remaining_time": "11:53:21"}
{"current_steps": 1430, "total_steps": 4816, "loss": 0.2699, "lr": 3.546997636893067e-05, "epoch": 2.078488372093023, "percentage": 29.69, "elapsed_time": "5:00:43", "remaining_time": "11:52:04"}
{"current_steps": 1435, "total_steps": 4816, "loss": 0.2725, "lr": 3.542393267735098e-05, "epoch": 2.0857558139534884, "percentage": 29.8, "elapsed_time": "5:01:46", "remaining_time": "11:51:01"}
{"current_steps": 1440, "total_steps": 4816, "loss": 0.2795, "lr": 3.537768637777312e-05, "epoch": 2.0930232558139537, "percentage": 29.9, "elapsed_time": "5:02:52", "remaining_time": "11:50:05"}
{"current_steps": 1445, "total_steps": 4816, "loss": 0.2609, "lr": 3.533123807768612e-05, "epoch": 2.1002906976744184, "percentage": 30.0, "elapsed_time": "5:03:57", "remaining_time": "11:49:06"}
{"current_steps": 1450, "total_steps": 4816, "loss": 0.2708, "lr": 3.52845883872325e-05, "epoch": 2.1075581395348837, "percentage": 30.11, "elapsed_time": "5:05:03", "remaining_time": "11:48:08"}
{"current_steps": 1455, "total_steps": 4816, "loss": 0.2636, "lr": 3.523773791920023e-05, "epoch": 2.114825581395349, "percentage": 30.21, "elapsed_time": "5:06:06", "remaining_time": "11:47:04"}
{"current_steps": 1460, "total_steps": 4816, "loss": 0.267, "lr": 3.51906872890147e-05, "epoch": 2.1220930232558137, "percentage": 30.32, "elapsed_time": "5:07:06", "remaining_time": "11:45:56"}
{"current_steps": 1465, "total_steps": 4816, "loss": 0.2655, "lr": 3.514343711473058e-05, "epoch": 2.129360465116279, "percentage": 30.42, "elapsed_time": "5:08:03", "remaining_time": "11:44:37"}
{"current_steps": 1470, "total_steps": 4816, "loss": 0.2563, "lr": 3.509598801702378e-05, "epoch": 2.136627906976744, "percentage": 30.52, "elapsed_time": "5:09:03", "remaining_time": "11:43:29"}
{"current_steps": 1475, "total_steps": 4816, "loss": 0.2591, "lr": 3.504834061918324e-05, "epoch": 2.1438953488372094, "percentage": 30.63, "elapsed_time": "5:10:06", "remaining_time": "11:42:26"}
{"current_steps": 1480, "total_steps": 4816, "loss": 0.2664, "lr": 3.5000495547102766e-05, "epoch": 2.1511627906976742, "percentage": 30.73, "elapsed_time": "5:11:08", "remaining_time": "11:41:19"}
{"current_steps": 1485, "total_steps": 4816, "loss": 0.2625, "lr": 3.49524534292728e-05, "epoch": 2.1584302325581395, "percentage": 30.83, "elapsed_time": "5:12:10", "remaining_time": "11:40:15"}
{"current_steps": 1490, "total_steps": 4816, "loss": 0.2644, "lr": 3.490421489677217e-05, "epoch": 2.1656976744186047, "percentage": 30.94, "elapsed_time": "5:13:12", "remaining_time": "11:39:08"}
{"current_steps": 1495, "total_steps": 4816, "loss": 0.2737, "lr": 3.485578058325979e-05, "epoch": 2.17296511627907, "percentage": 31.04, "elapsed_time": "5:14:15", "remaining_time": "11:38:05"}
{"current_steps": 1500, "total_steps": 4816, "loss": 0.2628, "lr": 3.480715112496634e-05, "epoch": 2.1802325581395348, "percentage": 31.15, "elapsed_time": "5:15:19", "remaining_time": "11:37:05"}
{"current_steps": 1505, "total_steps": 4816, "loss": 0.2624, "lr": 3.475832716068595e-05, "epoch": 2.1875, "percentage": 31.25, "elapsed_time": "5:17:00", "remaining_time": "11:37:24"}
{"current_steps": 1510, "total_steps": 4816, "loss": 0.2595, "lr": 3.47093093317677e-05, "epoch": 2.1947674418604652, "percentage": 31.35, "elapsed_time": "5:18:06", "remaining_time": "11:36:27"}
{"current_steps": 1515, "total_steps": 4816, "loss": 0.2653, "lr": 3.4660098282107344e-05, "epoch": 2.20203488372093, "percentage": 31.46, "elapsed_time": "5:19:06", "remaining_time": "11:35:17"}
{"current_steps": 1520, "total_steps": 4816, "loss": 0.2725, "lr": 3.461069465813871e-05, "epoch": 2.2093023255813953, "percentage": 31.56, "elapsed_time": "5:20:04", "remaining_time": "11:34:03"}
{"current_steps": 1525, "total_steps": 4816, "loss": 0.2703, "lr": 3.4561099108825323e-05, "epoch": 2.2165697674418605, "percentage": 31.67, "elapsed_time": "5:21:05", "remaining_time": "11:32:55"}
{"current_steps": 1530, "total_steps": 4816, "loss": 0.2625, "lr": 3.451131228565179e-05, "epoch": 2.2238372093023258, "percentage": 31.77, "elapsed_time": "5:22:08", "remaining_time": "11:31:51"}
{"current_steps": 1535, "total_steps": 4816, "loss": 0.276, "lr": 3.446133484261529e-05, "epoch": 2.2311046511627906, "percentage": 31.87, "elapsed_time": "5:23:09", "remaining_time": "11:30:43"}
{"current_steps": 1540, "total_steps": 4816, "loss": 0.2742, "lr": 3.4411167436217004e-05, "epoch": 2.238372093023256, "percentage": 31.98, "elapsed_time": "5:24:16", "remaining_time": "11:29:49"}
{"current_steps": 1545, "total_steps": 4816, "loss": 0.2636, "lr": 3.436081072545343e-05, "epoch": 2.245639534883721, "percentage": 32.08, "elapsed_time": "5:25:19", "remaining_time": "11:28:46"}
{"current_steps": 1550, "total_steps": 4816, "loss": 0.276, "lr": 3.4310265371807775e-05, "epoch": 2.2529069767441863, "percentage": 32.18, "elapsed_time": "5:26:20", "remaining_time": "11:27:37"}
{"current_steps": 1555, "total_steps": 4816, "loss": 0.2708, "lr": 3.4259532039241234e-05, "epoch": 2.260174418604651, "percentage": 32.29, "elapsed_time": "5:27:19", "remaining_time": "11:26:25"}
{"current_steps": 1560, "total_steps": 4816, "loss": 0.2662, "lr": 3.420861139418429e-05, "epoch": 2.2674418604651163, "percentage": 32.39, "elapsed_time": "5:28:23", "remaining_time": "11:25:25"}
{"current_steps": 1565, "total_steps": 4816, "loss": 0.2667, "lr": 3.4157504105527976e-05, "epoch": 2.2747093023255816, "percentage": 32.5, "elapsed_time": "5:29:28", "remaining_time": "11:24:25"}
{"current_steps": 1570, "total_steps": 4816, "loss": 0.2877, "lr": 3.410621084461503e-05, "epoch": 2.2819767441860463, "percentage": 32.6, "elapsed_time": "5:30:34", "remaining_time": "11:23:27"}
{"current_steps": 1575, "total_steps": 4816, "loss": 0.2639, "lr": 3.405473228523114e-05, "epoch": 2.2892441860465116, "percentage": 32.7, "elapsed_time": "5:31:30", "remaining_time": "11:22:09"}
{"current_steps": 1580, "total_steps": 4816, "loss": 0.2711, "lr": 3.4003069103596034e-05, "epoch": 2.296511627906977, "percentage": 32.81, "elapsed_time": "5:32:38", "remaining_time": "11:21:16"}
{"current_steps": 1585, "total_steps": 4816, "loss": 0.2722, "lr": 3.395122197835467e-05, "epoch": 2.303779069767442, "percentage": 32.91, "elapsed_time": "5:33:37", "remaining_time": "11:20:05"}
{"current_steps": 1590, "total_steps": 4816, "loss": 0.2656, "lr": 3.389919159056825e-05, "epoch": 2.311046511627907, "percentage": 33.01, "elapsed_time": "5:34:42", "remaining_time": "11:19:06"}
{"current_steps": 1595, "total_steps": 4816, "loss": 0.2731, "lr": 3.384697862370531e-05, "epoch": 2.318313953488372, "percentage": 33.12, "elapsed_time": "5:35:42", "remaining_time": "11:17:56"}
{"current_steps": 1600, "total_steps": 4816, "loss": 0.2588, "lr": 3.379458376363274e-05, "epoch": 2.3255813953488373, "percentage": 33.22, "elapsed_time": "5:36:44", "remaining_time": "11:16:51"}
{"current_steps": 1605, "total_steps": 4816, "loss": 0.2614, "lr": 3.374200769860676e-05, "epoch": 2.332848837209302, "percentage": 33.33, "elapsed_time": "5:37:47", "remaining_time": "11:15:47"}
{"current_steps": 1610, "total_steps": 4816, "loss": 0.2749, "lr": 3.368925111926391e-05, "epoch": 2.3401162790697674, "percentage": 33.43, "elapsed_time": "5:38:47", "remaining_time": "11:14:39"}
{"current_steps": 1615, "total_steps": 4816, "loss": 0.2697, "lr": 3.363631471861194e-05, "epoch": 2.3473837209302326, "percentage": 33.53, "elapsed_time": "5:39:50", "remaining_time": "11:13:34"}
{"current_steps": 1620, "total_steps": 4816, "loss": 0.2671, "lr": 3.358319919202071e-05, "epoch": 2.354651162790698, "percentage": 33.64, "elapsed_time": "5:40:54", "remaining_time": "11:12:33"}
{"current_steps": 1625, "total_steps": 4816, "loss": 0.2756, "lr": 3.35299052372131e-05, "epoch": 2.3619186046511627, "percentage": 33.74, "elapsed_time": "5:41:55", "remaining_time": "11:11:26"}
{"current_steps": 1630, "total_steps": 4816, "loss": 0.2824, "lr": 3.3476433554255806e-05, "epoch": 2.369186046511628, "percentage": 33.85, "elapsed_time": "5:42:59", "remaining_time": "11:10:25"}
{"current_steps": 1635, "total_steps": 4816, "loss": 0.2686, "lr": 3.342278484555014e-05, "epoch": 2.376453488372093, "percentage": 33.95, "elapsed_time": "5:43:58", "remaining_time": "11:09:13"}
{"current_steps": 1640, "total_steps": 4816, "loss": 0.2863, "lr": 3.336895981582282e-05, "epoch": 2.383720930232558, "percentage": 34.05, "elapsed_time": "5:44:58", "remaining_time": "11:08:03"}
{"current_steps": 1645, "total_steps": 4816, "loss": 0.2655, "lr": 3.3314959172116705e-05, "epoch": 2.390988372093023, "percentage": 34.16, "elapsed_time": "5:46:07", "remaining_time": "11:07:12"}
{"current_steps": 1650, "total_steps": 4816, "loss": 0.2635, "lr": 3.326078362378152e-05, "epoch": 2.3982558139534884, "percentage": 34.26, "elapsed_time": "5:47:13", "remaining_time": "11:06:15"}
{"current_steps": 1655, "total_steps": 4816, "loss": 0.255, "lr": 3.320643388246452e-05, "epoch": 2.4055232558139537, "percentage": 34.36, "elapsed_time": "5:48:18", "remaining_time": "11:05:15"}
{"current_steps": 1660, "total_steps": 4816, "loss": 0.2727, "lr": 3.315191066210117e-05, "epoch": 2.4127906976744184, "percentage": 34.47, "elapsed_time": "5:49:19", "remaining_time": "11:04:08"}
{"current_steps": 1665, "total_steps": 4816, "loss": 0.2738, "lr": 3.309721467890571e-05, "epoch": 2.4200581395348837, "percentage": 34.57, "elapsed_time": "5:50:21", "remaining_time": "11:03:03"}
{"current_steps": 1670, "total_steps": 4816, "loss": 0.264, "lr": 3.3042346651361804e-05, "epoch": 2.427325581395349, "percentage": 34.68, "elapsed_time": "5:51:26", "remaining_time": "11:02:02"}
{"current_steps": 1675, "total_steps": 4816, "loss": 0.2645, "lr": 3.298730730021309e-05, "epoch": 2.4345930232558137, "percentage": 34.78, "elapsed_time": "5:52:28", "remaining_time": "11:00:57"}
{"current_steps": 1680, "total_steps": 4816, "loss": 0.2736, "lr": 3.2932097348453696e-05, "epoch": 2.441860465116279, "percentage": 34.88, "elapsed_time": "5:53:29", "remaining_time": "10:59:50"}
{"current_steps": 1685, "total_steps": 4816, "loss": 0.264, "lr": 3.287671752131875e-05, "epoch": 2.449127906976744, "percentage": 34.99, "elapsed_time": "5:54:32", "remaining_time": "10:58:48"}
{"current_steps": 1690, "total_steps": 4816, "loss": 0.2756, "lr": 3.282116854627485e-05, "epoch": 2.4563953488372094, "percentage": 35.09, "elapsed_time": "5:55:41", "remaining_time": "10:57:55"}
{"current_steps": 1695, "total_steps": 4816, "loss": 0.2739, "lr": 3.276545115301053e-05, "epoch": 2.4636627906976742, "percentage": 35.2, "elapsed_time": "5:56:45", "remaining_time": "10:56:54"}
{"current_steps": 1700, "total_steps": 4816, "loss": 0.2682, "lr": 3.270956607342663e-05, "epoch": 2.4709302325581395, "percentage": 35.3, "elapsed_time": "5:57:50", "remaining_time": "10:55:54"}
{"current_steps": 1705, "total_steps": 4816, "loss": 0.2761, "lr": 3.265351404162673e-05, "epoch": 2.4781976744186047, "percentage": 35.4, "elapsed_time": "5:58:57", "remaining_time": "10:54:58"}
{"current_steps": 1710, "total_steps": 4816, "loss": 0.2635, "lr": 3.259729579390749e-05, "epoch": 2.4854651162790695, "percentage": 35.51, "elapsed_time": "5:59:56", "remaining_time": "10:53:48"}
{"current_steps": 1715, "total_steps": 4816, "loss": 0.276, "lr": 3.254091206874895e-05, "epoch": 2.4927325581395348, "percentage": 35.61, "elapsed_time": "6:00:52", "remaining_time": "10:52:30"}
{"current_steps": 1720, "total_steps": 4816, "loss": 0.2559, "lr": 3.248436360680487e-05, "epoch": 2.5, "percentage": 35.71, "elapsed_time": "6:01:53", "remaining_time": "10:51:25"}
{"current_steps": 1725, "total_steps": 4816, "loss": 0.2675, "lr": 3.2427651150892984e-05, "epoch": 2.5072674418604652, "percentage": 35.82, "elapsed_time": "6:02:57", "remaining_time": "10:50:22"}
{"current_steps": 1730, "total_steps": 4816, "loss": 0.2744, "lr": 3.237077544598524e-05, "epoch": 2.5145348837209305, "percentage": 35.92, "elapsed_time": "6:04:03", "remaining_time": "10:49:24"}
{"current_steps": 1735, "total_steps": 4816, "loss": 0.2737, "lr": 3.2313737239198015e-05, "epoch": 2.5218023255813953, "percentage": 36.03, "elapsed_time": "6:05:06", "remaining_time": "10:48:21"}
{"current_steps": 1740, "total_steps": 4816, "loss": 0.2661, "lr": 3.22565372797823e-05, "epoch": 2.5290697674418605, "percentage": 36.13, "elapsed_time": "6:06:08", "remaining_time": "10:47:15"}
{"current_steps": 1745, "total_steps": 4816, "loss": 0.2655, "lr": 3.219917631911387e-05, "epoch": 2.5363372093023253, "percentage": 36.23, "elapsed_time": "6:07:10", "remaining_time": "10:46:10"}
{"current_steps": 1750, "total_steps": 4816, "loss": 0.2567, "lr": 3.2141655110683396e-05, "epoch": 2.5436046511627906, "percentage": 36.34, "elapsed_time": "6:08:03", "remaining_time": "10:44:49"}
{"current_steps": 1755, "total_steps": 4816, "loss": 0.2611, "lr": 3.208397441008655e-05, "epoch": 2.550872093023256, "percentage": 36.44, "elapsed_time": "6:09:04", "remaining_time": "10:43:44"}
{"current_steps": 1760, "total_steps": 4816, "loss": 0.2708, "lr": 3.20261349750141e-05, "epoch": 2.558139534883721, "percentage": 36.54, "elapsed_time": "6:10:07", "remaining_time": "10:42:40"}
{"current_steps": 1765, "total_steps": 4816, "loss": 0.2718, "lr": 3.1968137565241936e-05, "epoch": 2.5654069767441863, "percentage": 36.65, "elapsed_time": "6:11:13", "remaining_time": "10:41:41"}
{"current_steps": 1770, "total_steps": 4816, "loss": 0.2613, "lr": 3.1909982942621085e-05, "epoch": 2.572674418604651, "percentage": 36.75, "elapsed_time": "6:12:18", "remaining_time": "10:40:42"}
{"current_steps": 1775, "total_steps": 4816, "loss": 0.2698, "lr": 3.185167187106774e-05, "epoch": 2.5799418604651163, "percentage": 36.86, "elapsed_time": "6:13:22", "remaining_time": "10:39:41"}
{"current_steps": 1780, "total_steps": 4816, "loss": 0.2575, "lr": 3.179320511655317e-05, "epoch": 2.5872093023255816, "percentage": 36.96, "elapsed_time": "6:14:27", "remaining_time": "10:38:40"}
{"current_steps": 1785, "total_steps": 4816, "loss": 0.2739, "lr": 3.1734583447093696e-05, "epoch": 2.5944767441860463, "percentage": 37.06, "elapsed_time": "6:15:29", "remaining_time": "10:37:36"}
{"current_steps": 1790, "total_steps": 4816, "loss": 0.2731, "lr": 3.167580763274061e-05, "epoch": 2.6017441860465116, "percentage": 37.17, "elapsed_time": "6:16:35", "remaining_time": "10:36:37"}
{"current_steps": 1795, "total_steps": 4816, "loss": 0.2573, "lr": 3.161687844557002e-05, "epoch": 2.609011627906977, "percentage": 37.27, "elapsed_time": "6:17:35", "remaining_time": "10:35:29"}
{"current_steps": 1800, "total_steps": 4816, "loss": 0.2628, "lr": 3.155779665967275e-05, "epoch": 2.616279069767442, "percentage": 37.38, "elapsed_time": "6:18:34", "remaining_time": "10:34:18"}
{"current_steps": 1805, "total_steps": 4816, "loss": 0.2543, "lr": 3.149856305114416e-05, "epoch": 2.623546511627907, "percentage": 37.48, "elapsed_time": "6:19:37", "remaining_time": "10:33:16"}
{"current_steps": 1810, "total_steps": 4816, "loss": 0.2561, "lr": 3.1439178398073896e-05, "epoch": 2.630813953488372, "percentage": 37.58, "elapsed_time": "6:20:39", "remaining_time": "10:32:11"}
{"current_steps": 1815, "total_steps": 4816, "loss": 0.2704, "lr": 3.137964348053578e-05, "epoch": 2.6380813953488373, "percentage": 37.69, "elapsed_time": "6:21:45", "remaining_time": "10:31:12"}
{"current_steps": 1820, "total_steps": 4816, "loss": 0.2818, "lr": 3.1319959080577464e-05, "epoch": 2.645348837209302, "percentage": 37.79, "elapsed_time": "6:22:45", "remaining_time": "10:30:05"}
{"current_steps": 1825, "total_steps": 4816, "loss": 0.2582, "lr": 3.12601259822102e-05, "epoch": 2.6526162790697674, "percentage": 37.89, "elapsed_time": "6:23:52", "remaining_time": "10:29:07"}
{"current_steps": 1830, "total_steps": 4816, "loss": 0.2663, "lr": 3.120014497139853e-05, "epoch": 2.6598837209302326, "percentage": 38.0, "elapsed_time": "6:24:53", "remaining_time": "10:28:02"}
{"current_steps": 1835, "total_steps": 4816, "loss": 0.2655, "lr": 3.114001683604999e-05, "epoch": 2.667151162790698, "percentage": 38.1, "elapsed_time": "6:25:53", "remaining_time": "10:26:53"}
{"current_steps": 1840, "total_steps": 4816, "loss": 0.252, "lr": 3.1079742366004713e-05, "epoch": 2.6744186046511627, "percentage": 38.21, "elapsed_time": "6:26:57", "remaining_time": "10:25:51"}
{"current_steps": 1845, "total_steps": 4816, "loss": 0.2685, "lr": 3.101932235302508e-05, "epoch": 2.681686046511628, "percentage": 38.31, "elapsed_time": "6:27:55", "remaining_time": "10:24:40"}
{"current_steps": 1850, "total_steps": 4816, "loss": 0.2567, "lr": 3.095875759078532e-05, "epoch": 2.688953488372093, "percentage": 38.41, "elapsed_time": "6:28:52", "remaining_time": "10:23:27"}
