初始化项目,由ModelHub XC社区提供模型

Model: happyhappy-jun/our_qwen2_5_vl_7b_0123_full_reasoning_sft_ep5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-07 00:34:45 +08:00
commit 91c1b227ee
24 changed files with 156263 additions and 0 deletions

36
.gitattributes vendored Normal file
View File

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

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-VL-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: our_qwen2_5_vl_7b_0123_full_reasoning_sft_ep5
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. -->
# our_qwen2_5_vl_7b_0123_full_reasoning_sft_ep5
This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the 0123_qwen2_5_vl_7b_full_reasoning_sft dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
### Framework versions
- Transformers 4.55.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1

24
added_tokens.json Normal file
View File

@@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|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
}

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 5.0,
"total_flos": 5.81885338088951e+19,
"train_loss": 0.4002110935962461,
"train_runtime": 41268.2997,
"train_samples_per_second": 6.721,
"train_steps_per_second": 0.105
}

7
chat_template.jinja Normal file
View File

@@ -0,0 +1,7 @@
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
You are a helpful assistant.<|im_end|>
{% endif %}<|im_start|>{{ message['role'] }}
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
{% endif %}

135
config.json Normal file
View File

@@ -0,0 +1,135 @@
{
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "qwen2_5_vl",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"text