{"current_steps": 1855, "total_steps": 4816, "loss": 0.2695, "lr": 3.089804887486109e-05, "epoch": 2.696220930232558, "percentage": 38.52, "elapsed_time": "6:29:59", "remaining_time": "10:22:30"}
{"current_steps": 1860, "total_steps": 4816, "loss": 0.2699, "lr": 3.083719700271899e-05, "epoch": 2.703488372093023, "percentage": 38.62, "elapsed_time": "6:31:05", "remaining_time": "10:21:32"}
{"current_steps": 1865, "total_steps": 4816, "loss": 0.2613, "lr": 3.0776202773706136e-05, "epoch": 2.7107558139534884, "percentage": 38.73, "elapsed_time": "6:32:09", "remaining_time": "10:20:31"}
{"current_steps": 1870, "total_steps": 4816, "loss": 0.2583, "lr": 3.0715066989039634e-05, "epoch": 2.7180232558139537, "percentage": 38.83, "elapsed_time": "6:33:15", "remaining_time": "10:19:32"}
{"current_steps": 1875, "total_steps": 4816, "loss": 0.2681, "lr": 3.0653790451796065e-05, "epoch": 2.7252906976744184, "percentage": 38.93, "elapsed_time": "6:34:19", "remaining_time": "10:18:30"}
{"current_steps": 1880, "total_steps": 4816, "loss": 0.2623, "lr": 3.05923739669009e-05, "epoch": 2.7325581395348837, "percentage": 39.04, "elapsed_time": "6:35:19", "remaining_time": "10:17:23"}
{"current_steps": 1885, "total_steps": 4816, "loss": 0.2822, "lr": 3.0530818341117974e-05, "epoch": 2.739825581395349, "percentage": 39.14, "elapsed_time": "6:36:24", "remaining_time": "10:16:23"}
{"current_steps": 1890, "total_steps": 4816, "loss": 0.2689, "lr": 3.046912438303887e-05, "epoch": 2.7470930232558137, "percentage": 39.24, "elapsed_time": "6:37:25", "remaining_time": "10:15:16"}
{"current_steps": 1895, "total_steps": 4816, "loss": 0.2767, "lr": 3.040729290307231e-05, "epoch": 2.754360465116279, "percentage": 39.35, "elapsed_time": "6:38:30", "remaining_time": "10:14:16"}
{"current_steps": 1900, "total_steps": 4816, "loss": 0.2717, "lr": 3.0345324713433454e-05, "epoch": 2.761627906976744, "percentage": 39.45, "elapsed_time": "6:39:26", "remaining_time": "10:13:02"}
{"current_steps": 1905, "total_steps": 4816, "loss": 0.2729, "lr": 3.0283220628133328e-05, "epoch": 2.7688953488372094, "percentage": 39.56, "elapsed_time": "6:40:24", "remaining_time": "10:11:51"}
{"current_steps": 1910, "total_steps": 4816, "loss": 0.2735, "lr": 3.0220981462968038e-05, "epoch": 2.7761627906976747, "percentage": 39.66, "elapsed_time": "6:41:30", "remaining_time": "10:10:52"}
{"current_steps": 1915, "total_steps": 4816, "loss": 0.2646, "lr": 3.0158608035508107e-05, "epoch": 2.7834302325581395, "percentage": 39.76, "elapsed_time": "6:42:30", "remaining_time": "10:09:44"}
{"current_steps": 1920, "total_steps": 4816, "loss": 0.2628, "lr": 3.0096101165087715e-05, "epoch": 2.7906976744186047, "percentage": 39.87, "elapsed_time": "6:43:35", "remaining_time": "10:08:44"}
{"current_steps": 1925, "total_steps": 4816, "loss": 0.2672, "lr": 3.0033461672793946e-05, "epoch": 2.7979651162790695, "percentage": 39.97, "elapsed_time": "6:44:35", "remaining_time": "10:07:37"}
{"current_steps": 1930, "total_steps": 4816, "loss": 0.2502, "lr": 2.9970690381456e-05, "epoch": 2.8052325581395348, "percentage": 40.07, "elapsed_time": "6:45:33", "remaining_time": "10:06:26"}
{"current_steps": 1935, "total_steps": 4816, "loss": 0.2541, "lr": 2.990778811563438e-05, "epoch": 2.8125, "percentage": 40.18, "elapsed_time": "6:46:30", "remaining_time": "10:05:15"}
{"current_steps": 1940, "total_steps": 4816, "loss": 0.2631, "lr": 2.984475570161005e-05, "epoch": 2.8197674418604652, "percentage": 40.28, "elapsed_time": "6:47:32", "remaining_time": "10:04:10"}
{"current_steps": 1945, "total_steps": 4816, "loss": 0.2622, "lr": 2.978159396737363e-05, "epoch": 2.8270348837209305, "percentage": 40.39, "elapsed_time": "6:48:34", "remaining_time": "10:03:05"}
{"current_steps": 1950, "total_steps": 4816, "loss": 0.2545, "lr": 2.9718303742614437e-05, "epoch": 2.8343023255813953, "percentage": 40.49, "elapsed_time": "6:49:39", "remaining_time": "10:02:05"}
{"current_steps": 1955, "total_steps": 4816, "loss": 0.2585, "lr": 2.9654885858709678e-05, "epoch": 2.8415697674418605, "percentage": 40.59, "elapsed_time": "6:50:42", "remaining_time": "10:01:01"}
{"current_steps": 1960, "total_steps": 4816, "loss": 0.2654, "lr": 2.9591341148713444e-05, "epoch": 2.8488372093023253, "percentage": 40.7, "elapsed_time": "6:51:47", "remaining_time": "10:00:03"}
{"current_steps": 1965, "total_steps": 4816, "loss": 0.269, "lr": 2.952767044734584e-05, "epoch": 2.8561046511627906, "percentage": 40.8, "elapsed_time": "6:52:45", "remaining_time": "9:58:51"}
{"current_steps": 1970, "total_steps": 4816, "loss": 0.2542, "lr": 2.946387459098196e-05, "epoch": 2.863372093023256, "percentage": 40.91, "elapsed_time": "6:53:50", "remaining_time": "9:57:52"}
{"current_steps": 1975, "total_steps": 4816, "loss": 0.265, "lr": 2.9399954417640956e-05, "epoch": 2.870639534883721, "percentage": 41.01, "elapsed_time": "6:54:51", "remaining_time": "9:56:45"}
{"current_steps": 1980, "total_steps": 4816, "loss": 0.2777, "lr": 2.9335910766974977e-05, "epoch": 2.8779069767441863, "percentage": 41.11, "elapsed_time": "6:55:56", "remaining_time": "9:55:46"}
{"current_steps": 1985, "total_steps": 4816, "loss": 0.2529, "lr": 2.9271744480258174e-05, "epoch": 2.885174418604651, "percentage": 41.22, "elapsed_time": "6:56:59", "remaining_time": "9:54:43"}
{"current_steps": 1990, "total_steps": 4816, "loss": 0.2762, "lr": 2.9207456400375646e-05, "epoch": 2.8924418604651163, "percentage": 41.32, "elapsed_time": "6:57:59", "remaining_time": "9:53:35"}
{"current_steps": 1995, "total_steps": 4816, "loss": 0.2845, "lr": 2.914304737181234e-05, "epoch": 2.8997093023255816, "percentage": 41.42, "elapsed_time": "6:59:03", "remaining_time": "9:52:33"}
{"current_steps": 2000, "total_steps": 4816, "loss": 0.2688, "lr": 2.9078518240642e-05, "epoch": 2.9069767441860463, "percentage": 41.53, "elapsed_time": "7:00:04", "remaining_time": "9:51:27"}
{"current_steps": 2005, "total_steps": 4816, "loss": 0.2543, "lr": 2.9013869854516028e-05, "epoch": 2.9142441860465116, "percentage": 41.63, "elapsed_time": "7:01:14", "remaining_time": "9:50:34"}
{"current_steps": 2010, "total_steps": 4816, "loss": 0.2635, "lr": 2.894910306265234e-05, "epoch": 2.921511627906977, "percentage": 41.74, "elapsed_time": "7:02:19", "remaining_time": "9:49:34"}
{"current_steps": 2015, "total_steps": 4816, "loss": 0.2726, "lr": 2.888421871582423e-05, "epoch": 2.928779069767442, "percentage": 41.84, "elapsed_time": "7:03:21", "remaining_time": "9:48:30"}
{"current_steps": 2020, "total_steps": 4816, "loss": 0.2622, "lr": 2.8819217666349198e-05, "epoch": 2.936046511627907, "percentage": 41.94, "elapsed_time": "7:04:18", "remaining_time": "9:47:19"}
{"current_steps": 2025, "total_steps": 4816, "loss": 0.2525, "lr": 2.8754100768077743e-05, "epoch": 2.943313953488372, "percentage": 42.05, "elapsed_time": "7:05:19", "remaining_time": "9:46:12"}
{"current_steps": 2030, "total_steps": 4816, "loss": 0.2582, "lr": 2.8688868876382122e-05, "epoch": 2.9505813953488373, "percentage": 42.15, "elapsed_time": "7:06:24", "remaining_time": "9:45:12"}
{"current_steps": 2035, "total_steps": 4816, "loss": 0.2594, "lr": 2.862352284814518e-05, "epoch": 2.957848837209302, "percentage": 42.25, "elapsed_time": "7:07:28", "remaining_time": "9:44:11"}
{"current_steps": 2040, "total_steps": 4816, "loss": 0.2699, "lr": 2.855806354174901e-05, "epoch": 2.9651162790697674, "percentage": 42.36, "elapsed_time": "7:08:32", "remaining_time": "9:43:09"}
{"current_steps": 2045, "total_steps": 4816, "loss": 0.2638, "lr": 2.8492491817063767e-05, "epoch": 2.9723837209302326, "percentage": 42.46, "elapsed_time": "7:09:39", "remaining_time": "9:42:11"}
{"current_steps": 2050, "total_steps": 4816, "loss": 0.254, "lr": 2.8426808535436294e-05, "epoch": 2.979651162790698, "percentage": 42.57, "elapsed_time": "7:10:45", "remaining_time": "9:41:11"}
{"current_steps": 2055, "total_steps": 4816, "loss": 0.2592, "lr": 2.8361014559678856e-05, "epoch": 2.9869186046511627, "percentage": 42.67, "elapsed_time": "7:11:44", "remaining_time": "9:40:04"}
{"current_steps": 2060, "total_steps": 4816, "loss": 0.2552, "lr": 2.8295110754057776e-05, "epoch": 2.994186046511628, "percentage": 42.77, "elapsed_time": "7:12:46", "remaining_time": "9:38:59"}
{"current_steps": 2065, "total_steps": 4816, "loss": 0.2498, "lr": 2.822909798428211e-05, "epoch": 3.001453488372093, "percentage": 42.88, "elapsed_time": "7:13:45", "remaining_time": "9:37:51"}
{"current_steps": 2070, "total_steps": 4816, "loss": 0.2634, "lr": 2.8162977117492257e-05, "epoch": 3.008720930232558, "percentage": 42.98, "elapsed_time": "7:14:51", "remaining_time": "9:36:51"}
{"current_steps": 2075, "total_steps": 4816, "loss": 0.2532, "lr": 2.809674902224857e-05, "epoch": 3.015988372093023, "percentage": 43.09, "elapsed_time": "7:15:53", "remaining_time": "9:35:47"}
{"current_steps": 2080, "total_steps": 4816, "loss": 0.2547, "lr": 2.8030414568519963e-05, "epoch": 3.0232558139534884, "percentage": 43.19, "elapsed_time": "7:16:53", "remaining_time": "9:34:40"}
{"current_steps": 2085, "total_steps": 4816, "loss": 0.2467, "lr": 2.796397462767245e-05, "epoch": 3.0305232558139537, "percentage": 43.29, "elapsed_time": "7:17:55", "remaining_time": "9:33:36"}
{"current_steps": 2090, "total_steps": 4816, "loss": 0.2504, "lr": 2.7897430072457733e-05, "epoch": 3.0377906976744184, "percentage": 43.4, "elapsed_time": "7:19:02", "remaining_time": "9:32:39"}
{"current_steps": 2095, "total_steps": 4816, "loss": 0.2642, "lr": 2.7830781777001706e-05, "epoch": 3.0450581395348837, "percentage": 43.5, "elapsed_time": "7:20:00", "remaining_time": "9:31:29"}
{"current_steps": 2100, "total_steps": 4816, "loss": 0.2567, "lr": 2.7764030616793017e-05, "epoch": 3.052325581395349, "percentage": 43.6, "elapsed_time": "7:21:02", "remaining_time": "9:30:24"}
{"current_steps": 2105, "total_steps": 4816, "loss": 0.2604, "lr": 2.7697177468671516e-05, "epoch": 3.059593023255814, "percentage": 43.71, "elapsed_time": "7:22:03", "remaining_time": "9:29:19"}
{"current_steps": 2110, "total_steps": 4816, "loss": 0.2604, "lr": 2.7630223210816765e-05, "epoch": 3.066860465116279, "percentage": 43.81, "elapsed_time": "7:23:05", "remaining_time": "9:28:14"}
{"current_steps": 2115, "total_steps": 4816, "loss": 0.2624, "lr": 2.7563168722736517e-05, "epoch": 3.074127906976744, "percentage": 43.92, "elapsed_time": "7:24:07", "remaining_time": "9:27:10"}
{"current_steps": 2120, "total_steps": 4816, "loss": 0.2511, "lr": 2.749601488525512e-05, "epoch": 3.0813953488372094, "percentage": 44.02, "elapsed_time": "7:25:11", "remaining_time": "9:26:09"}
{"current_steps": 2125, "total_steps": 4816, "loss": 0.2506, "lr": 2.7428762580501982e-05, "epoch": 3.0886627906976742, "percentage": 44.12, "elapsed_time": "7:26:15", "remaining_time": "9:25:07"}
{"current_steps": 2130, "total_steps": 4816, "loss": 0.2561, "lr": 2.7361412691899972e-05, "epoch": 3.0959302325581395, "percentage": 44.23, "elapsed_time": "7:27:19", "remaining_time": "9:24:05"}
{"current_steps": 2135, "total_steps": 4816, "loss": 0.2423, "lr": 2.7293966104153814e-05, "epoch": 3.1031976744186047, "percentage": 44.33, "elapsed_time": "7:28:19", "remaining_time": "9:22:58"}
{"current_steps": 2140, "total_steps": 4816, "loss": 0.2495, "lr": 2.722642370323847e-05, "epoch": 3.11046511627907, "percentage": 44.44, "elapsed_time": "7:29:26", "remaining_time": "9:22:00"}
{"current_steps": 2145, "total_steps": 4816, "loss": 0.2492, "lr": 2.7158786376387486e-05, "epoch": 3.1177325581395348, "percentage": 44.54, "elapsed_time": "7:30:21", "remaining_time": "9:20:47"}
{"current_steps": 2150, "total_steps": 4816, "loss": 0.2423, "lr": 2.7091055012081376e-05, "epoch": 3.125, "percentage": 44.64, "elapsed_time": "7:31:19", "remaining_time": "9:19:38"}
{"current_steps": 2155, "total_steps": 4816, "loss": 0.2499, "lr": 2.7023230500035896e-05, "epoch": 3.1322674418604652, "percentage": 44.75, "elapsed_time": "7:32:27", "remaining_time": "9:18:41"}
{"current_steps": 2160, "total_steps": 4816, "loss": 0.2605, "lr": 2.6955313731190412e-05, "epoch": 3.13953488372093, "percentage": 44.85, "elapsed_time": "7:33:26", "remaining_time": "9:17:33"}
{"current_steps": 2165, "total_steps": 4816, "loss": 0.2523, "lr": 2.688730559769615e-05, "epoch": 3.1468023255813953, "percentage": 44.95, "elapsed_time": "7:34:27", "remaining_time": "9:16:28"}
{"current_steps": 2170, "total_steps": 4816, "loss": 0.2504, "lr": 2.6819206992904508e-05, "epoch": 3.1540697674418605, "percentage": 45.06, "elapsed_time": "7:35:33", "remaining_time": "9:15:28"}
{"current_steps": 2175, "total_steps": 4816, "loss": 0.2463, "lr": 2.6751018811355307e-05, "epoch": 3.1613372093023258, "percentage": 45.16, "elapsed_time": "7:36:34", "remaining_time": "9:14:23"}
{"current_steps": 2180, "total_steps": 4816, "loss": 0.2454, "lr": 2.6682741948765047e-05, "epoch": 3.1686046511627906, "percentage": 45.27, "elapsed_time": "7:37:37", "remaining_time": "9:13:21"}
{"current_steps": 2185, "total_steps": 4816, "loss": 0.2548, "lr": 2.661437730201514e-05, "epoch": 3.175872093023256, "percentage": 45.37, "elapsed_time": "7:38:41", "remaining_time": "9:12:19"}
{"current_steps": 2190, "total_steps": 4816, "loss": 0.2451, "lr": 2.654592576914011e-05, "epoch": 3.183139534883721, "percentage": 45.47, "elapsed_time": "7:39:44", "remaining_time": "9:11:15"}
{"current_steps": 2195, "total_steps": 4816, "loss": 0.2446, "lr": 2.6477388249315836e-05, "epoch": 3.1904069767441863, "percentage": 45.58, "elapsed_time": "7:40:55", "remaining_time": "9:10:22"}
{"current_steps": 2200, "total_steps": 4816, "loss": 0.2558, "lr": 2.6408765642847698e-05, "epoch": 3.197674418604651, "percentage": 45.68, "elapsed_time": "7:41:58", "remaining_time": "9:09:19"}
{"current_steps": 2205, "total_steps": 4816, "loss": 0.2538, "lr": 2.6340058851158788e-05, "epoch": 3.2049418604651163, "percentage": 45.78, "elapsed_time": "7:42:57", "remaining_time": "9:08:12"}
{"current_steps": 2210, "total_steps": 4816, "loss": 0.2412, "lr": 2.6271268776778032e-05, "epoch": 3.2122093023255816, "percentage": 45.89, "elapsed_time": "7:44:00", "remaining_time": "9:07:08"}
{"current_steps": 2215, "total_steps": 4816, "loss": 0.2435, "lr": 2.6202396323328357e-05, "epoch": 3.2194767441860463, "percentage": 45.99, "elapsed_time": "7:45:02", "remaining_time": "9:06:04"}
{"current_steps": 2220, "total_steps": 4816, "loss": 0.2612, "lr": 2.6133442395514833e-05, "epoch": 3.2267441860465116, "percentage": 46.1, "elapsed_time": "7:46:10", "remaining_time": "9:05:08"}
{"current_steps": 2225, "total_steps": 4816, "loss": 0.2476, "lr": 2.606440789911276e-05, "epoch": 3.234011627906977, "percentage": 46.2, "elapsed_time": "7:47:09", "remaining_time": "9:03:59"}
{"current_steps": 2230, "total_steps": 4816, "loss": 0.2508, "lr": 2.599529374095578e-05, "epoch": 3.241279069767442, "percentage": 46.3, "elapsed_time": "7:48:10", "remaining_time": "9:02:54"}
{"current_steps": 2235, "total_steps": 4816, "loss": 0.2435, "lr": 2.5926100828923985e-05, "epoch": 3.248546511627907, "percentage": 46.41, "elapsed_time": "7:49:11", "remaining_time": "9:01:49"}
{"current_steps": 2240, "total_steps": 4816, "loss": 0.2583, "lr": 2.5856830071931944e-05, "epoch": 3.255813953488372, "percentage": 46.51, "elapsed_time": "7:50:11", "remaining_time": "9:00:42"}
{"current_steps": 2245, "total_steps": 4816, "loss": 0.2588, "lr": 2.578748237991682e-05, "epoch": 3.2630813953488373, "percentage": 46.62, "elapsed_time": "7:51:15", "remaining_time": "8:59:41"}
{"current_steps": 2250, "total_steps": 4816, "loss": 0.2553, "lr": 2.571805866382638e-05, "epoch": 3.270348837209302, "percentage": 46.72, "elapsed_time": "7:52:22", "remaining_time": "8:58:42"}
{"current_steps": 2255, "total_steps": 4816, "loss": 0.245, "lr": 2.5648559835607047e-05, "epoch": 3.2776162790697674, "percentage": 46.82, "elapsed_time": "7:53:28", "remaining_time": "8:57:43"}
{"current_steps": 2260, "total_steps": 4816, "loss": 0.2502, "lr": 2.5578986808191904e-05, "epoch": 3.2848837209302326, "percentage": 46.93, "elapsed_time": "7:54:31", "remaining_time": "8:56:40"}
{"current_steps": 2265, "total_steps": 4816, "loss": 0.2443, "lr": 2.5509340495488707e-05, "epoch": 3.292151162790698, "percentage": 47.03, "elapsed_time": "7:55:36", "remaining_time": "8:55:39"}
{"current_steps": 2270, "total_steps": 4816, "loss": 0.2558, "lr": 2.5439621812367907e-05, "epoch": 3.2994186046511627, "percentage": 47.13, "elapsed_time": "7:56:34", "remaining_time": "8:54:30"}
{"current_steps": 2275, "total_steps": 4816, "loss": 0.2504, "lr": 2.5369831674650572e-05, "epoch": 3.306686046511628, "percentage": 47.24, "elapsed_time": "7:57:36", "remaining_time": "8:53:27"}
{"current_steps": 2280, "total_steps": 4816, "loss": 0.2542, "lr": 2.529997099909643e-05, "epoch": 3.313953488372093, "percentage": 47.34, "elapsed_time": "7:58:31", "remaining_time": "8:52:15"}
{"current_steps": 2285, "total_steps": 4816, "loss": 0.2394, "lr": 2.5230040703391775e-05, "epoch": 3.321220930232558, "percentage": 47.45, "elapsed_time": "7:59:32", "remaining_time": "8:51:10"}
{"current_steps": 2290, "total_steps": 4816, "loss": 0.2497, "lr": 2.5160041706137424e-05, "epoch": 3.328488372093023, "percentage": 47.55, "elapsed_time": "8:00:31", "remaining_time": "8:50:02"}
{"current_steps": 2295, "total_steps": 4816, "loss": 0.2372, "lr": 2.508997492683666e-05, "epoch": 3.3357558139534884, "percentage": 47.65, "elapsed_time": "8:01:33", "remaining_time": "8:48:59"}
{"current_steps": 2300, "total_steps": 4816, "loss": 0.2378, "lr": 2.5019841285883143e-05, "epoch": 3.3430232558139537, "percentage": 47.76, "elapsed_time": "8:02:39", "remaining_time": "8:47:58"}
{"current_steps": 2305, "total_steps": 4816, "loss": 0.2378, "lr": 2.4949641704548834e-05, "epoch": 3.3502906976744184, "percentage": 47.86, "elapsed_time": "8:03:43", "remaining_time": "8:46:57"}
{"current_steps": 2310, "total_steps": 4816, "loss": 0.2462, "lr": 2.4879377104971863e-05, "epoch": 3.3575581395348837, "percentage": 47.97, "elapsed_time": "8:04:49", "remaining_time": "8:45:57"}
{"current_steps": 2315, "total_steps": 4816, "loss": 0.2461, "lr": 2.4809048410144467e-05, "epoch": 3.364825581395349, "percentage": 48.07, "elapsed_time": "8:05:51", "remaining_time": "8:44:53"}
{"current_steps": 2320, "total_steps": 4816, "loss": 0.2436, "lr": 2.4738656543900808e-05, "epoch": 3.3720930232558137, "percentage": 48.17, "elapsed_time": "8:06:55", "remaining_time": "8:43:52"}
{"current_steps": 2325, "total_steps": 4816, "loss": 0.2469, "lr": 2.4668202430904872e-05, "epoch": 3.379360465116279, "percentage": 48.28, "elapsed_time": "8:07:56", "remaining_time": "8:42:46"}
{"current_steps": 2330, "total_steps": 4816, "loss": 0.2584, "lr": 2.4597686996638334e-05, "epoch": 3.386627906976744, "percentage": 48.38, "elapsed_time": "8:08:55", "remaining_time": "8:41:39"}
{"current_steps": 2335, "total_steps": 4816, "loss": 0.2442, "lr": 2.452711116738834e-05, "epoch": 3.3938953488372094, "percentage": 48.48, "elapsed_time": "8:10:01", "remaining_time": "8:40:40"}
{"current_steps": 2340, "total_steps": 4816, "loss": 0.2468, "lr": 2.4456475870235433e-05, "epoch": 3.4011627906976742, "percentage": 48.59, "elapsed_time": "8:11:02", "remaining_time": "8:39:35"}
{"current_steps": 2345, "total_steps": 4816, "loss": 0.2333, "lr": 2.4385782033041282e-05, "epoch": 3.4084302325581395, "percentage": 48.69, "elapsed_time": "8:12:05", "remaining_time": "8:38:31"}
{"current_steps": 2350, "total_steps": 4816, "loss": 0.2453, "lr": 2.431503058443655e-05, "epoch": 3.4156976744186047, "percentage": 48.8, "elapsed_time": "8:13:11", "remaining_time": "8:37:32"}
{"current_steps": 2355, "total_steps": 4816, "loss": 0.2571, "lr": 2.4244222453808694e-05, "epoch": 3.4229651162790695, "percentage": 48.9, "elapsed_time": "8:14:14", "remaining_time": "8:36:28"}
{"current_steps": 2360, "total_steps": 4816, "loss": 0.2532, "lr": 2.4173358571289716e-05, "epoch": 3.4302325581395348, "percentage": 49.0, "elapsed_time": "8:15:15", "remaining_time": "8:35:24"}
{"current_steps": 2365, "total_steps": 4816, "loss": 0.2477, "lr": 2.4102439867743995e-05, "epoch": 3.4375, "percentage": 49.11, "elapsed_time": "8:16:17", "remaining_time": "8:34:20"}
{"current_steps": 2370, "total_steps": 4816, "loss": 0.2402, "lr": 2.4031467274756026e-05, "epoch": 3.4447674418604652, "percentage": 49.21, "elapsed_time": "8:17:23", "remaining_time": "8:33:20"}
{"current_steps": 2375, "total_steps": 4816, "loss": 0.2536, "lr": 2.3960441724618195e-05, "epoch": 3.4520348837209305, "percentage": 49.31, "elapsed_time": "8:18:24", "remaining_time": "8:32:15"}
{"current_steps": 2380, "total_steps": 4816, "loss": 0.2593, "lr": 2.3889364150318523e-05, "epoch": 3.4593023255813953, "percentage": 49.42, "elapsed_time": "8:19:31", "remaining_time": "8:31:16"}
{"current_steps": 2385, "total_steps": 4816, "loss": 0.2612, "lr": 2.3818235485528438e-05, "epoch": 3.4665697674418605, "percentage": 49.52, "elapsed_time": "8:20:39", "remaining_time": "8:30:19"}
{"current_steps": 2390, "total_steps": 4816, "loss": 0.2562, "lr": 2.374705666459046e-05, "epoch": 3.4738372093023258, "percentage": 49.63, "elapsed_time": "8:21:35", "remaining_time": "8:29:08"}
{"current_steps": 2395, "total_steps": 4816, "loss": 0.2451, "lr": 2.367582862250599e-05, "epoch": 3.4811046511627906, "percentage": 49.73, "elapsed_time": "8:22:40", "remaining_time": "8:28:07"}
{"current_steps": 2400, "total_steps": 4816, "loss": 0.2473, "lr": 2.3604552294922974e-05, "epoch": 3.488372093023256, "percentage": 49.83, "elapsed_time": "8:23:47", "remaining_time": "8:27:09"}
{"current_steps": 2405, "total_steps": 4816, "loss": 0.2542, "lr": 2.353322861812364e-05, "epoch": 3.495639534883721, "percentage": 49.94, "elapsed_time": "8:24:49", "remaining_time": "8:26:05"}
{"current_steps": 2410, "total_steps": 4816, "loss": 0.2423, "lr": 2.346185852901219e-05, "epoch": 3.5029069767441863, "percentage": 50.04, "elapsed_time": "8:25:51", "remaining_time": "8:25:00"}
{"current_steps": 2415, "total_steps": 4816, "loss": 0.2449, "lr": 2.3390442965102503e-05, "epoch": 3.510174418604651, "percentage": 50.15, "elapsed_time": "8:26:56", "remaining_time": "8:23:59"}
{"current_steps": 2420, "total_steps": 4816, "loss": 0.2572, "lr": 2.3318982864505806e-05, "epoch": 3.5174418604651163, "percentage": 50.25, "elapsed_time": "8:27:58", "remaining_time": "8:22:56"}
{"current_steps": 2425, "total_steps": 4816, "loss": 0.252, "lr": 2.324747916591836e-05, "epoch": 3.5247093023255816, "percentage": 50.35, "elapsed_time": "8:29:02", "remaining_time": "8:21:53"}
{"current_steps": 2430, "total_steps": 4816, "loss": 0.2333, "lr": 2.317593280860913e-05, "epoch": 3.5319767441860463, "percentage": 50.46, "elapsed_time": "8:30:03", "remaining_time": "8:20:49"}
{"current_steps": 2435, "total_steps": 4816, "loss": 0.2545, "lr": 2.3104344732407436e-05, "epoch": 3.5392441860465116, "percentage": 50.56, "elapsed_time": "8:31:09", "remaining_time": "8:19:49"}
{"current_steps": 2440, "total_steps": 4816, "loss": 0.2392, "lr": 2.3032715877690622e-05, "epoch": 3.546511627906977, "percentage": 50.66, "elapsed_time": "8:32:09", "remaining_time": "8:18:43"}
{"current_steps": 2445, "total_steps": 4816, "loss": 0.2527, "lr": 2.296104718537169e-05, "epoch": 3.553779069767442, "percentage": 50.77, "elapsed_time": "8:33:12", "remaining_time": "8:17:40"}
{"current_steps": 2450, "total_steps": 4816, "loss": 0.2504, "lr": 2.2889339596886958e-05, "epoch": 3.561046511627907, "percentage": 50.87, "elapsed_time": "8:34:15", "remaining_time": "8:16:37"}
{"current_steps": 2455, "total_steps": 4816, "loss": 0.2423, "lr": 2.2817594054183675e-05, "epoch": 3.568313953488372, "percentage": 50.98, "elapsed_time": "8:35:20", "remaining_time": "8:15:36"}
{"current_steps": 2460, "total_steps": 4816, "loss": 0.2575, "lr": 2.2745811499707645e-05, "epoch": 3.5755813953488373, "percentage": 51.08, "elapsed_time": "8:36:22", "remaining_time": "8:14:32"}
{"current_steps": 2465, "total_steps": 4816, "loss": 0.2395, "lr": 2.267399287639088e-05, "epoch": 3.582848837209302, "percentage": 51.18, "elapsed_time": "8:37:21", "remaining_time": "8:13:25"}
{"current_steps": 2470, "total_steps": 4816, "loss": 0.2458, "lr": 2.260213912763917e-05, "epoch": 3.5901162790697674, "percentage": 51.29, "elapsed_time": "8:38:17", "remaining_time": "8:12:16"}
{"current_steps": 2475, "total_steps": 4816, "loss": 0.2409, "lr": 2.2530251197319723e-05, "epoch": 3.5973837209302326, "percentage": 51.39, "elapsed_time": "8:39:18", "remaining_time": "8:11:11"}
{"current_steps": 2480, "total_steps": 4816, "loss": 0.2439, "lr": 2.2458330029748736e-05, "epoch": 3.604651162790698, "percentage": 51.5, "elapsed_time": "8:40:26", "remaining_time": "8:10:12"}
{"current_steps": 2485, "total_steps": 4816, "loss": 0.2604, "lr": 2.2386376569679036e-05, "epoch": 3.6119186046511627, "percentage": 51.6, "elapsed_time": "8:41:34", "remaining_time": "8:09:14"}
{"current_steps": 2490, "total_steps": 4816, "loss": 0.2457, "lr": 2.231439176228763e-05, "epoch": 3.619186046511628, "percentage": 51.7, "elapsed_time": "8:42:38", "remaining_time": "8:08:13"}
{"current_steps": 2495, "total_steps": 4816, "loss": 0.2473, "lr": 2.2242376553163286e-05, "epoch": 3.626453488372093, "percentage": 51.81, "elapsed_time": "8:43:40", "remaining_time": "8:07:09"}
{"current_steps": 2500, "total_steps": 4816, "loss": 0.2541, "lr": 2.217033188829416e-05, "epoch": 3.633720930232558, "percentage": 51.91, "elapsed_time": "8:44:46", "remaining_time": "8:06:09"}
{"current_steps": 2505, "total_steps": 4816, "loss": 0.2523, "lr": 2.2098258714055303e-05, "epoch": 3.640988372093023, "percentage": 52.01, "elapsed_time": "8:45:45", "remaining_time": "8:05:02"}
{"current_steps": 2510, "total_steps": 4816, "loss": 0.2436, "lr": 2.20261579771963e-05, "epoch": 3.6482558139534884, "percentage": 52.12, "elapsed_time": "8:46:49", "remaining_time": "8:04:00"}
{"current_steps": 2515, "total_steps": 4816, "loss": 0.2532, "lr": 2.1954030624828757e-05, "epoch": 3.6555232558139537, "percentage": 52.22, "elapsed_time": "8:47:48", "remaining_time": "8:02:53"}
{"current_steps": 2520, "total_steps": 4816, "loss": 0.2406, "lr": 2.1881877604413927e-05, "epoch": 3.6627906976744184, "percentage": 52.33, "elapsed_time": "8:48:42", "remaining_time": "8:01:43"}
{"current_steps": 2525, "total_steps": 4816, "loss": 0.2497, "lr": 2.1809699863750236e-05, "epoch": 3.6700581395348837, "percentage": 52.43, "elapsed_time": "8:49:41", "remaining_time": "8:00:35"}
{"current_steps": 2530, "total_steps": 4816, "loss": 0.2353, "lr": 2.1737498350960825e-05, "epoch": 3.677325581395349, "percentage": 52.53, "elapsed_time": "8:50:41", "remaining_time": "7:59:30"}
{"current_steps": 2535, "total_steps": 4816, "loss": 0.2528, "lr": 2.1665274014481112e-05, "epoch": 3.6845930232558137, "percentage": 52.64, "elapsed_time": "8:51:41", "remaining_time": "7:58:24"}
{"current_steps": 2540, "total_steps": 4816, "loss": 0.2494, "lr": 2.159302780304631e-05, "epoch": 3.691860465116279, "percentage": 52.74, "elapsed_time": "8:52:44", "remaining_time": "7:57:22"}
{"current_steps": 2545, "total_steps": 4816, "loss": 0.2538, "lr": 2.152076066567901e-05, "epoch": 3.699127906976744, "percentage": 52.84, "elapsed_time": "8:53:52", "remaining_time": "7:56:23"}
{"current_steps": 2550, "total_steps": 4816, "loss": 0.2427, "lr": 2.1448473551676644e-05, "epoch": 3.7063953488372094, "percentage": 52.95, "elapsed_time": "8:54:54", "remaining_time": "7:55:20"}
{"current_steps": 2555, "total_steps": 4816, "loss": 0.2523, "lr": 2.13761674105991e-05, "epoch": 3.7136627906976747, "percentage": 53.05, "elapsed_time": "8:55:58", "remaining_time": "7:54:18"}
{"current_steps": 2560, "total_steps": 4816, "loss": 0.2478, "lr": 2.130384319225617e-05, "epoch": 3.7209302325581395, "percentage": 53.16, "elapsed_time": "8:56:58", "remaining_time": "7:53:12"}
{"current_steps": 2565, "total_steps": 4816, "loss": 0.2399, "lr": 2.1231501846695128e-05, "epoch": 3.7281976744186047, "percentage": 53.26, "elapsed_time": "8:57:58", "remaining_time": "7:52:07"}
{"current_steps": 2570, "total_steps": 4816, "loss": 0.2729, "lr": 2.115914432418822e-05, "epoch": 3.7354651162790695, "percentage": 53.36, "elapsed_time": "8:58:59", "remaining_time": "7:51:02"}
{"current_steps": 2575, "total_steps": 4816, "loss": 0.25, "lr": 2.1086771575220203e-05, "epoch": 3.7427325581395348, "percentage": 53.47, "elapsed_time": "9:00:03", "remaining_time": "7:50:00"}
{"current_steps": 2580, "total_steps": 4816, "loss": 0.2516, "lr": 2.1014384550475836e-05, "epoch": 3.75, "percentage": 53.57, "elapsed_time": "9:01:09", "remaining_time": "7:48:59"}
{"current_steps": 2585, "total_steps": 4816, "loss": 0.2503, "lr": 2.0941984200827402e-05, "epoch": 3.7572674418604652, "percentage": 53.68, "elapsed_time": "9:02:09", "remaining_time": "7:47:54"}
{"current_steps": 2590, "total_steps": 4816, "loss": 0.2449, "lr": 2.0869571477322244e-05, "epoch": 3.7645348837209305, "percentage": 53.78, "elapsed_time": "9:03:14", "remaining_time": "7:46:53"}
{"current_steps": 2595, "total_steps": 4816, "loss": 0.2455, "lr": 2.079714733117021e-05, "epoch": 3.7718023255813953, "percentage": 53.88, "elapsed_time": "9:04:18", "remaining_time": "7:45:52"}
{"current_steps": 2600, "total_steps": 4816, "loss": 0.2485, "lr": 2.0724712713731226e-05, "epoch": 3.7790697674418605, "percentage": 53.99, "elapsed_time": "9:05:18", "remaining_time": "7:44:46"}
{"current_steps": 2605, "total_steps": 4816, "loss": 0.2429, "lr": 2.065226857650275e-05, "epoch": 3.7863372093023253, "percentage": 54.09, "elapsed_time": "9:06:20", "remaining_time": "7:43:42"}
{"current_steps": 2610, "total_steps": 4816, "loss": 0.2548, "lr": 2.0579815871107304e-05, "epoch": 3.7936046511627906, "percentage": 54.19, "elapsed_time": "9:07:19", "remaining_time": "7:42:36"}
{"current_steps": 2615, "total_steps": 4816, "loss": 0.2563, "lr": 2.0507355549279948e-05, "epoch": 3.800872093023256, "percentage": 54.3, "elapsed_time": "9:08:19", "remaining_time": "7:41:30"}
{"current_steps": 2620, "total_steps": 4816, "loss": 0.2539, "lr": 2.04348885628558e-05, "epoch": 3.808139534883721, "percentage": 54.4, "elapsed_time": "9:09:18", "remaining_time": "7:40:24"}
{"current_steps": 2625, "total_steps": 4816, "loss": 0.2587, "lr": 2.036241586375753e-05, "epoch": 3.8154069767441863, "percentage": 54.51, "elapsed_time": "9:10:20", "remaining_time": "7:39:21"}
{"current_steps": 2630, "total_steps": 4816, "loss": 0.2573, "lr": 2.0289938403982834e-05, "epoch": 3.822674418604651, "percentage": 54.61, "elapsed_time": "9:11:27", "remaining_time": "7:38:21"}
{"current_steps": 2635, "total_steps": 4816, "loss": 0.2504, "lr": 2.0217457135591957e-05, "epoch": 3.8299418604651163, "percentage": 54.71, "elapsed_time": "9:12:27", "remaining_time": "7:37:16"}
{"current_steps": 2640, "total_steps": 4816, "loss": 0.2381, "lr": 2.0144973010695157e-05, "epoch": 3.8372093023255816, "percentage": 54.82, "elapsed_time": "9:13:31", "remaining_time": "7:36:14"}
{"current_steps": 2645, "total_steps": 4816, "loss": 0.2644, "lr": 2.0072486981440237e-05, "epoch": 3.8444767441860463, "percentage": 54.92, "elapsed_time": "9:14:33", "remaining_time": "7:35:10"}
{"current_steps": 2650, "total_steps": 4816, "loss": 0.2434, "lr": 2e-05, "epoch": 3.8517441860465116, "percentage": 55.02, "elapsed_time": "9:15:35", "remaining_time": "7:34:06"}
{"current_steps": 2655, "total_steps": 4816, "loss": 0.2588, "lr": 1.9927513018559767e-05, "epoch": 3.859011627906977, "percentage": 55.13, "elapsed_time": "9:16:39", "remaining_time": "7:33:04"}
{"current_steps": 2660, "total_steps": 4816, "loss": 0.2484, "lr": 1.985502698930485e-05, "epoch": 3.866279069767442, "percentage": 55.23, "elapsed_time": "9:17:39", "remaining_time": "7:31:59"}
{"current_steps": 2665, "total_steps": 4816, "loss": 0.256, "lr": 1.978254286440805e-05, "epoch": 3.873546511627907, "percentage": 55.34, "elapsed_time": "9:18:38", "remaining_time": "7:30:54"}
{"current_steps": 2670, "total_steps": 4816, "loss": 0.2522, "lr": 1.9710061596017172e-05, "epoch": 3.880813953488372, "percentage": 55.44, "elapsed_time": "9:19:37", "remaining_time": "7:29:47"}
{"current_steps": 2675, "total_steps": 4816, "loss": 0.2443, "lr": 1.9637584136242474e-05, "epoch": 3.8880813953488373, "percentage": 55.54, "elapsed_time": "9:20:39", "remaining_time": "7:28:44"}
{"current_steps": 2680, "total_steps": 4816, "loss": 0.2456, "lr": 1.9565111437144204e-05, "epoch": 3.895348837209302, "percentage": 55.65, "elapsed_time": "9:21:43", "remaining_time": "7:27:42"}
{"current_steps": 2685, "total_steps": 4816, "loss": 0.2362, "lr": 1.949264445072006e-05, "epoch": 3.9026162790697674, "percentage": 55.75, "elapsed_time": "9:22:48", "remaining_time": "7:26:40"}
{"current_steps": 2690, "total_steps": 4816, "loss": 0.2542, "lr": 1.9420184128892702e-05, "epoch": 3.9098837209302326, "percentage": 55.86, "elapsed_time": "9:23:53", "remaining_time": "7:25:39"}
{"current_steps": 2695, "total_steps": 4816, "loss": 0.2389, "lr": 1.9347731423497255e-05, "epoch": 3.917151162790698, "percentage": 55.96, "elapsed_time": "9:24:56", "remaining_time": "7:24:37"}
{"current_steps": 2700, "total_steps": 4816, "loss": 0.2448, "lr": 1.927528728626878e-05, "epoch": 3.9244186046511627, "percentage": 56.06, "elapsed_time": "9:25:59", "remaining_time": "7:23:34"}
{"current_steps": 2705, "total_steps": 4816, "loss": 0.2359, "lr": 1.9202852668829796e-05, "epoch": 3.931686046511628, "percentage": 56.17, "elapsed_time": "9:27:03", "remaining_time": "7:22:32"}
{"current_steps": 2710, "total_steps": 4816, "loss": 0.26, "lr": 1.9130428522677762e-05, "epoch": 3.938953488372093, "percentage": 56.27, "elapsed_time": "9:28:04", "remaining_time": "7:21:28"}
{"current_steps": 2715, "total_steps": 4816, "loss": 0.2491, "lr": 1.90580157991726e-05, "epoch": 3.946220930232558, "percentage": 56.37, "elapsed_time": "9:29:03", "remaining_time": "7:20:22"}
{"current_steps": 2720, "total_steps": 4816, "loss": 0.2498, "lr": 1.898561544952417e-05, "epoch": 3.953488372093023, "percentage": 56.48, "elapsed_time": "9:30:06", "remaining_time": "7:19:19"}
{"current_steps": 2725, "total_steps": 4816, "loss": 0.2591, "lr": 1.8913228424779807e-05, "epoch": 3.9607558139534884, "percentage": 56.58, "elapsed_time": "9:31:10", "remaining_time": "7:18:16"}
{"current_steps": 2730, "total_steps": 4816, "loss": 0.2475, "lr": 1.8840855675811788e-05, "epoch": 3.9680232558139537, "percentage": 56.69, "elapsed_time": "9:32:17", "remaining_time": "7:17:17"}
{"current_steps": 2735, "total_steps": 4816, "loss": 0.2443, "lr": 1.876849815330488e-05, "epoch": 3.9752906976744184, "percentage": 56.79, "elapsed_time": "9:33:15", "remaining_time": "7:16:10"}
{"current_steps": 2740, "total_steps": 4816, "loss": 0.2465, "lr": 1.869615680774384e-05, "epoch": 3.9825581395348837, "percentage": 56.89, "elapsed_time": "9:34:19", "remaining_time": "7:15:08"}
{"current_steps": 2745, "total_steps": 4816, "loss": 0.2506, "lr": 1.862383258940091e-05, "epoch": 3.989825581395349, "percentage": 57.0, "elapsed_time": "9:35:21", "remaining_time": "7:14:05"}
{"current_steps": 2750, "total_steps": 4816, "loss": 0.2565, "lr": 1.8551526448323366e-05, "epoch": 3.9970930232558137, "percentage": 57.1, "elapsed_time": "9:36:22", "remaining_time": "7:13:00"}
{"current_steps": 2755, "total_steps": 4816, "loss": 0.2407, "lr": 1.8479239334321005e-05, "epoch": 4.004360465116279, "percentage": 57.21, "elapsed_time": "9:37:21", "remaining_time": "7:11:54"}
{"current_steps": 2760, "total_steps": 4816, "loss": 0.2441, "lr": 1.84069721969537e-05, "epoch": 4.011627906976744, "percentage": 57.31, "elapsed_time": "9:38:23", "remaining_time": "7:10:51"}
{"current_steps": 2765, "total_steps": 4816, "loss": 0.2303, "lr": 1.8334725985518898e-05, "epoch": 4.0188953488372094, "percentage": 57.41, "elapsed_time": "9:39:24", "remaining_time": "7:09:47"}
{"current_steps": 2770, "total_steps": 4816, "loss": 0.2244, "lr": 1.8262501649039178e-05, "epoch": 4.026162790697675, "percentage": 57.52, "elapsed_time": "9:40:24", "remaining_time": "7:08:42"}
{"current_steps": 2775, "total_steps": 4816, "loss": 0.2225, "lr": 1.819030013624977e-05, "epoch": 4.03343023255814, "percentage": 57.62, "elapsed_time": "9:41:28", "remaining_time": "7:07:40"}
{"current_steps": 2780, "total_steps": 4816, "loss": 0.2299, "lr": 1.8118122395586076e-05, "epoch": 4.040697674418604, "percentage": 57.72, "elapsed_time": "9:42:29", "remaining_time": "7:06:36"}
{"current_steps": 2785, "total_steps": 4816, "loss": 0.2274, "lr": 1.8045969375171257e-05, "epoch": 4.0479651162790695, "percentage": 57.83, "elapsed_time": "9:43:36", "remaining_time": "7:05:36"}
{"current_steps": 2790, "total_steps": 4816, "loss": 0.2341, "lr": 1.797384202280371e-05, "epoch": 4.055232558139535, "percentage": 57.93, "elapsed_time": "9:44:39", "remaining_time": "7:04:33"}
{"current_steps": 2795, "total_steps": 4816, "loss": 0.2428, "lr": 1.7901741285944703e-05, "epoch": 4.0625, "percentage": 58.04, "elapsed_time": "9:45:44", "remaining_time": "7:03:31"}
{"current_steps": 2800, "total_steps": 4816, "loss": 0.2292, "lr": 1.782966811170585e-05, "epoch": 4.069767441860465, "percentage": 58.14, "elapsed_time": "9:46:44", "remaining_time": "7:02:27"}
{"current_steps": 2805, "total_steps": 4816, "loss": 0.2364, "lr": 1.7757623446836718e-05, "epoch": 4.0770348837209305, "percentage": 58.24, "elapsed_time": "9:47:44", "remaining_time": "7:01:22"}
{"current_steps": 2810, "total_steps": 4816, "loss": 0.2415, "lr": 1.768560823771238e-05, "epoch": 4.084302325581396, "percentage": 58.35, "elapsed_time": "9:48:45", "remaining_time": "7:00:18"}
{"current_steps": 2815, "total_steps": 4816, "loss": 0.2312, "lr": 1.761362343032097e-05, "epoch": 4.09156976744186, "percentage": 58.45, "elapsed_time": "9:49:48", "remaining_time": "6:59:15"}
{"current_steps": 2820, "total_steps": 4816, "loss": 0.2305, "lr": 1.754166997025127e-05, "epoch": 4.098837209302325, "percentage": 58.55, "elapsed_time": "9:50:51", "remaining_time": "6:58:12"}
{"current_steps": 2825, "total_steps": 4816, "loss": 0.2419, "lr": 1.7469748802680284e-05, "epoch": 4.1061046511627906, "percentage": 58.66, "elapsed_time": "9:52:01", "remaining_time": "6:57:15"}
{"current_steps": 2830, "total_steps": 4816, "loss": 0.2266, "lr": 1.739786087236083e-05, "epoch": 4.113372093023256, "percentage": 58.76, "elapsed_time": "9:53:11", "remaining_time": "6:56:16"}
{"current_steps": 2835, "total_steps": 4816, "loss": 0.2294, "lr": 1.7326007123609123e-05, "epoch": 4.120639534883721, "percentage": 58.87, "elapsed_time": "9:54:11", "remaining_time": "6:55:11"}
{"current_steps": 2840, "total_steps": 4816, "loss": 0.2492, "lr": 1.7254188500292355e-05, "epoch": 4.127906976744186, "percentage": 58.97, "elapsed_time": "9:55:08", "remaining_time": "6:54:04"}
{"current_steps": 2845, "total_steps": 4816, "loss": 0.2389, "lr": 1.718240594581633e-05, "epoch": 4.1351744186046515, "percentage": 59.07, "elapsed_time": "9:56:03", "remaining_time": "6:52:57"}
{"current_steps": 2850, "total_steps": 4816, "loss": 0.2469, "lr": 1.7110660403113045e-05, "epoch": 4.142441860465116, "percentage": 59.18, "elapsed_time": "9:57:02", "remaining_time": "6:51:50"}
{"current_steps": 2855, "total_steps": 4816, "loss": 0.2403, "lr": 1.7038952814628312e-05, "epoch": 4.149709302325581, "percentage": 59.28, "elapsed_time": "9:58:06", "remaining_time": "6:50:49"}
{"current_steps": 2860, "total_steps": 4816, "loss": 0.2374, "lr": 1.6967284122309385e-05, "epoch": 4.156976744186046, "percentage": 59.39, "elapsed_time": "9:59:07", "remaining_time": "6:49:45"}
{"current_steps": 2865, "total_steps": 4816, "loss": 0.2343, "lr": 1.6895655267592567e-05, "epoch": 4.164244186046512, "percentage": 59.49, "elapsed_time": "10:00:12", "remaining_time": "6:48:43"}
{"current_steps": 2870, "total_steps": 4816, "loss": 0.238, "lr": 1.6824067191390872e-05, "epoch": 4.171511627906977, "percentage": 59.59, "elapsed_time": "10:01:18", "remaining_time": "6:47:42"}
{"current_steps": 2875, "total_steps": 4816, "loss": 0.2295, "lr": 1.675252083408164e-05, "epoch": 4.178779069767442, "percentage": 59.7, "elapsed_time": "10:02:14", "remaining_time": "6:46:35"}
{"current_steps": 2880, "total_steps": 4816, "loss": 0.2324, "lr": 1.6681017135494194e-05, "epoch": 4.186046511627907, "percentage": 59.8, "elapsed_time": "10:03:15", "remaining_time": "6:45:31"}
{"current_steps": 2885, "total_steps": 4816, "loss": 0.2362, "lr": 1.66095570348975e-05, "epoch": 4.1933139534883725, "percentage": 59.9, "elapsed_time": "10:04:24", "remaining_time": "6:44:32"}
{"current_steps": 2890, "total_steps": 4816, "loss": 0.2374, "lr": 1.653814147098781e-05, "epoch": 4.200581395348837, "percentage": 60.01, "elapsed_time": "10:05:29", "remaining_time": "6:43:31"}
{"current_steps": 2895, "total_steps": 4816, "loss": 0.2351, "lr": 1.6466771381876365e-05, "epoch": 4.207848837209302, "percentage": 60.11, "elapsed_time": "10:06:36", "remaining_time": "6:42:31"}
{"current_steps": 2900, "total_steps": 4816, "loss": 0.2366, "lr": 1.639544770507703e-05, "epoch": 4.215116279069767, "percentage": 60.22, "elapsed_time": "10:07:35", "remaining_time": "6:41:25"}
{"current_steps": 2905, "total_steps": 4816, "loss": 0.2399, "lr": 1.6324171377494015e-05, "epoch": 4.222383720930233, "percentage": 60.32, "elapsed_time": "10:08:38", "remaining_time": "6:40:22"}
{"current_steps": 2910, "total_steps": 4816, "loss": 0.233, "lr": 1.6252943335409542e-05, "epoch": 4.229651162790698, "percentage": 60.42, "elapsed_time": "10:09:43", "remaining_time": "6:39:21"}
{"current_steps": 2915, "total_steps": 4816, "loss": 0.231, "lr": 1.6181764514471566e-05, "epoch": 4.236918604651163, "percentage": 60.53, "elapsed_time": "10:10:46", "remaining_time": "6:38:19"}
{"current_steps": 2920, "total_steps": 4816, "loss": 0.2266, "lr": 1.611063584968148e-05, "epoch": 4.2441860465116275, "percentage": 60.63, "elapsed_time": "10:11:52", "remaining_time": "6:37:17"}
{"current_steps": 2925, "total_steps": 4816, "loss": 0.243, "lr": 1.6039558275381812e-05, "epoch": 4.251453488372093, "percentage": 60.74, "elapsed_time": "10:12:52", "remaining_time": "6:36:13"}
{"current_steps": 2930, "total_steps": 4816, "loss": 0.2305, "lr": 1.596853272524398e-05, "epoch": 4.258720930232558, "percentage": 60.84, "elapsed_time": "10:13:58", "remaining_time": "6:35:12"}
{"current_steps": 2935, "total_steps": 4816, "loss": 0.2348, "lr": 1.5897560132256008e-05, "epoch": 4.265988372093023, "percentage": 60.94, "elapsed_time": "10:15:05", "remaining_time": "6:34:12"}
{"current_steps": 2940, "total_steps": 4816, "loss": 0.2459, "lr": 1.582664142871029e-05, "epoch": 4.273255813953488, "percentage": 61.05, "elapsed_time": "10:16:10", "remaining_time": "6:33:10"}
{"current_steps": 2945, "total_steps": 4816, "loss": 0.2202, "lr": 1.5755777546191313e-05, "epoch": 4.280523255813954, "percentage": 61.15, "elapsed_time": "10:17:11", "remaining_time": "6:32:06"}
{"current_steps": 2950, "total_steps": 4816, "loss": 0.2319, "lr": 1.5684969415563456e-05, "epoch": 4.287790697674419, "percentage": 61.25, "elapsed_time": "10:18:13", "remaining_time": "6:31:03"}
{"current_steps": 2955, "total_steps": 4816, "loss": 0.2385, "lr": 1.5614217966958725e-05, "epoch": 4.295058139534884, "percentage": 61.36, "elapsed_time": "10:19:13", "remaining_time": "6:29:58"}
{"current_steps": 2960, "total_steps": 4816, "loss": 0.2318, "lr": 1.554352412976457e-05, "epoch": 4.3023255813953485, "percentage": 61.46, "elapsed_time": "10:20:17", "remaining_time": "6:28:56"}
{"current_steps": 2965, "total_steps": 4816, "loss": 0.2395, "lr": 1.5472888832611662e-05, "epoch": 4.309593023255814, "percentage": 61.57, "elapsed_time": "10:21:21", "remaining_time": "6:27:54"}
{"current_steps": 2970, "total_steps": 4816, "loss": 0.2455, "lr": 1.5402313003361676e-05, "epoch": 4.316860465116279, "percentage": 61.67, "elapsed_time": "10:22:19", "remaining_time": "6:26:48"}
{"current_steps": 2975, "total_steps": 4816, "loss": 0.2526, "lr": 1.533179756909513e-05, "epoch": 4.324127906976744, "percentage": 61.77, "elapsed_time": "10:23:25", "remaining_time": "6:25:47"}
{"current_steps": 2980, "total_steps": 4816, "loss": 0.2355, "lr": 1.52613434560992e-05, "epoch": 4.3313953488372094, "percentage": 61.88, "elapsed_time": "10:24:25", "remaining_time": "6:24:42"}
{"current_steps": 2985, "total_steps": 4816, "loss": 0.2357, "lr": 1.519095158985554e-05, "epoch": 4.338662790697675, "percentage": 61.98, "elapsed_time": "10:25:29", "remaining_time": "6:23:40"}
{"current_steps": 2990, "total_steps": 4816, "loss": 0.2331, "lr": 1.512062289502814e-05, "epoch": 4.34593023255814, "percentage": 62.08, "elapsed_time": "10:26:28", "remaining_time": "6:22:35"}
{"current_steps": 2995, "total_steps": 4816, "loss": 0.2347, "lr": 1.5050358295451173e-05, "epoch": 4.353197674418604, "percentage": 62.19, "elapsed_time": "10:27:33", "remaining_time": "6:21:33"}
{"current_steps": 3000, "total_steps": 4816, "loss": 0.2283, "lr": 1.4980158714116864e-05, "epoch": 4.3604651162790695, "percentage": 62.29, "elapsed_time": "10:28:39", "remaining_time": "6:20:33"}
{"current_steps": 3005, "total_steps": 4816, "loss": 0.2342, "lr": 1.4910025073163346e-05, "epoch": 4.367732558139535, "percentage": 62.4, "elapsed_time": "10:30:21", "remaining_time": "6:19:53"}
{"current_steps": 3010, "total_steps": 4816, "loss": 0.2446, "lr": 1.4839958293862582e-05, "epoch": 4.375, "percentage": 62.5, "elapsed_time": "10:31:27", "remaining_time": "6:18:52"}
{"current_steps": 3015, "total_steps": 4816, "loss": 0.2426, "lr": 1.4769959296608228e-05, "epoch": 4.382267441860465, "percentage": 62.6, "elapsed_time": "10:32:30", "remaining_time": "6:17:49"}
{"current_steps": 3020, "total_steps": 4816, "loss": 0.2412, "lr": 1.4700029000903575e-05, "epoch": 4.3895348837209305, "percentage": 62.71, "elapsed_time": "10:33:30", "remaining_time": "6:16:44"}
{"current_steps": 3025, "total_steps": 4816, "loss": 0.2526, "lr": 1.463016832534943e-05, "epoch": 4.396802325581396, "percentage": 62.81, "elapsed_time": "10:34:30", "remaining_time": "6:15:40"}
{"current_steps": 3030, "total_steps": 4816, "loss": 0.2349, "lr": 1.4560378187632101e-05, "epoch": 4.40406976744186, "percentage": 62.92, "elapsed_time": "10:35:33", "remaining_time": "6:14:37"}
{"current_steps": 3035, "total_steps": 4816, "loss": 0.2423, "lr": 1.4490659504511295e-05, "epoch": 4.411337209302325, "percentage": 63.02, "elapsed_time": "10:36:36", "remaining_time": "6:13:34"}
{"current_steps": 3040, "total_steps": 4816, "loss": 0.2309, "lr": 1.44210131918081e-05, "epoch": 4.4186046511627906, "percentage": 63.12, "elapsed_time": "10:37:39", "remaining_time": "6:12:31"}
{"current_steps": 3045, "total_steps": 4816, "loss": 0.2356, "lr": 1.4351440164392956e-05, "epoch": 4.425872093023256, "percentage": 63.23, "elapsed_time": "10:38:39", "remaining_time": "6:11:27"}
{"current_steps": 3050, "total_steps": 4816, "loss": 0.2305, "lr": 1.4281941336173621e-05, "epoch": 4.433139534883721, "percentage": 63.33, "elapsed_time": "10:39:42", "remaining_time": "6:10:24"}
{"current_steps": 3055, "total_steps": 4816, "loss": 0.2215, "lr": 1.4212517620083186e-05, "epoch": 4.440406976744186, "percentage": 63.43, "elapsed_time": "10:40:38", "remaining_time": "6:09:17"}
{"current_steps": 3060, "total_steps": 4816, "loss": 0.2333, "lr": 1.4143169928068061e-05, "epoch": 4.4476744186046515, "percentage": 63.54, "elapsed_time": "10:41:45", "remaining_time": "6:08:16"}
{"current_steps": 3065, "total_steps": 4816, "loss": 0.2287, "lr": 1.4073899171076022e-05, "epoch": 4.454941860465116, "percentage": 63.64, "elapsed_time": "10:42:46", "remaining_time": "6:07:12"}
{"current_steps": 3070, "total_steps": 4816, "loss": 0.2261, "lr": 1.400470625904422e-05, "epoch": 4.462209302325581, "percentage": 63.75, "elapsed_time": "10:43:48", "remaining_time": "6:06:08"}
{"current_steps": 3075, "total_steps": 4816, "loss": 0.2281, "lr": 1.3935592100887242e-05, "epoch": 4.469476744186046, "percentage": 63.85, "elapsed_time": "10:44:47", "remaining_time": "6:05:04"}
{"current_steps": 3080, "total_steps": 4816, "loss": 0.2353, "lr": 1.386655760448517e-05, "epoch": 4.476744186046512, "percentage": 63.95, "elapsed_time": "10:45:52", "remaining_time": "6:04:02"}
{"current_steps": 3085, "total_steps": 4816, "loss": 0.2344, "lr": 1.3797603676671646e-05, "epoch": 4.484011627906977, "percentage": 64.06, "elapsed_time": "10:46:51", "remaining_time": "6:02:57"}
{"current_steps": 3090, "total_steps": 4816, "loss": 0.229, "lr": 1.372873122322198e-05, "epoch": 4.491279069767442, "percentage": 64.16, "elapsed_time": "10:47:55", "remaining_time": "6:01:54"}
{"current_steps": 3095, "total_steps": 4816, "loss": 0.2391, "lr": 1.365994114884122e-05, "epoch": 4.498546511627907, "percentage": 64.26, "elapsed_time": "10:49:00", "remaining_time": "6:00:53"}
{"current_steps": 3100, "total_steps": 4816, "loss": 0.2357, "lr": 1.359123435715231e-05, "epoch": 4.5058139534883725, "percentage": 64.37, "elapsed_time": "10:50:02", "remaining_time": "5:59:49"}
{"current_steps": 3105, "total_steps": 4816, "loss": 0.2297, "lr": 1.3522611750684171e-05, "epoch": 4.513081395348837, "percentage": 64.47, "elapsed_time": "10:51:01", "remaining_time": "5:58:44"}
{"current_steps": 3110, "total_steps": 4816, "loss": 0.2428, "lr": 1.3454074230859896e-05, "epoch": 4.520348837209302, "percentage": 64.58, "elapsed_time": "10:52:03", "remaining_time": "5:57:41"}
{"current_steps": 3115, "total_steps": 4816, "loss": 0.2332, "lr": 1.3385622697984872e-05, "epoch": 4.527616279069767, "percentage": 64.68, "elapsed_time": "10:53:01", "remaining_time": "5:56:35"}
{"current_steps": 3120, "total_steps": 4816, "loss": 0.2386, "lr": 1.331725805123496e-05, "epoch": 4.534883720930233, "percentage": 64.78, "elapsed_time": "10:54:04", "remaining_time": "5:55:33"}
{"current_steps": 3125, "total_steps": 4816, "loss": 0.2374, "lr": 1.3248981188644703e-05, "epoch": 4.542151162790698, "percentage": 64.89, "elapsed_time": "10:55:06", "remaining_time": "5:54:29"}
{"current_steps": 3130, "total_steps": 4816, "loss": 0.2296, "lr": 1.3180793007095502e-05, "epoch": 4.549418604651163, "percentage": 64.99, "elapsed_time": "10:56:04", "remaining_time": "5:53:23"}
{"current_steps": 3135, "total_steps": 4816, "loss": 0.2527, "lr": 1.3112694402303863e-05, "epoch": 4.5566860465116275, "percentage": 65.1, "elapsed_time": "10:57:03", "remaining_time": "5:52:18"}
{"current_steps": 3140, "total_steps": 4816, "loss": 0.2489, "lr": 1.3044686268809596e-05, "epoch": 4.563953488372093, "percentage": 65.2, "elapsed_time": "10:58:04", "remaining_time": "5:51:15"}
{"current_steps": 3145, "total_steps": 4816, "loss": 0.236, "lr": 1.2976769499964109e-05, "epoch": 4.571220930232558, "percentage": 65.3, "elapsed_time": "10:59:02", "remaining_time": "5:50:09"}
{"current_steps": 3150, "total_steps": 4816, "loss": 0.2395, "lr": 1.2908944987918633e-05, "epoch": 4.578488372093023, "percentage": 65.41, "elapsed_time": "11:00:10", "remaining_time": "5:49:09"}
{"current_steps": 3155, "total_steps": 4816, "loss": 0.2301, "lr": 1.2841213623612519e-05, "epoch": 4.585755813953488, "percentage": 65.51, "elapsed_time": "11:01:13", "remaining_time": "5:48:06"}
{"current_steps": 3160, "total_steps": 4816, "loss": 0.2346, "lr": 1.2773576296761542e-05, "epoch": 4.593023255813954, "percentage": 65.61, "elapsed_time": "11:02:15", "remaining_time": "5:47:03"}
{"current_steps": 3165, "total_steps": 4816, "loss": 0.2265, "lr": 1.2706033895846192e-05, "epoch": 4.600290697674419, "percentage": 65.72, "elapsed_time": "11:03:22", "remaining_time": "5:46:02"}
{"current_steps": 3170, "total_steps": 4816, "loss": 0.2395, "lr": 1.2638587308100036e-05, "epoch": 4.607558139534884, "percentage": 65.82, "elapsed_time": "11:04:24", "remaining_time": "5:44:59"}
{"current_steps": 3175, "total_steps": 4816, "loss": 0.227, "lr": 1.2571237419498018e-05, "epoch": 4.6148255813953485, "percentage": 65.93, "elapsed_time": "11:05:26", "remaining_time": "5:43:55"}
{"current_steps": 3180, "total_steps": 4816, "loss": 0.2283, "lr": 1.2503985114744883e-05, "epoch": 4.622093023255814, "percentage": 66.03, "elapsed_time": "11:06:30", "remaining_time": "5:42:53"}
{"current_steps": 3185, "total_steps": 4816, "loss": 0.2497, "lr": 1.2436831277263481e-05, "epoch": 4.629360465116279, "percentage": 66.13, "elapsed_time": "11:07:37", "remaining_time": "5:41:53"}
{"current_steps": 3190, "total_steps": 4816, "loss": 0.2417, "lr": 1.2369776789183234e-05, "epoch": 4.636627906976744, "percentage": 66.24, "elapsed_time": "11:08:39", "remaining_time": "5:40:49"}
{"current_steps": 3195, "total_steps": 4816, "loss": 0.238, "lr": 1.230282253132849e-05, "epoch": 4.6438953488372094, "percentage": 66.34, "elapsed_time": "11:09:32", "remaining_time": "5:39:41"}
{"current_steps": 3200, "total_steps": 4816, "loss": 0.2459, "lr": 1.2235969383206987e-05, "epoch": 4.651162790697675, "percentage": 66.45, "elapsed_time": "11:10:35", "remaining_time": "5:38:39"}
{"current_steps": 3205, "total_steps": 4816, "loss": 0.2293, "lr": 1.2169218222998294e-05, "epoch": 4.658430232558139, "percentage": 66.55, "elapsed_time": "11:11:34", "remaining_time": "5:37:33"}
{"current_steps": 3210, "total_steps": 4816, "loss": 0.237, "lr": 1.2102569927542275e-05, "epoch": 4.665697674418604, "percentage": 66.65, "elapsed_time": "11:12:34", "remaining_time": "5:36:29"}
{"current_steps": 3215, "total_steps": 4816, "loss": 0.2292, "lr": 1.2036025372327553e-05, "epoch": 4.6729651162790695, "percentage": 66.76, "elapsed_time": "11:13:43", "remaining_time": "5:35:29"}
{"current_steps": 3220, "total_steps": 4816, "loss": 0.2418, "lr": 1.1969585431480037e-05, "epoch": 4.680232558139535, "percentage": 66.86, "elapsed_time": "11:14:39", "remaining_time": "5:34:23"}
{"current_steps": 3225, "total_steps": 4816, "loss": 0.2291, "lr": 1.1903250977751429e-05, "epoch": 4.6875, "percentage": 66.96, "elapsed_time": "11:15:31", "remaining_time": "5:33:15"}
{"current_steps": 3230, "total_steps": 4816, "loss": 0.2325, "lr": 1.1837022882507745e-05, "epoch": 4.694767441860465, "percentage": 67.07, "elapsed_time": "11:16:30", "remaining_time": "5:32:10"}
{"current_steps": 3235, "total_steps": 4816, "loss": 0.2303, "lr": 1.1770902015717894e-05, "epoch": 4.7020348837209305, "percentage": 67.17, "elapsed_time": "11:17:35", "remaining_time": "5:31:09"}
{"current_steps": 3240, "total_steps": 4816, "loss": 0.2349, "lr": 1.1704889245942229e-05, "epoch": 4.709302325581396, "percentage": 67.28, "elapsed_time": "11:18:39", "remaining_time": "5:30:06"}
{"current_steps": 3245, "total_steps": 4816, "loss": 0.2286, "lr": 1.163898544032115e-05, "epoch": 4.716569767441861, "percentage": 67.38, "elapsed_time": "11:19:42", "remaining_time": "5:29:03"}
{"current_steps": 3250, "total_steps": 4816, "loss": 0.2372, "lr": 1.1573191464563709e-05, "epoch": 4.723837209302325, "percentage": 67.48, "elapsed_time": "11:20:48", "remaining_time": "5:28:02"}
{"current_steps": 3255, "total_steps": 4816, "loss": 0.242, "lr": 1.1507508182936231e-05, "epoch": 4.7311046511627906, "percentage": 67.59, "elapsed_time": "11:21:48", "remaining_time": "5:26:58"}
{"current_steps": 3260, "total_steps": 4816, "loss": 0.2338, "lr": 1.144193645825099e-05, "epoch": 4.738372093023256, "percentage": 67.69, "elapsed_time": "11:22:54", "remaining_time": "5:25:57"}
{"current_steps": 3265, "total_steps": 4816, "loss": 0.2282, "lr": 1.1376477151854832e-05, "epoch": 4.745639534883721, "percentage": 67.79, "elapsed_time": "11:23:59", "remaining_time": "5:24:55"}
{"current_steps": 3270, "total_steps": 4816, "loss": 0.2343, "lr": 1.131113112361788e-05, "epoch": 4.752906976744186, "percentage": 67.9, "elapsed_time": "11:24:56", "remaining_time": "5:23:49"}
{"current_steps": 3275, "total_steps": 4816, "loss": 0.2296, "lr": 1.1245899231922265e-05, "epoch": 4.7601744186046515, "percentage": 68.0, "elapsed_time": "11:26:02", "remaining_time": "5:22:48"}
{"current_steps": 3280, "total_steps": 4816, "loss": 0.2324, "lr": 1.1180782333650807e-05, "epoch": 4.767441860465116, "percentage": 68.11, "elapsed_time": "11:27:04", "remaining_time": "5:21:45"}
{"current_steps": 3285, "total_steps": 4816, "loss": 0.2345, "lr": 1.1115781284175777e-05, "epoch": 4.774709302325581, "percentage": 68.21, "elapsed_time": "11:28:09", "remaining_time": "5:20:43"}
{"current_steps": 3290, "total_steps": 4816, "loss": 0.2495, "lr": 1.1050896937347666e-05, "epoch": 4.781976744186046, "percentage": 68.31, "elapsed_time": "11:29:10", "remaining_time": "5:19:39"}
{"current_steps": 3295, "total_steps": 4816, "loss": 0.2369, "lr": 1.098613014548398e-05, "epoch": 4.789244186046512, "percentage": 68.42, "elapsed_time": "11:30:13", "remaining_time": "5:18:36"}
{"current_steps": 3300, "total_steps": 4816, "loss": 0.2396, "lr": 1.0921481759358005e-05, "epoch": 4.796511627906977, "percentage": 68.52, "elapsed_time": "11:31:18", "remaining_time": "5:17:35"}
{"current_steps": 3305, "total_steps": 4816, "loss": 0.231, "lr": 1.0856952628187662e-05, "epoch": 4.803779069767442, "percentage": 68.63, "elapsed_time": "11:32:19", "remaining_time": "5:16:31"}
{"current_steps": 3310, "total_steps": 4816, "loss": 0.2336, "lr": 1.079254359962436e-05, "epoch": 4.811046511627907, "percentage": 68.73, "elapsed_time": "11:33:20", "remaining_time": "5:15:27"}
{"current_steps": 3315, "total_steps": 4816, "loss": 0.2372, "lr": 1.0728255519741831e-05, "epoch": 4.8183139534883725, "percentage": 68.83, "elapsed_time": "11:34:20", "remaining_time": "5:14:23"}
{"current_steps": 3320, "total_steps": 4816, "loss": 0.2455, "lr": 1.066408923302503e-05, "epoch": 4.825581395348837, "percentage": 68.94, "elapsed_time": "11:35:24", "remaining_time": "5:13:20"}
{"current_steps": 3325, "total_steps": 4816, "loss": 0.2407, "lr": 1.060004558235905e-05, "epoch": 4.832848837209302, "percentage": 69.04, "elapsed_time": "11:36:28", "remaining_time": "5:12:18"}
{"current_steps": 3330, "total_steps": 4816, "loss": 0.2304, "lr": 1.0536125409018043e-05, "epoch": 4.840116279069767, "percentage": 69.14, "elapsed_time": "11:37:33", "remaining_time": "5:11:17"}
{"current_steps": 3335, "total_steps": 4816, "loss": 0.2293, "lr": 1.0472329552654172e-05, "epoch": 4.847383720930233, "percentage": 69.25, "elapsed_time": "11:38:37", "remaining_time": "5:10:14"}
{"current_steps": 3340, "total_steps": 4816, "loss": 0.2346, "lr": 1.040865885128656e-05, "epoch": 4.854651162790698, "percentage": 69.35, "elapsed_time": "11:39:44", "remaining_time": "5:09:13"}
{"current_steps": 3345, "total_steps": 4816, "loss": 0.253, "lr": 1.034511414129033e-05, "epoch": 4.861918604651163, "percentage": 69.46, "elapsed_time": "11:40:42", "remaining_time": "5:08:08"}
{"current_steps": 3350, "total_steps": 4816, "loss": 0.2369, "lr": 1.0281696257385566e-05, "epoch": 4.8691860465116275, "percentage": 69.56, "elapsed_time": "11:41:44", "remaining_time": "5:07:05"}
{"current_steps": 3355, "total_steps": 4816, "loss": 0.2243, "lr": 1.0218406032626383e-05, "epoch": 4.876453488372093, "percentage": 69.66, "elapsed_time": "11:42:50", "remaining_time": "5:06:04"}
{"current_steps": 3360, "total_steps": 4816, "loss": 0.2348, "lr": 1.015524429838995e-05, "epoch": 4.883720930232558, "percentage": 69.77, "elapsed_time": "11:43:50", "remaining_time": "5:05:00"}
{"current_steps": 3365, "total_steps": 4816, "loss": 0.2313, "lr": 1.009221188436563e-05, "epoch": 4.890988372093023, "percentage": 69.87, "elapsed_time": "11:44:54", "remaining_time": "5:03:57"}
{"current_steps": 3370, "total_steps": 4816, "loss": 0.2366, "lr": 1.0029309618544008e-05, "epoch": 4.898255813953488, "percentage": 69.98, "elapsed_time": "11:45:54", "remaining_time": "5:02:53"}
{"current_steps": 3375, "total_steps": 4816, "loss": 0.2414, "lr": 9.966538327206055e-06, "epoch": 4.905523255813954, "percentage": 70.08, "elapsed_time": "11:46:56", "remaining_time": "5:01:50"}
{"current_steps": 3380, "total_steps": 4816, "loss": 0.2358, "lr": 9.903898834912288e-06, "epoch": 4.912790697674419, "percentage": 70.18, "elapsed_time": "11:47:58", "remaining_time": "5:00:47"}
{"current_steps": 3385, "total_steps": 4816, "loss": 0.2605, "lr": 9.8413919644919e-06, "epoch": 4.920058139534884, "percentage": 70.29, "elapsed_time": "11:49:07", "remaining_time": "4:59:46"}
{"current_steps": 3390, "total_steps": 4816, "loss": 0.2464, "lr": 9.77901853703197e-06, "epoch": 4.9273255813953485, "percentage": 70.39, "elapsed_time": "11:50:10", "remaining_time": "4:58:44"}
{"current_steps": 3395, "total_steps": 4816, "loss": 0.2372, "lr": 9.716779371866674e-06, "epoch": 4.934593023255814, "percentage": 70.49, "elapsed_time": "11:51:15", "remaining_time": "4:57:42"}
{"current_steps": 3400, "total_steps": 4816, "loss": 0.2347, "lr": 9.654675286566548e-06, "epoch": 4.941860465116279, "percentage": 70.6, "elapsed_time": "11:52:21", "remaining_time": "4:56:40"}
{"current_steps": 3405, "total_steps": 4816, "loss": 0.2219, "lr": 9.592707096927704e-06, "epoch": 4.949127906976744, "percentage": 70.7, "elapsed_time": "11:53:21", "remaining_time": "4:55:36"}
{"current_steps": 3410, "total_steps": 4816, "loss": 0.2336, "lr": 9.53087561696113e-06, "epoch": 4.9563953488372094, "percentage": 70.81, "elapsed_time": "11:54:21", "remaining_time": "4:54:32"}
{"current_steps": 3415, "total_steps": 4816, "loss": 0.2459, "lr": 9.469181658882034e-06, "epoch": 4.963662790697675, "percentage": 70.91, "elapsed_time": "11:55:22", "remaining_time": "4:53:28"}
{"current_steps": 3420, "total_steps": 4816, "loss": 0.238, "lr": 9.40762603309911e-06, "epoch": 4.970930232558139, "percentage": 71.01, "elapsed_time": "11:56:24", "remaining_time": "4:52:25"}
{"current_steps": 3425, "total_steps": 4816, "loss": 0.2319, "lr": 9.346209548203947e-06, "epoch": 4.978197674418604, "percentage": 71.12, "elapsed_time": "11:57:28", "remaining_time": "4:51:23"}
{"current_steps": 3430, "total_steps": 4816, "loss": 0.2512, "lr": 9.284933010960364e-06, "epoch": 4.9854651162790695, "percentage": 71.22, "elapsed_time": "11:58:34", "remaining_time": "4:50:21"}
{"current_steps": 3435, "total_steps": 4816, "loss": 0.231, "lr": 9.223797226293867e-06, "epoch": 4.992732558139535, "percentage": 71.32, "elapsed_time": "11:59:38", "remaining_time": "4:49:19"}
{"current_steps": 3440, "total_steps": 4816, "loss": 0.2371, "lr": 9.162802997281022e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "12:00:39", "remaining_time": "4:48:15"}
{"current_steps": 3445, "total_steps": 4816, "loss": 0.2274, "lr": 9.10195112513892e-06, "epoch": 5.007267441860465, "percentage": 71.53, "elapsed_time": "12:01:39", "remaining_time": "4:47:11"}
{"current_steps": 3450, "total_steps": 4816, "loss": 0.219, "lr": 9.041242409214686e-06, "epoch": 5.0145348837209305, "percentage": 71.64, "elapsed_time": "12:02:45", "remaining_time": "4:46:10"}
{"current_steps": 3455, "total_steps": 4816, "loss": 0.2222, "lr": 8.980677646974926e-06, "epoch": 5.021802325581396, "percentage": 71.74, "elapsed_time": "12:03:50", "remaining_time": "4:45:08"}
{"current_steps": 3460, "total_steps": 4816, "loss": 0.2215, "lr": 8.920257633995295e-06, "epoch": 5.02906976744186, "percentage": 71.84, "elapsed_time": "12:04:49", "remaining_time": "4:44:04"}
{"current_steps": 3465, "total_steps": 4816, "loss": 0.2304, "lr": 8.85998316395001e-06, "epoch": 5.036337209302325, "percentage": 71.95, "elapsed_time": "12:05:43", "remaining_time": "4:42:57"}
{"current_steps": 3470, "total_steps": 4816, "loss": 0.2313, "lr": 8.799855028601472e-06, "epoch": 5.0436046511627906, "percentage": 72.05, "elapsed_time": "12:06:45", "remaining_time": "4:41:54"}
{"current_steps": 3475, "total_steps": 4816, "loss": 0.223, "lr": 8.739874017789813e-06, "epoch": 5.050872093023256, "percentage": 72.16, "elapsed_time": "12:07:47", "remaining_time": "4:40:51"}
{"current_steps": 3480, "total_steps": 4816, "loss": 0.2288, "lr": 8.680040919422544e-06, "epoch": 5.058139534883721, "percentage": 72.26, "elapsed_time": "12:08:49", "remaining_time": "4:39:48"}
{"current_steps": 3485, "total_steps": 4816, "loss": 0.2262, "lr": 8.620356519464228e-06, "epoch": 5.065406976744186, "percentage": 72.36, "elapsed_time": "12:09:52", "remaining_time": "4:38:45"}
{"current_steps": 3490, "total_steps": 4816, "loss": 0.2416, "lr": 8.560821601926112e-06, "epoch": 5.0726744186046515, "percentage": 72.47, "elapsed_time": "12:10:58", "remaining_time": "4:37:43"}
{"current_steps": 3495, "total_steps": 4816, "loss": 0.2155, "lr": 8.501436948855857e-06, "epoch": 5.079941860465116, "percentage": 72.57, "elapsed_time": "12:12:01", "remaining_time": "4:36:41"}
{"current_steps": 3500, "total_steps": 4816, "loss": 0.2137, "lr": 8.44220334032725e-06, "epoch": 5.087209302325581, "percentage": 72.67, "elapsed_time": "12:13:03", "remaining_time": "4:35:37"}
{"current_steps": 3505, "total_steps": 4816, "loss": 0.2239, "lr": 8.383121554429985e-06, "epoch": 5.094476744186046, "percentage": 72.78, "elapsed_time": "12:14:07", "remaining_time": "4:34:35"}
{"current_steps": 3510, "total_steps": 4816, "loss": 0.222, "lr": 8.3241923672594e-06, "epoch": 5.101744186046512, "percentage": 72.88, "elapsed_time": "12:15:05", "remaining_time": "4:33:30"}
{"current_steps": 3515, "total_steps": 4816, "loss": 0.2308, "lr": 8.265416552906316e-06, "epoch": 5.109011627906977, "percentage": 72.99, "elapsed_time": "12:16:09", "remaining_time": "4:32:28"}
{"current_steps": 3520, "total_steps": 4816, "loss": 0.2181, "lr": 8.20679488344684e-06, "epoch": 5.116279069767442, "percentage": 73.09, "elapsed_time": "12:17:07", "remaining_time": "4:31:23"}
{"current_steps": 3525, "total_steps": 4816, "loss": 0.2286, "lr": 8.148328128932263e-06, "epoch": 5.123546511627907, "percentage": 73.19, "elapsed_time": "12:18:10", "remaining_time": "4:30:20"}
{"current_steps": 3530, "total_steps": 4816, "loss": 0.2332, "lr": 8.090017057378913e-06, "epoch": 5.1308139534883725, "percentage": 73.3, "elapsed_time": "12:19:16", "remaining_time": "4:29:19"}
{"current_steps": 3535, "total_steps": 4816, "loss": 0.2325, "lr": 8.03186243475807e-06, "epoch": 5.138081395348837, "percentage": 73.4, "elapsed_time": "12:20:10", "remaining_time": "4:28:13"}
{"current_steps": 3540, "total_steps": 4816, "loss": 0.2221, "lr": 7.9738650249859e-06, "epoch": 5.145348837209302, "percentage": 73.5, "elapsed_time": "12:21:08", "remaining_time": "4:27:08"}
{"current_steps": 3545, "total_steps": 4816, "loss": 0.2243, "lr": 7.916025589913452e-06, "epoch": 5.152616279069767, "percentage": 73.61, "elapsed_time": "12:22:08", "remaining_time": "4:26:05"}
{"current_steps": 3550, "total_steps": 4816, "loss": 0.2212, "lr": 7.858344889316611e-06, "epoch": 5.159883720930233, "percentage": 73.71, "elapsed_time": "12:23:13", "remaining_time": "4:25:02"}
{"current_steps": 3555, "total_steps": 4816, "loss": 0.224, "lr": 7.80082368088613e-06, "epoch": 5.167151162790698, "percentage": 73.82, "elapsed_time": "12:24:19", "remaining_time": "4:24:01"}
{"current_steps": 3560, "total_steps": 4816, "loss": 0.2348, "lr": 7.743462720217698e-06, "epoch": 5.174418604651163, "percentage": 73.92, "elapsed_time": "12:25:17", "remaining_time": "4:22:56"}
{"current_steps": 3565, "total_steps": 4816, "loss": 0.2211, "lr": 7.686262760801985e-06, "epoch": 5.1816860465116275, "percentage": 74.02, "elapsed_time": "12:26:16", "remaining_time": "4:21:52"}
{"current_steps": 3570, "total_steps": 4816, "loss": 0.231, "lr": 7.629224554014763e-06, "epoch": 5.188953488372093, "percentage": 74.13, "elapsed_time": "12:27:12", "remaining_time": "4:20:47"}
{"current_steps": 3575, "total_steps": 4816, "loss": 0.2208, "lr": 7.5723488491070116e-06, "epoch": 5.196220930232558, "percentage": 74.23, "elapsed_time": "12:28:11", "remaining_time": "4:19:43"}
{"current_steps": 3580, "total_steps": 4816, "loss": 0.2126, "lr": 7.515636393195129e-06, "epoch": 5.203488372093023, "percentage": 74.34, "elapsed_time": "12:29:13", "remaining_time": "4:18:40"}
{"current_steps": 3585, "total_steps": 4816, "loss": 0.2276, "lr": 7.459087931251052e-06, "epoch": 5.210755813953488, "percentage": 74.44, "elapsed_time": "12:30:17", "remaining_time": "4:17:37"}
{"current_steps": 3590, "total_steps": 4816, "loss": 0.2144, "lr": 7.402704206092508e-06, "epoch": 5.218023255813954, "percentage": 74.54, "elapsed_time": "12:31:08", "remaining_time": "4:16:31"}
{"current_steps": 3595, "total_steps": 4816, "loss": 0.2218, "lr": 7.346485958373266e-06, "epoch": 5.225290697674419, "percentage": 74.65, "elapsed_time": "12:32:15", "remaining_time": "4:15:29"}
{"current_steps": 3600, "total_steps": 4816, "loss": 0.2369, "lr": 7.290433926573373e-06, "epoch": 5.232558139534884, "percentage": 74.75, "elapsed_time": "12:33:14", "remaining_time": "4:14:25"}
{"current_steps": 3605, "total_steps": 4816, "loss": 0.2232, "lr": 7.234548846989478e-06, "epoch": 5.2398255813953485, "percentage": 74.85, "elapsed_time": "12:34:15", "remaining_time": "4:13:22"}
{"current_steps": 3610, "total_steps": 4816, "loss": 0.2318, "lr": 7.17883145372515e-06, "epoch": 5.247093023255814, "percentage": 74.96, "elapsed_time": "12:35:19", "remaining_time": "4:12:19"}
{"current_steps": 3615, "total_steps": 4816, "loss": 0.2341, "lr": 7.123282478681255e-06, "epoch": 5.254360465116279, "percentage": 75.06, "elapsed_time": "12:36:18", "remaining_time": "4:11:16"}
{"current_steps": 3620, "total_steps": 4816, "loss": 0.2314, "lr": 7.06790265154631e-06, "epoch": 5.261627906976744, "percentage": 75.17, "elapsed_time": "12:37:22", "remaining_time": "4:10:13"}
{"current_steps": 3625, "total_steps": 4816, "loss": 0.211, "lr": 7.012692699786918e-06, "epoch": 5.2688953488372094, "percentage": 75.27, "elapsed_time": "12:38:25", "remaining_time": "4:09:10"}
{"current_steps": 3630, "total_steps": 4816, "loss": 0.233, "lr": 6.9576533486382004e-06, "epoch": 5.276162790697675, "percentage": 75.37, "elapsed_time": "12:39:25", "remaining_time": "4:08:07"}
{"current_steps": 3635, "total_steps": 4816, "loss": 0.2186, "lr": 6.902785321094301e-06, "epoch": 5.28343023255814, "percentage": 75.48, "elapsed_time": "12:40:31", "remaining_time": "4:07:05"}
{"current_steps": 3640, "total_steps": 4816, "loss": 0.2314, "lr": 6.84808933789884e-06, "epoch": 5.290697674418604, "percentage": 75.58, "elapsed_time": "12:41:31", "remaining_time": "4:06:01"}
{"current_steps": 3645, "total_steps": 4816, "loss": 0.2234, "lr": 6.793566117535475e-06, "epoch": 5.2979651162790695, "percentage": 75.69, "elapsed_time": "12:42:29", "remaining_time": "4:04:57"}
{"current_steps": 3650, "total_steps": 4816, "loss": 0.2258, "lr": 6.739216376218483e-06, "epoch": 5.305232558139535, "percentage": 75.79, "elapsed_time": "12:43:35", "remaining_time": "4:03:55"}
{"current_steps": 3655, "total_steps": 4816, "loss": 0.2309, "lr": 6.6850408278833e-06, "epoch": 5.3125, "percentage": 75.89, "elapsed_time": "12:44:37", "remaining_time": "4:02:52"}
{"current_steps": 3660, "total_steps": 4816, "loss": 0.2197, "lr": 6.631040184177191e-06, "epoch": 5.319767441860465, "percentage": 76.0, "elapsed_time": "12:45:42", "remaining_time": "4:01:50"}
{"current_steps": 3665, "total_steps": 4816, "loss": 0.2209, "lr": 6.577215154449863e-06, "epoch": 5.3270348837209305, "percentage": 76.1, "elapsed_time": "12:46:43", "remaining_time": "4:00:47"}
{"current_steps": 3670, "total_steps": 4816, "loss": 0.2327, "lr": 6.523566445744196e-06, "epoch": 5.334302325581396, "percentage": 76.2, "elapsed_time": "12:47:47", "remaining_time": "3:59:45"}
{"current_steps": 3675, "total_steps": 4816, "loss": 0.2177, "lr": 6.470094762786901e-06, "epoch": 5.34156976744186, "percentage": 76.31, "elapsed_time": "12:48:49", "remaining_time": "3:58:41"}
{"current_steps": 3680, "total_steps": 4816, "loss": 0.2245, "lr": 6.4168008079792906e-06, "epoch": 5.348837209302325, "percentage": 76.41, "elapsed_time": "12:49:52", "remaining_time": "3:57:39"}
{"current_steps": 3685, "total_steps": 4816, "loss": 0.2243, "lr": 6.36368528138807e-06, "epoch": 5.3561046511627906, "percentage": 76.52, "elapsed_time": "12:50:56", "remaining_time": "3:56:37"}
{"current_steps": 3690, "total_steps": 4816, "loss": 0.2267, "lr": 6.310748880736095e-06, "epoch": 5.363372093023256, "percentage": 76.62, "elapsed_time": "12:52:02", "remaining_time": "3:55:35"}
{"current_steps": 3695, "total_steps": 4816, "loss": 0.2228, "lr": 6.2579923013932435e-06, "epoch": 5.370639534883721, "percentage": 76.72, "elapsed_time": "12:53:07", "remaining_time": "3:54:33"}
{"current_steps": 3700, "total_steps": 4816, "loss": 0.2313, "lr": 6.205416236367263e-06, "epoch": 5.377906976744186, "percentage": 76.83, "elapsed_time": "12:54:08", "remaining_time": "3:53:29"}
{"current_steps": 3705, "total_steps": 4816, "loss": 0.2281, "lr": 6.1530213762946944e-06, "epoch": 5.3851744186046515, "percentage": 76.93, "elapsed_time": "12:55:14", "remaining_time": "3:52:28"}
{"current_steps": 3710, "total_steps": 4816, "loss": 0.2274, "lr": 6.100808409431755e-06, "epoch": 5.392441860465116, "percentage": 77.03, "elapsed_time": "12:56:13", "remaining_time": "3:51:24"}
{"current_steps": 3715, "total_steps": 4816, "loss": 0.2131, "lr": 6.048778021645329e-06, "epoch": 5.399709302325581, "percentage": 77.14, "elapsed_time": "12:57:16", "remaining_time": "3:50:21"}
{"current_steps": 3720, "total_steps": 4816, "loss": 0.2309, "lr": 5.996930896403967e-06, "epoch": 5.406976744186046, "percentage": 77.24, "elapsed_time": "12:58:21", "remaining_time": "3:49:19"}
{"current_steps": 3725, "total_steps": 4816, "loss": 0.2224, "lr": 5.94526771476887e-06, "epoch": 5.414244186046512, "percentage": 77.35, "elapsed_time": "12:59:26", "remaining_time": "3:48:17"}
{"current_steps": 3730, "total_steps": 4816, "loss": 0.2227, "lr": 5.893789155384975e-06, "epoch": 5.421511627906977, "percentage": 77.45, "elapsed_time": "13:00:24", "remaining_time": "3:47:13"}
{"current_steps": 3735, "total_steps": 4816, "loss": 0.2256, "lr": 5.8424958944720245e-06, "epoch": 5.428779069767442, "percentage": 77.55, "elapsed_time": "13:01:30", "remaining_time": "3:46:11"}
{"current_steps": 3740, "total_steps": 4816, "loss": 0.2315, "lr": 5.791388605815709e-06, "epoch": 5.436046511627907, "percentage": 77.66, "elapsed_time": "13:02:37", "remaining_time": "3:45:09"}
{"current_steps": 3745, "total_steps": 4816, "loss": 0.2164, "lr": 5.740467960758776e-06, "epoch": 5.4433139534883725, "percentage": 77.76, "elapsed_time": "13:03:41", "remaining_time": "3:44:07"}
{"current_steps": 3750, "total_steps": 4816, "loss": 0.2222, "lr": 5.68973462819223e-06, "epoch": 5.450581395348837, "percentage": 77.87, "elapsed_time": "13:04:44", "remaining_time": "3:43:04"}
{"current_steps": 3755, "total_steps": 4816, "loss": 0.2219, "lr": 5.63918927454657e-06, "epoch": 5.457848837209302, "percentage": 77.97, "elapsed_time": "13:05:44", "remaining_time": "3:42:00"}
{"current_steps": 3760, "total_steps": 4816, "loss": 0.2212, "lr": 5.588832563783e-06, "epoch": 5.465116279069767, "percentage": 78.07, "elapsed_time": "13:06:44", "remaining_time": "3:40:57"}
{"current_steps": 3765, "total_steps": 4816, "loss": 0.2249, "lr": 5.538665157384715e-06, "epoch": 5.472383720930233, "percentage": 78.18, "elapsed_time": "13:07:53", "remaining_time": "3:39:56"}
{"current_steps": 3770, "total_steps": 4816, "loss": 0.226, "lr": 5.48868771434822e-06, "epoch": 5.479651162790698, "percentage": 78.28, "elapsed_time": "13:08:52", "remaining_time": "3:38:52"}
{"current_steps": 3775, "total_steps": 4816, "loss": 0.2369, "lr": 5.438900891174686e-06, "epoch": 5.486918604651163, "percentage": 78.38, "elapsed_time": "13:09:56", "remaining_time": "3:37:50"}
{"current_steps": 3780, "total_steps": 4816, "loss": 0.2369, "lr": 5.389305341861293e-06, "epoch": 5.4941860465116275, "percentage": 78.49, "elapsed_time": "13:11:00", "remaining_time": "3:36:47"}
{"current_steps": 3785, "total_steps": 4816, "loss": 0.2198, "lr": 5.3399017178926614e-06, "epoch": 5.501453488372093, "percentage": 78.59, "elapsed_time": "13:12:01", "remaining_time": "3:35:44"}
{"current_steps": 3790, "total_steps": 4816, "loss": 0.2283, "lr": 5.290690668232301e-06, "epoch": 5.508720930232558, "percentage": 78.7, "elapsed_time": "13:13:07", "remaining_time": "3:34:42"}
{"current_steps": 3795, "total_steps": 4816, "loss": 0.2269, "lr": 5.2416728393140624e-06, "epoch": 5.515988372093023, "percentage": 78.8, "elapsed_time": "13:14:11", "remaining_time": "3:33:40"}
{"current_steps": 3800, "total_steps": 4816, "loss": 0.2257, "lr": 5.192848875033663e-06, "epoch": 5.523255813953488, "percentage": 78.9, "elapsed_time": "13:15:11", "remaining_time": "3:32:36"}
{"current_steps": 3805, "total_steps": 4816, "loss": 0.238, "lr": 5.144219416740217e-06, "epoch": 5.530523255813954, "percentage": 79.01, "elapsed_time": "13:16:15", "remaining_time": "3:31:34"}
{"current_steps": 3810, "total_steps": 4816, "loss": 0.222, "lr": 5.095785103227835e-06, "epoch": 5.537790697674419, "percentage": 79.11, "elapsed_time": "13:17:12", "remaining_time": "3:30:29"}
{"current_steps": 3815, "total_steps": 4816, "loss": 0.2166, "lr": 5.047546570727205e-06, "epoch": 5.545058139534884, "percentage": 79.22, "elapsed_time": "13:18:11", "remaining_time": "3:29:26"}
{"current_steps": 3820, "total_steps": 4816, "loss": 0.2208, "lr": 4.999504452897232e-06, "epoch": 5.5523255813953485, "percentage": 79.32, "elapsed_time": "13:19:17", "remaining_time": "3:28:24"}
{"current_steps": 3825, "total_steps": 4816, "loss": 0.2301, "lr": 4.95165938081676e-06, "epoch": 5.559593023255814, "percentage": 79.42, "elapsed_time": "13:20:23", "remaining_time": "3:27:22"}
{"current_steps": 3830, "total_steps": 4816, "loss": 0.2317, "lr": 4.9040119829762246e-06, "epoch": 5.566860465116279, "percentage": 79.53, "elapsed_time": "13:21:28", "remaining_time": "3:26:20"}
{"current_steps": 3835, "total_steps": 4816, "loss": 0.2166, "lr": 4.856562885269427e-06, "epoch": 5.574127906976744, "percentage": 79.63, "elapsed_time": "13:22:28", "remaining_time": "3:25:16"}
{"current_steps": 3840, "total_steps": 4816, "loss": 0.2366, "lr": 4.809312710985308e-06, "epoch": 5.5813953488372094, "percentage": 79.73, "elapsed_time": "13:23:34", "remaining_time": "3:24:14"}
{"current_steps": 3845, "total_steps": 4816, "loss": 0.2396, "lr": 4.762262080799771e-06, "epoch": 5.588662790697675, "percentage": 79.84, "elapsed_time": "13:24:38", "remaining_time": "3:23:12"}
{"current_steps": 3850, "total_steps": 4816, "loss": 0.2127, "lr": 4.715411612767508e-06, "epoch": 5.595930232558139, "percentage": 79.94, "elapsed_time": "13:25:45", "remaining_time": "3:22:10"}
{"current_steps": 3855, "total_steps": 4816, "loss": 0.2235, "lr": 4.668761922313893e-06, "epoch": 5.603197674418604, "percentage": 80.05, "elapsed_time": "13:26:49", "remaining_time": "3:21:07"}
{"current_steps": 3860, "total_steps": 4816, "loss": 0.2248, "lr": 4.622313622226888e-06, "epoch": 5.6104651162790695, "percentage": 80.15, "elapsed_time": "13:27:51", "remaining_time": "3:20:04"}
{"current_steps": 3865, "total_steps": 4816, "loss": 0.2391, "lr": 4.5760673226490245e-06, "epoch": 5.617732558139535, "percentage": 80.25, "elapsed_time": "13:28:54", "remaining_time": "3:19:02"}
{"current_steps": 3870, "total_steps": 4816, "loss": 0.2326, "lr": 4.530023631069342e-06, "epoch": 5.625, "percentage": 80.36, "elapsed_time": "13:29:53", "remaining_time": "3:17:58"}
{"current_steps": 3875, "total_steps": 4816, "loss": 0.2223, "lr": 4.484183152315435e-06, "epoch": 5.632267441860465, "percentage": 80.46, "elapsed_time": "13:30:57", "remaining_time": "3:16:55"}
{"current_steps": 3880, "total_steps": 4816, "loss": 0.2206, "lr": 4.438546488545516e-06, "epoch": 5.6395348837209305, "percentage": 80.56, "elapsed_time": "13:32:00", "remaining_time": "3:15:53"}
{"current_steps": 3885, "total_steps": 4816, "loss": 0.2206, "lr": 4.393114239240495e-06, "epoch": 5.646802325581396, "percentage": 80.67, "elapsed_time": "13:33:02", "remaining_time": "3:14:50"}
{"current_steps": 3890, "total_steps": 4816, "loss": 0.2185, "lr": 4.347887001196089e-06, "epoch": 5.654069767441861, "percentage": 80.77, "elapsed_time": "13:34:07", "remaining_time": "3:13:47"}
{"current_steps": 3895, "total_steps": 4816, "loss": 0.215, "lr": 4.302865368515002e-06, "epoch": 5.661337209302325, "percentage": 80.88, "elapsed_time": "13:35:09", "remaining_time": "3:12:44"}
{"current_steps": 3900, "total_steps": 4816, "loss": 0.2277, "lr": 4.2580499325991284e-06, "epoch": 5.6686046511627906, "percentage": 80.98, "elapsed_time": "13:36:10", "remaining_time": "3:11:41"}
{"current_steps": 3905, "total_steps": 4816, "loss": 0.2243, "lr": 4.213441282141762e-06, "epoch": 5.675872093023256, "percentage": 81.08, "elapsed_time": "13:37:05", "remaining_time": "3:10:37"}
{"current_steps": 3910, "total_steps": 4816, "loss": 0.2297, "lr": 4.169040003119871e-06, "epoch": 5.683139534883721, "percentage": 81.19, "elapsed_time": "13:38:05", "remaining_time": "3:09:33"}
{"current_steps": 3915, "total_steps": 4816, "loss": 0.2212, "lr": 4.124846678786405e-06, "epoch": 5.690406976744186, "percentage": 81.29, "elapsed_time": "13:39:04", "remaining_time": "3:08:30"}
{"current_steps": 3920, "total_steps": 4816, "loss": 0.2324, "lr": 4.080861889662642e-06, "epoch": 5.6976744186046515, "percentage": 81.4, "elapsed_time": "13:40:07", "remaining_time": "3:07:27"}
{"current_steps": 3925, "total_steps": 4816, "loss": 0.2401, "lr": 4.037086213530539e-06, "epoch": 5.704941860465116, "percentage": 81.5, "elapsed_time": "13:41:09", "remaining_time": "3:06:24"}
{"current_steps": 3930, "total_steps": 4816, "loss": 0.235, "lr": 3.993520225425154e-06, "epoch": 5.712209302325581, "percentage": 81.6, "elapsed_time": "13:42:10", "remaining_time": "3:05:21"}
{"current_steps": 3935, "total_steps": 4816, "loss": 0.2258, "lr": 3.9501644976271095e-06, "epoch": 5.719476744186046, "percentage": 81.71, "elapsed_time": "13:43:16", "remaining_time": "3:04:19"}
{"current_steps": 3940, "total_steps": 4816, "loss": 0.2205, "lr": 3.907019599655044e-06, "epoch": 5.726744186046512, "percentage": 81.81, "elapsed_time": "13:44:18", "remaining_time": "3:03:16"}
{"current_steps": 3945, "total_steps": 4816, "loss": 0.2239, "lr": 3.864086098258153e-06, "epoch": 5.734011627906977, "percentage": 81.91, "elapsed_time": "13:45:20", "remaining_time": "3:02:13"}
{"current_steps": 3950, "total_steps": 4816, "loss": 0.2194, "lr": 3.8213645574087286e-06, "epoch": 5.741279069767442, "percentage": 82.02, "elapsed_time": "13:46:23", "remaining_time": "3:01:10"}
{"current_steps": 3955, "total_steps": 4816, "loss": 0.2226, "lr": 3.778855538294779e-06, "epoch": 5.748546511627907, "percentage": 82.12, "elapsed_time": "13:47:31", "remaining_time": "3:00:08"}
{"current_steps": 3960, "total_steps": 4816, "loss": 0.227, "lr": 3.736559599312619e-06, "epoch": 5.7558139534883725, "percentage": 82.23, "elapsed_time": "13:48:29", "remaining_time": "2:59:05"}
{"current_steps": 3965, "total_steps": 4816, "loss": 0.2268, "lr": 3.6944772960595597e-06, "epoch": 5.763081395348837, "percentage": 82.33, "elapsed_time": "13:49:30", "remaining_time": "2:58:02"}
{"current_steps": 3970, "total_steps": 4816, "loss": 0.2338, "lr": 3.652609181326601e-06, "epoch": 5.770348837209302, "percentage": 82.43, "elapsed_time": "13:50:37", "remaining_time": "2:57:00"}
{"current_steps": 3975, "total_steps": 4816, "loss": 0.217, "lr": 3.610955805091185e-06, "epoch": 5.777616279069767, "percentage": 82.54, "elapsed_time": "13:51:35", "remaining_time": "2:55:56"}
{"current_steps": 3980, "total_steps": 4816, "loss": 0.2204, "lr": 3.569517714509947e-06, "epoch": 5.784883720930233, "percentage": 82.64, "elapsed_time": "13:52:35", "remaining_time": "2:54:53"}
{"current_steps": 3985, "total_steps": 4816, "loss": 0.2307, "lr": 3.528295453911541e-06, "epoch": 5.792151162790698, "percentage": 82.75, "elapsed_time": "13:53:39", "remaining_time": "2:53:50"}
{"current_steps": 3990, "total_steps": 4816, "loss": 0.229, "lr": 3.4872895647895045e-06, "epoch": 5.799418604651163, "percentage": 82.85, "elapsed_time": "13:54:44", "remaining_time": "2:52:48"}
{"current_steps": 3995, "total_steps": 4816, "loss": 0.2182, "lr": 3.446500585795112e-06, "epoch": 5.8066860465116275, "percentage": 82.95, "elapsed_time": "13:55:49", "remaining_time": "2:51:45"}
{"current_steps": 4000, "total_steps": 4816, "loss": 0.2414, "lr": 3.4059290527303256e-06, "epoch": 5.813953488372093, "percentage": 83.06, "elapsed_time": "13:56:54", "remaining_time": "2:50:43"}
{"current_steps": 4005, "total_steps": 4816, "loss": 0.2335, "lr": 3.3655754985407453e-06, "epoch": 5.821220930232558, "percentage": 83.16, "elapsed_time": "13:57:53", "remaining_time": "2:49:40"}
{"current_steps": 4010, "total_steps": 4816, "loss": 0.2248, "lr": 3.3254404533086216e-06, "epoch": 5.828488372093023, "percentage": 83.26, "elapsed_time": "13:58:55", "remaining_time": "2:48:37"}
{"current_steps": 4015, "total_steps": 4816, "loss": 0.2373, "lr": 3.285524444245873e-06, "epoch": 5.835755813953488, "percentage": 83.37, "elapsed_time": "13:59:57", "remaining_time": "2:47:34"}
{"current_steps": 4020, "total_steps": 4816, "loss": 0.2215, "lr": 3.245827995687165e-06, "epoch": 5.843023255813954, "percentage": 83.47, "elapsed_time": "14:01:01", "remaining_time": "2:46:31"}
{"current_steps": 4025, "total_steps": 4816, "loss": 0.2311, "lr": 3.2063516290830445e-06, "epoch": 5.850290697674419, "percentage": 83.58, "elapsed_time": "14:02:03", "remaining_time": "2:45:28"}
{"current_steps": 4030, "total_steps": 4816, "loss": 0.2328, "lr": 3.1670958629930595e-06, "epoch": 5.857558139534884, "percentage": 83.68, "elapsed_time": "14:03:03", "remaining_time": "2:44:25"}
{"current_steps": 4035, "total_steps": 4816, "loss": 0.227, "lr": 3.1280612130789633e-06, "epoch": 5.8648255813953485, "percentage": 83.78, "elapsed_time": "14:04:07", "remaining_time": "2:43:23"}
{"current_steps": 4040, "total_steps": 4816, "loss": 0.2216, "lr": 3.0892481920979355e-06, "epoch": 5.872093023255814, "percentage": 83.89, "elapsed_time": "14:05:15", "remaining_time": "2:42:21"}
{"current_steps": 4045, "total_steps": 4816, "loss": 0.2299, "lr": 3.0506573098958613e-06, "epoch": 5.879360465116279, "percentage": 83.99, "elapsed_time": "14:06:20", "remaining_time": "2:41:19"}
{"current_steps": 4050, "total_steps": 4816, "loss": 0.222, "lr": 3.0122890734006114e-06, "epoch": 5.886627906976744, "percentage": 84.09, "elapsed_time": "14:07:23", "remaining_time": "2:40:16"}
{"current_steps": 4055, "total_steps": 4816, "loss": 0.2246, "lr": 2.97414398661539e-06, "epoch": 5.8938953488372094, "percentage": 84.2, "elapsed_time": "14:08:26", "remaining_time": "2:39:13"}
{"current_steps": 4060, "total_steps": 4816, "loss": 0.2167, "lr": 2.9362225506121357e-06, "epoch": 5.901162790697675, "percentage": 84.3, "elapsed_time": "14:09:30", "remaining_time": "2:38:11"}
{"current_steps": 4065, "total_steps": 4816, "loss": 0.2189, "lr": 2.8985252635249026e-06, "epoch": 5.908430232558139, "percentage": 84.41, "elapsed_time": "14:10:33", "remaining_time": "2:37:08"}
{"current_steps": 4070, "total_steps": 4816, "loss": 0.2314, "lr": 2.8610526205433476e-06, "epoch": 5.915697674418604, "percentage": 84.51, "elapsed_time": "14:11:42", "remaining_time": "2:36:06"}
{"current_steps": 4075, "total_steps": 4816, "loss": 0.218, "lr": 2.823805113906204e-06, "epoch": 5.9229651162790695, "percentage": 84.61, "elapsed_time": "14:12:44", "remaining_time": "2:35:03"}
{"current_steps": 4080, "total_steps": 4816, "loss": 0.2138, "lr": 2.7867832328948385e-06, "epoch": 5.930232558139535, "percentage": 84.72, "elapsed_time": "14:13:53", "remaining_time": "2:34:02"}
{"current_steps": 4085, "total_steps": 4816, "loss": 0.2265, "lr": 2.7499874638268044e-06, "epoch": 5.9375, "percentage": 84.82, "elapsed_time": "14:14:54", "remaining_time": "2:32:59"}
{"current_steps": 4090, "total_steps": 4816, "loss": 0.2314, "lr": 2.7134182900494542e-06, "epoch": 5.944767441860465, "percentage": 84.93, "elapsed_time": "14:15:51", "remaining_time": "2:31:55"}
{"current_steps": 4095, "total_steps": 4816, "loss": 0.2226, "lr": 2.6770761919336098e-06, "epoch": 5.9520348837209305, "percentage": 85.03, "elapsed_time": "14:16:53", "remaining_time": "2:30:52"}
{"current_steps": 4100, "total_steps": 4816, "loss": 0.2412, "lr": 2.640961646867224e-06, "epoch": 5.959302325581396, "percentage": 85.13, "elapsed_time": "14:17:59", "remaining_time": "2:29:50"}
{"current_steps": 4105, "total_steps": 4816, "loss": 0.2221, "lr": 2.605075129249135e-06, "epoch": 5.966569767441861, "percentage": 85.24, "elapsed_time": "14:19:06", "remaining_time": "2:28:47"}
{"current_steps": 4110, "total_steps": 4816, "loss": 0.2253, "lr": 2.5694171104828146e-06, "epoch": 5.973837209302325, "percentage": 85.34, "elapsed_time": "14:20:03", "remaining_time": "2:27:44"}
{"current_steps": 4115, "total_steps": 4816, "loss": 0.2212, "lr": 2.533988058970198e-06, "epoch": 5.9811046511627906, "percentage": 85.44, "elapsed_time": "14:21:01", "remaining_time": "2:26:40"}
{"current_steps": 4120, "total_steps": 4816, "loss": 0.224, "lr": 2.498788440105506e-06, "epoch": 5.988372093023256, "percentage": 85.55, "elapsed_time": "14:21:59", "remaining_time": "2:25:37"}
{"current_steps": 4125, "total_steps": 4816, "loss": 0.2239, "lr": 2.4638187162691487e-06, "epoch": 5.995639534883721, "percentage": 85.65, "elapsed_time": "14:23:01", "remaining_time": "2:24:34"}
{"current_steps": 4130, "total_steps": 4816, "loss": 0.2187, "lr": 2.42907934682165e-06, "epoch": 6.002906976744186, "percentage": 85.76, "elapsed_time": "14:24:01", "remaining_time": "2:23:30"}
{"current_steps": 4135, "total_steps": 4816, "loss": 0.218, "lr": 2.3945707880976034e-06, "epoch": 6.0101744186046515, "percentage": 85.86, "elapsed_time": "14:25:07", "remaining_time": "2:22:28"}
{"current_steps": 4140, "total_steps": 4816, "loss": 0.2308, "lr": 2.36029349339969e-06, "epoch": 6.017441860465116, "percentage": 85.96, "elapsed_time": "14:26:06", "remaining_time": "2:21:25"}
{"current_steps": 4145, "total_steps": 4816, "loss": 0.2236, "lr": 2.3262479129927116e-06, "epoch": 6.024709302325581, "percentage": 86.07, "elapsed_time": "14:27:09", "remaining_time": "2:20:22"}
{"current_steps": 4150, "total_steps": 4816, "loss": 0.2211, "lr": 2.2924344940976975e-06, "epoch": 6.031976744186046, "percentage": 86.17, "elapsed_time": "14:28:17", "remaining_time": "2:19:20"}
{"current_steps": 4155, "total_steps": 4816, "loss": 0.2125, "lr": 2.2588536808859975e-06, "epoch": 6.039244186046512, "percentage": 86.27, "elapsed_time": "14:29:17", "remaining_time": "2:18:17"}
{"current_steps": 4160, "total_steps": 4816, "loss": 0.2101, "lr": 2.225505914473469e-06, "epoch": 6.046511627906977, "percentage": 86.38, "elapsed_time": "14:30:16", "remaining_time": "2:17:14"}
{"current_steps": 4165, "total_steps": 4816, "loss": 0.2182, "lr": 2.19239163291469e-06, "epoch": 6.053779069767442, "percentage": 86.48, "elapsed_time": "14:31:19", "remaining_time": "2:16:11"}
{"current_steps": 4170, "total_steps": 4816, "loss": 0.2243, "lr": 2.1595112711971835e-06, "epoch": 6.061046511627907, "percentage": 86.59, "elapsed_time": "14:32:24", "remaining_time": "2:15:08"}
{"current_steps": 4175, "total_steps": 4816, "loss": 0.2347, "lr": 2.1268652612357153e-06, "epoch": 6.068313953488372, "percentage": 86.69, "elapsed_time": "14:33:20", "remaining_time": "2:14:05"}
{"current_steps": 4180, "total_steps": 4816, "loss": 0.2093, "lr": 2.0944540318666107e-06, "epoch": 6.075581395348837, "percentage": 86.79, "elapsed_time": "14:34:19", "remaining_time": "2:13:01"}
{"current_steps": 4185, "total_steps": 4816, "loss": 0.2354, "lr": 2.062278008842147e-06, "epoch": 6.082848837209302, "percentage": 86.9, "elapsed_time": "14:35:21", "remaining_time": "2:11:59"}
{"current_steps": 4190, "total_steps": 4816, "loss": 0.2242, "lr": 2.030337614824929e-06, "epoch": 6.090116279069767, "percentage": 87.0, "elapsed_time": "14:36:24", "remaining_time": "2:10:56"}
{"current_steps": 4195, "total_steps": 4816, "loss": 0.2206, "lr": 1.9986332693823487e-06, "epoch": 6.097383720930233, "percentage": 87.11, "elapsed_time": "14:37:22", "remaining_time": "2:09:52"}
{"current_steps": 4200, "total_steps": 4816, "loss": 0.2212, "lr": 1.9671653889810893e-06, "epoch": 6.104651162790698, "percentage": 87.21, "elapsed_time": "14:38:26", "remaining_time": "2:08:50"}
{"current_steps": 4205, "total_steps": 4816, "loss": 0.2173, "lr": 1.9359343869816307e-06, "epoch": 6.111918604651163, "percentage": 87.31, "elapsed_time": "14:39:23", "remaining_time": "2:07:46"}
{"current_steps": 4210, "total_steps": 4816, "loss": 0.2119, "lr": 1.9049406736328336e-06, "epoch": 6.119186046511628, "percentage": 87.42, "elapsed_time": "14:40:25", "remaining_time": "2:06:43"}
{"current_steps": 4215, "total_steps": 4816, "loss": 0.2188, "lr": 1.87418465606654e-06, "epoch": 6.126453488372093, "percentage": 87.52, "elapsed_time": "14:41:24", "remaining_time": "2:05:40"}
{"current_steps": 4220, "total_steps": 4816, "loss": 0.2197, "lr": 1.8436667382922468e-06, "epoch": 6.133720930232558, "percentage": 87.62, "elapsed_time": "14:42:23", "remaining_time": "2:04:37"}
{"current_steps": 4225, "total_steps": 4816, "loss": 0.2214, "lr": 1.8133873211917686e-06, "epoch": 6.140988372093023, "percentage": 87.73, "elapsed_time": "14:43:26", "remaining_time": "2:03:34"}
{"current_steps": 4230, "total_steps": 4816, "loss": 0.2334, "lr": 1.783346802514001e-06, "epoch": 6.148255813953488, "percentage": 87.83, "elapsed_time": "14:44:30", "remaining_time": "2:02:32"}
{"current_steps": 4235, "total_steps": 4816, "loss": 0.2243, "lr": 1.7535455768696686e-06, "epoch": 6.155523255813954, "percentage": 87.94, "elapsed_time": "14:45:34", "remaining_time": "2:01:29"}
{"current_steps": 4240, "total_steps": 4816, "loss": 0.2234, "lr": 1.7239840357261695e-06, "epoch": 6.162790697674419, "percentage": 88.04, "elapsed_time": "14:46:39", "remaining_time": "2:00:27"}
{"current_steps": 4245, "total_steps": 4816, "loss": 0.2216, "lr": 1.6946625674024053e-06, "epoch": 6.170058139534884, "percentage": 88.14, "elapsed_time": "14:47:43", "remaining_time": "1:59:24"}
{"current_steps": 4250, "total_steps": 4816, "loss": 0.2249, "lr": 1.6655815570637002e-06, "epoch": 6.1773255813953485, "percentage": 88.25, "elapsed_time": "14:48:42", "remaining_time": "1:58:21"}
{"current_steps": 4255, "total_steps": 4816, "loss": 0.2216, "lr": 1.636741386716727e-06, "epoch": 6.184593023255814, "percentage": 88.35, "elapsed_time": "14:49:36", "remaining_time": "1:57:17"}
{"current_steps": 4260, "total_steps": 4816, "loss": 0.2165, "lr": 1.6081424352045093e-06, "epoch": 6.191860465116279, "percentage": 88.46, "elapsed_time": "14:50:43", "remaining_time": "1:56:15"}
{"current_steps": 4265, "total_steps": 4816, "loss": 0.2177, "lr": 1.5797850782014236e-06, "epoch": 6.199127906976744, "percentage": 88.56, "elapsed_time": "14:51:49", "remaining_time": "1:55:12"}
{"current_steps": 4270, "total_steps": 4816, "loss": 0.2202, "lr": 1.5516696882082704e-06, "epoch": 6.2063953488372094, "percentage": 88.66, "elapsed_time": "14:52:54", "remaining_time": "1:54:10"}
{"current_steps": 4275, "total_steps": 4816, "loss": 0.2238, "lr": 1.5237966345473942e-06, "epoch": 6.213662790697675, "percentage": 88.77, "elapsed_time": "14:53:59", "remaining_time": "1:53:08"}
{"current_steps": 4280, "total_steps": 4816, "loss": 0.2218, "lr": 1.4961662833578117e-06, "epoch": 6.22093023255814, "percentage": 88.87, "elapsed_time": "14:54:58", "remaining_time": "1:52:04"}
{"current_steps": 4285, "total_steps": 4816, "loss": 0.2269, "lr": 1.4687789975904188e-06, "epoch": 6.228197674418604, "percentage": 88.97, "elapsed_time": "14:55:59", "remaining_time": "1:51:01"}
{"current_steps": 4290, "total_steps": 4816, "loss": 0.2202, "lr": 1.4416351370032077e-06, "epoch": 6.2354651162790695, "percentage": 89.08, "elapsed_time": "14:57:04", "remaining_time": "1:49:59"}
{"current_steps": 4295, "total_steps": 4816, "loss": 0.2265, "lr": 1.4147350581565644e-06, "epoch": 6.242732558139535, "percentage": 89.18, "elapsed_time": "14:58:05", "remaining_time": "1:48:56"}
{"current_steps": 4300, "total_steps": 4816, "loss": 0.2201, "lr": 1.3880791144085582e-06, "epoch": 6.25, "percentage": 89.29, "elapsed_time": "14:59:07", "remaining_time": "1:47:53"}
{"current_steps": 4305, "total_steps": 4816, "loss": 0.2205, "lr": 1.3616676559103104e-06, "epoch": 6.257267441860465, "percentage": 89.39, "elapsed_time": "15:00:10", "remaining_time": "1:46:51"}
{"current_steps": 4310, "total_steps": 4816, "loss": 0.2214, "lr": 1.3355010296014114e-06, "epoch": 6.2645348837209305, "percentage": 89.49, "elapsed_time": "15:01:14", "remaining_time": "1:45:48"}
{"current_steps": 4315, "total_steps": 4816, "loss": 0.2213, "lr": 1.3095795792053333e-06, "epoch": 6.271802325581396, "percentage": 89.6, "elapsed_time": "15:02:15", "remaining_time": "1:44:45"}
{"current_steps": 4320, "total_steps": 4816, "loss": 0.2246, "lr": 1.2839036452249354e-06, "epoch": 6.27906976744186, "percentage": 89.7, "elapsed_time": "15:03:21", "remaining_time": "1:43:43"}
{"current_steps": 4325, "total_steps": 4816, "loss": 0.2174, "lr": 1.258473564937981e-06, "epoch": 6.286337209302325, "percentage": 89.8, "elapsed_time": "15:04:26", "remaining_time": "1:42:40"}
{"current_steps": 4330, "total_steps": 4816, "loss": 0.2206, "lr": 1.2332896723927257e-06, "epoch": 6.2936046511627906, "percentage": 89.91, "elapsed_time": "15:05:29", "remaining_time": "1:41:37"}
{"current_steps": 4335, "total_steps": 4816, "loss": 0.2214, "lr": 1.2083522984035012e-06, "epoch": 6.300872093023256, "percentage": 90.01, "elapsed_time": "15:06:32", "remaining_time": "1:40:35"}
{"current_steps": 4340, "total_steps": 4816, "loss": 0.2205, "lr": 1.183661770546387e-06, "epoch": 6.308139534883721, "percentage": 90.12, "elapsed_time": "15:07:35", "remaining_time": "1:39:32"}
{"current_steps": 4345, "total_steps": 4816, "loss": 0.2246, "lr": 1.1592184131549056e-06, "epoch": 6.315406976744186, "percentage": 90.22, "elapsed_time": "15:08:39", "remaining_time": "1:38:29"}
{"current_steps": 4350, "total_steps": 4816, "loss": 0.2159, "lr": 1.1350225473157672e-06, "epoch": 6.3226744186046515, "percentage": 90.32, "elapsed_time": "15:09:44", "remaining_time": "1:37:27"}
{"current_steps": 4355, "total_steps": 4816, "loss": 0.2126, "lr": 1.1110744908646365e-06, "epoch": 6.329941860465116, "percentage": 90.43, "elapsed_time": "15:10:50", "remaining_time": "1:36:25"}
{"current_steps": 4360, "total_steps": 4816, "loss": 0.2242, "lr": 1.0873745583819661e-06, "epoch": 6.337209302325581, "percentage": 90.53, "elapsed_time": "15:11:48", "remaining_time": "1:35:21"}
{"current_steps": 4365, "total_steps": 4816, "loss": 0.2175, "lr": 1.063923061188874e-06, "epoch": 6.344476744186046, "percentage": 90.64, "elapsed_time": "15:12:50", "remaining_time": "1:34:19"}
{"current_steps": 4370, "total_steps": 4816, "loss": 0.2226, "lr": 1.040720307343035e-06, "epoch": 6.351744186046512, "percentage": 90.74, "elapsed_time": "15:13:53", "remaining_time": "1:33:16"}
{"current_steps": 4375, "total_steps": 4816, "loss": 0.2207, "lr": 1.017766601634651e-06, "epoch": 6.359011627906977, "percentage": 90.84, "elapsed_time": "15:14:56", "remaining_time": "1:32:13"}
{"current_steps": 4380, "total_steps": 4816, "loss": 0.218, "lr": 9.95062245582432e-07, "epoch": 6.366279069767442, "percentage": 90.95, "elapsed_time": "15:15:59", "remaining_time": "1:31:10"}
{"current_steps": 4385, "total_steps": 4816, "loss": 0.2113, "lr": 9.72607537429655e-07, "epoch": 6.373546511627907, "percentage": 91.05, "elapsed_time": "15:16:59", "remaining_time": "1:30:07"}
{"current_steps": 4390, "total_steps": 4816, "loss": 0.2222, "lr": 9.504027721402264e-07, "epoch": 6.3808139534883725, "percentage": 91.15, "elapsed_time": "15:18:01", "remaining_time": "1:29:05"}
{"current_steps": 4395, "total_steps": 4816, "loss": 0.2213, "lr": 9.284482413948148e-07, "epoch": 6.388081395348837, "percentage": 91.26, "elapsed_time": "15:19:07", "remaining_time": "1:28:02"}
{"current_steps": 4400, "total_steps": 4816, "loss": 0.2175, "lr": 9.067442335870313e-07, "epoch": 6.395348837209302, "percentage": 91.36, "elapsed_time": "15:20:06", "remaining_time": "1:26:59"}
{"current_steps": 4405, "total_steps": 4816, "loss": 0.2141, "lr": 8.852910338196152e-07, "epoch": 6.402616279069767, "percentage": 91.47, "elapsed_time": "15:21:06", "remaining_time": "1:25:56"}
{"current_steps": 4410, "total_steps": 4816, "loss": 0.222, "lr": 8.640889239007166e-07, "epoch": 6.409883720930233, "percentage": 91.57, "elapsed_time": "15:22:09", "remaining_time": "1:24:53"}
{"current_steps": 4415, "total_steps": 4816, "loss": 0.2209, "lr": 8.431381823401708e-07, "epoch": 6.417151162790698, "percentage": 91.67, "elapsed_time": "15:23:11", "remaining_time": "1:23:51"}
{"current_steps": 4420, "total_steps": 4816, "loss": 0.2207, "lr": 8.224390843458652e-07, "epoch": 6.424418604651163, "percentage": 91.78, "elapsed_time": "15:24:14", "remaining_time": "1:22:48"}
{"current_steps": 4425, "total_steps": 4816, "loss": 0.22, "lr": 8.019919018201005e-07, "epoch": 6.4316860465116275, "percentage": 91.88, "elapsed_time": "15:25:17", "remaining_time": "1:21:45"}
{"current_steps": 4430, "total_steps": 4816, "loss": 0.2226, "lr": 7.817969033560246e-07, "epoch": 6.438953488372093, "percentage": 91.99, "elapsed_time": "15:26:25", "remaining_time": "1:20:43"}
{"current_steps": 4435, "total_steps": 4816, "loss": 0.2168, "lr": 7.618543542341217e-07, "epoch": 6.446220930232558, "percentage": 92.09, "elapsed_time": "15:27:23", "remaining_time": "1:19:40"}
{"current_steps": 4440, "total_steps": 4816, "loss": 0.2207, "lr": 7.421645164187019e-07, "epoch": 6.453488372093023, "percentage": 92.19, "elapsed_time": "15:28:26", "remaining_time": "1:18:37"}
{"current_steps": 4445, "total_steps": 4816, "loss": 0.2136, "lr": 7.227276485544798e-07, "epoch": 6.460755813953488, "percentage": 92.3, "elapsed_time": "15:29:28", "remaining_time": "1:17:34"}
{"current_steps": 4450, "total_steps": 4816, "loss": 0.2087, "lr": 7.035440059631616e-07, "epoch": 6.468023255813954, "percentage": 92.4, "elapsed_time": "15:30:27", "remaining_time": "1:16:31"}
{"current_steps": 4455, "total_steps": 4816, "loss": 0.224, "lr": 6.846138406401137e-07, "epoch": 6.475290697674419, "percentage": 92.5, "elapsed_time": "15:31:28", "remaining_time": "1:15:28"}
{"current_steps": 4460, "total_steps": 4816, "loss": 0.2215, "lr": 6.6593740125102e-07, "epoch": 6.482558139534884, "percentage": 92.61, "elapsed_time": "15:32:26", "remaining_time": "1:14:25"}
{"current_steps": 4465, "total_steps": 4816, "loss": 0.2219, "lr": 6.475149331286457e-07, "epoch": 6.4898255813953485, "percentage": 92.71, "elapsed_time": "15:33:30", "remaining_time": "1:13:23"}
{"current_steps": 4470, "total_steps": 4816, "loss": 0.2244, "lr": 6.293466782696001e-07, "epoch": 6.497093023255814, "percentage": 92.82, "elapsed_time": "15:34:38", "remaining_time": "1:12:20"}
{"current_steps": 4475, "total_steps": 4816, "loss": 0.2307, "lr": 6.114328753311572e-07, "epoch": 6.504360465116279, "percentage": 92.92, "elapsed_time": "15:35:38", "remaining_time": "1:11:17"}
{"current_steps": 4480, "total_steps": 4816, "loss": 0.2319, "lr": 5.937737596281223e-07, "epoch": 6.511627906976744, "percentage": 93.02, "elapsed_time": "15:36:41", "remaining_time": "1:10:15"}
{"current_steps": 4485, "total_steps": 4816, "loss": 0.2294, "lr": 5.763695631297483e-07, "epoch": 6.5188953488372094, "percentage": 93.13, "elapsed_time": "15:37:44", "remaining_time": "1:09:12"}
{"current_steps": 4490, "total_steps": 4816, "loss": 0.2073, "lr": 5.592205144566753e-07, "epoch": 6.526162790697675, "percentage": 93.23, "elapsed_time": "15:38:45", "remaining_time": "1:08:09"}
{"current_steps": 4495, "total_steps": 4816, "loss": 0.2227, "lr": 5.423268388779424e-07, "epoch": 6.533430232558139, "percentage": 93.33, "elapsed_time": "15:39:47", "remaining_time": "1:07:06"}
{"current_steps": 4500, "total_steps": 4816, "loss": 0.2109, "lr": 5.256887583080094e-07, "epoch": 6.540697674418604, "percentage": 93.44, "elapsed_time": "15:40:55", "remaining_time": "1:06:04"}
{"current_steps": 4505, "total_steps": 4816, "loss": 0.2118, "lr": 5.093064913038648e-07, "epoch": 6.5479651162790695, "percentage": 93.54, "elapsed_time": "15:42:34", "remaining_time": "1:05:04"}
{"current_steps": 4510, "total_steps": 4816, "loss": 0.2096, "lr": 4.931802530621376e-07, "epoch": 6.555232558139535, "percentage": 93.65, "elapsed_time": "15:43:39", "remaining_time": "1:04:01"}
{"current_steps": 4515, "total_steps": 4816, "loss": 0.2288, "lr": 4.773102554162768e-07, "epoch": 6.5625, "percentage": 93.75, "elapsed_time": "15:44:42", "remaining_time": "1:02:58"}
{"current_steps": 4520, "total_steps": 4816, "loss": 0.215, "lr": 4.61696706833763e-07, "epoch": 6.569767441860465, "percentage": 93.85, "elapsed_time": "15:45:47", "remaining_time": "1:01:56"}
{"current_steps": 4525, "total_steps": 4816, "loss": 0.2195, "lr": 4.4633981241338333e-07, "epoch": 6.5770348837209305, "percentage": 93.96, "elapsed_time": "15:46:52", "remaining_time": "1:00:53"}
{"current_steps": 4530, "total_steps": 4816, "loss": 0.2258, "lr": 4.312397738825236e-07, "epoch": 6.584302325581396, "percentage": 94.06, "elapsed_time": "15:47:57", "remaining_time": "0:59:50"}
{"current_steps": 4535, "total_steps": 4816, "loss": 0.2183, "lr": 4.163967895945242e-07, "epoch": 6.591569767441861, "percentage": 94.17, "elapsed_time": "15:48:59", "remaining_time": "0:58:48"}
{"current_steps": 4540, "total_steps": 4816, "loss": 0.2142, "lr": 4.0181105452607563e-07, "epoch": 6.598837209302325, "percentage": 94.27, "elapsed_time": "15:49:56", "remaining_time": "0:57:45"}
{"current_steps": 4545, "total_steps": 4816, "loss": 0.2184, "lr": 3.874827602746556e-07, "epoch": 6.6061046511627906, "percentage": 94.37, "elapsed_time": "15:51:05", "remaining_time": "0:56:42"}
{"current_steps": 4550, "total_steps": 4816, "loss": 0.2242, "lr": 3.734120950560116e-07, "epoch": 6.613372093023256, "percentage": 94.48, "elapsed_time": "15:52:09", "remaining_time": "0:55:39"}
{"current_steps": 4555, "total_steps": 4816, "loss": 0.2143, "lr": 3.5959924370168487e-07, "epoch": 6.620639534883721, "percentage": 94.58, "elapsed_time": "15:53:14", "remaining_time": "0:54:37"}
{"current_steps": 4560, "total_steps": 4816, "loss": 0.2226, "lr": 3.4604438765659445e-07, "epoch": 6.627906976744186, "percentage": 94.68, "elapsed_time": "15:54:21", "remaining_time": "0:53:34"}
{"current_steps": 4565, "total_steps": 4816, "loss": 0.2208, "lr": 3.3274770497664365e-07, "epoch": 6.6351744186046515, "percentage": 94.79, "elapsed_time": "15:55:21", "remaining_time": "0:52:31"}
{"current_steps": 4570, "total_steps": 4816, "loss": 0.2171, "lr": 3.1970937032638206e-07, "epoch": 6.642441860465116, "percentage": 94.89, "elapsed_time": "15:56:24", "remaining_time": "0:51:28"}
{"current_steps": 4575, "total_steps": 4816, "loss": 0.2187, "lr": 3.0692955497670705e-07, "epoch": 6.649709302325581, "percentage": 95.0, "elapsed_time": "15:57:27", "remaining_time": "0:50:26"}
{"current_steps": 4580, "total_steps": 4816, "loss": 0.2285, "lr": 2.944084268026326e-07, "epoch": 6.656976744186046, "percentage": 95.1, "elapsed_time": "15:58:27", "remaining_time": "0:49:23"}
{"current_steps": 4585, "total_steps": 4816, "loss": 0.2193, "lr": 2.821461502810641e-07, "epoch": 6.664244186046512, "percentage": 95.2, "elapsed_time": "15:59:32", "remaining_time": "0:48:20"}
{"current_steps": 4590, "total_steps": 4816, "loss": 0.211, "lr": 2.701428864886402e-07, "epoch": 6.671511627906977, "percentage": 95.31, "elapsed_time": "16:00:36", "remaining_time": "0:47:17"}
{"current_steps": 4595, "total_steps": 4816, "loss": 0.2204, "lr": 2.583987930996279e-07, "epoch": 6.678779069767442, "percentage": 95.41, "elapsed_time": "16:01:41", "remaining_time": "0:46:15"}
{"current_steps": 4600, "total_steps": 4816, "loss": 0.2308, "lr": 2.469140243838464e-07, "epoch": 6.686046511627907, "percentage": 95.51, "elapsed_time": "16:02:41", "remaining_time": "0:45:12"}
{"current_steps": 4605, "total_steps": 4816, "loss": 0.2237, "lr": 2.3568873120462854e-07, "epoch": 6.6933139534883725, "percentage": 95.62, "elapsed_time": "16:03:44", "remaining_time": "0:44:09"}
{"current_steps": 4610, "total_steps": 4816, "loss": 0.2172, "lr": 2.247230610168627e-07, "epoch": 6.700581395348837, "percentage": 95.72, "elapsed_time": "16:04:49", "remaining_time": "0:43:06"}
{"current_steps": 4615, "total_steps": 4816, "loss": 0.2064, "lr": 2.1401715786503408e-07, "epoch": 6.707848837209302, "percentage": 95.83, "elapsed_time": "16:05:57", "remaining_time": "0:42:04"}
{"current_steps": 4620, "total_steps": 4816, "loss": 0.2172, "lr": 2.0357116238134633e-07, "epoch": 6.715116279069767, "percentage": 95.93, "elapsed_time": "16:06:59", "remaining_time": "0:41:01"}
{"current_steps": 4625, "total_steps": 4816, "loss": 0.2203, "lr": 1.9338521178386304e-07, "epoch": 6.722383720930233, "percentage": 96.03, "elapsed_time": "16:08:01", "remaining_time": "0:39:58"}
{"current_steps": 4630, "total_steps": 4816, "loss": 0.2162, "lr": 1.8345943987471804e-07, "epoch": 6.729651162790698, "percentage": 96.14, "elapsed_time": "16:09:04", "remaining_time": "0:38:55"}
{"current_steps": 4635, "total_steps": 4816, "loss": 0.2122, "lr": 1.7379397703834788e-07, "epoch": 6.736918604651163, "percentage": 96.24, "elapsed_time": "16:10:12", "remaining_time": "0:37:53"}
{"current_steps": 4640, "total_steps": 4816, "loss": 0.2259, "lr": 1.643889502397844e-07, "epoch": 6.7441860465116275, "percentage": 96.35, "elapsed_time": "16:11:16", "remaining_time": "0:36:50"}
{"current_steps": 4645, "total_steps": 4816, "loss": 0.2249, "lr": 1.5524448302297822e-07, "epoch": 6.751453488372093, "percentage": 96.45, "elapsed_time": "16:12:15", "remaining_time": "0:35:47"}
{"current_steps": 4650, "total_steps": 4816, "loss": 0.2201, "lr": 1.4636069550919118e-07, "epoch": 6.758720930232558, "percentage": 96.55, "elapsed_time": "16:13:18", "remaining_time": "0:34:44"}
{"current_steps": 4655, "total_steps": 4816, "loss": 0.2267, "lr": 1.3773770439540646e-07, "epoch": 6.765988372093023, "percentage": 96.66, "elapsed_time": "16:14:17", "remaining_time": "0:33:41"}
{"current_steps": 4660, "total_steps": 4816, "loss": 0.2163, "lr": 1.2937562295279648e-07, "epoch": 6.773255813953488, "percentage": 96.76, "elapsed_time": "16:15:15", "remaining_time": "0:32:38"}
{"current_steps": 4665, "total_steps": 4816, "loss": 0.2263, "lr": 1.2127456102523748e-07, "epoch": 6.780523255813954, "percentage": 96.86, "elapsed_time": "16:16:19", "remaining_time": "0:31:36"}
{"current_steps": 4670, "total_steps": 4816, "loss": 0.2252, "lr": 1.1343462502787506e-07, "epoch": 6.787790697674419, "percentage": 96.97, "elapsed_time": "16:17:15", "remaining_time": "0:30:33"}
{"current_steps": 4675, "total_steps": 4816, "loss": 0.2193, "lr": 1.0585591794570527e-07, "epoch": 6.795058139534884, "percentage": 97.07, "elapsed_time": "16:18:23", "remaining_time": "0:29:30"}
{"current_steps": 4680, "total_steps": 4816, "loss": 0.2213, "lr": 9.853853933224244e-08, "epoch": 6.8023255813953485, "percentage": 97.18, "elapsed_time": "16:19:24", "remaining_time": "0:28:27"}
{"current_steps": 4685, "total_steps": 4816, "loss": 0.2186, "lr": 9.14825853082002e-08, "epoch": 6.809593023255814, "percentage": 97.28, "elapsed_time": "16:20:30", "remaining_time": "0:27:24"}
{"current_steps": 4690, "total_steps": 4816, "loss": 0.2116, "lr": 8.468814856023466e-08, "epoch": 6.816860465116279, "percentage": 97.38, "elapsed_time": "16:21:30", "remaining_time": "0:26:22"}
{"current_steps": 4695, "total_steps": 4816, "loss": 0.2293, "lr": 7.815531833972323e-08, "epoch": 6.824127906976744, "percentage": 97.49, "elapsed_time": "16:22:30", "remaining_time": "0:25:19"}
{"current_steps": 4700, "total_steps": 4816, "loss": 0.2206, "lr": 7.188418046158996e-08, "epoch": 6.8313953488372094, "percentage": 97.59, "elapsed_time": "16:23:34", "remaining_time": "0:24:16"}
{"current_steps": 4705, "total_steps": 4816, "loss": 0.2113, "lr": 6.587481730318645e-08, "epoch": 6.838662790697675, "percentage": 97.7, "elapsed_time": "16:24:35", "remaining_time": "0:23:13"}
{"current_steps": 4710, "total_steps": 4816, "loss": 0.2271, "lr": 6.012730780320163e-08, "epoch": 6.845930232558139, "percentage": 97.8, "elapsed_time": "16:25:38", "remaining_time": "0:22:10"}
{"current_steps": 4715, "total_steps": 4816, "loss": 0.2208, "lr": 5.4641727460631455e-08, "epoch": 6.853197674418604, "percentage": 97.9, "elapsed_time": "16:26:46", "remaining_time": "0:21:08"}
{"current_steps": 4720, "total_steps": 4816, "loss": 0.2174, "lr": 4.941814833377745e-08, "epoch": 6.8604651162790695, "percentage": 98.01, "elapsed_time": "16:27:52", "remaining_time": "0:20:05"}
{"current_steps": 4725, "total_steps": 4816, "loss": 0.2141, "lr": 4.445663903931419e-08, "epoch": 6.867732558139535, "percentage": 98.11, "elapsed_time": "16:28:54", "remaining_time": "0:19:02"}
{"current_steps": 4730, "total_steps": 4816, "loss": 0.2245, "lr": 3.975726475137443e-08, "epoch": 6.875, "percentage": 98.21, "elapsed_time": "16:29:54", "remaining_time": "0:17:59"}
{"current_steps": 4735, "total_steps": 4816, "loss": 0.226, "lr": 3.5320087200698686e-08, "epoch": 6.882267441860465, "percentage": 98.32, "elapsed_time": "16:30:58", "remaining_time": "0:16:57"}
{"current_steps": 4740, "total_steps": 4816, "loss": 0.2203, "lr": 3.114516467383144e-08, "epoch": 6.8895348837209305, "percentage": 98.42, "elapsed_time": "16:31:58", "remaining_time": "0:15:54"}
{"current_steps": 4745, "total_steps": 4816, "loss": 0.2222, "lr": 2.7232552012339542e-08, "epoch": 6.896802325581396, "percentage": 98.53, "elapsed_time": "16:33:02", "remaining_time": "0:14:51"}
{"current_steps": 4750, "total_steps": 4816, "loss": 0.2166, "lr": 2.358230061210387e-08, "epoch": 6.904069767441861, "percentage": 98.63, "elapsed_time": "16:34:01", "remaining_time": "0:13:48"}
{"current_steps": 4755, "total_steps": 4816, "loss": 0.2075, "lr": 2.0194458422646557e-08, "epoch": 6.911337209302325, "percentage": 98.73, "elapsed_time": "16:35:01", "remaining_time": "0:12:45"}
{"current_steps": 4760, "total_steps": 4816, "loss": 0.2144, "lr": 1.706906994648705e-08, "epoch": 6.9186046511627906, "percentage": 98.84, "elapsed_time": "16:36:00", "remaining_time": "0:11:43"}
{"current_steps": 4765, "total_steps": 4816, "loss": 0.2132, "lr": 1.4206176238571457e-08, "epoch": 6.925872093023256, "percentage": 98.94, "elapsed_time": "16:37:02", "remaining_time": "0:10:40"}
{"current_steps": 4770, "total_steps": 4816, "loss": 0.2348, "lr": 1.160581490572632e-08, "epoch": 6.933139534883721, "percentage": 99.04, "elapsed_time": "16:38:08", "remaining_time": "0:09:37"}
{"current_steps": 4775, "total_steps": 4816, "loss": 0.2142, "lr": 9.268020106167896e-09, "epoch": 6.940406976744186, "percentage": 99.15, "elapsed_time": "16:39:12", "remaining_time": "0:08:34"}
{"current_steps": 4780, "total_steps": 4816, "loss": 0.2155, "lr": 7.192822549046963e-09, "epoch": 6.9476744186046515, "percentage": 99.25, "elapsed_time": "16:40:11", "remaining_time": "0:07:31"}
{"current_steps": 4785, "total_steps": 4816, "loss": 0.2268, "lr": 5.38024949405358e-09, "epoch": 6.954941860465116, "percentage": 99.36, "elapsed_time": "16:41:10", "remaining_time": "0:06:29"}
{"current_steps": 4790, "total_steps": 4816, "loss": 0.2196, "lr": 3.8303247510596e-09, "epoch": 6.962209302325581, "percentage": 99.46, "elapsed_time": "16:42:17", "remaining_time": "0:05:26"}
{"current_steps": 4795, "total_steps": 4816, "loss": 0.2158, "lr": 2.5430686797944803e-09, "epoch": 6.969476744186046, "percentage": 99.56, "elapsed_time": "16:43:20", "remaining_time": "0:04:23"}
{"current_steps": 4800, "total_steps": 4816, "loss": 0.2137, "lr": 1.5184981895899342e-09, "epoch": 6.976744186046512, "percentage": 99.67, "elapsed_time": "16:44:22", "remaining_time": "0:03:20"}
{"current_steps": 4805, "total_steps": 4816, "loss": 0.2238, "lr": 7.566267391512228e-10, "epoch": 6.984011627906977, "percentage": 99.77, "elapsed_time": "16:45:27", "remaining_time": "0:02:18"}
{"current_steps": 4810, "total_steps": 4816, "loss": 0.2351, "lr": 2.574643363839613e-10, "epoch": 6.991279069767442, "percentage": 99.88, "elapsed_time": "16:46:29", "remaining_time": "0:01:15"}
{"current_steps": 4815, "total_steps": 4816, "loss": 0.2106, "lr": 2.1017538260892367e-11, "epoch": 6.998546511627907, "percentage": 99.98, "elapsed_time": "16:47:27", "remaining_time": "0:00:12"}
{"current_steps": 4816, "total_steps": 4816, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "16:48:19", "remaining_time": "0:00:00"}

10640
trainer_state.json Normal file

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f98ed4e5da804586bf2e8a4c939209b0b5ec6f6522d7b0926fffefb7374f1785
size 8657

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 41 KiB

BIN
vocab.json (Stored with Git LFS) Normal file

Binary file not shown.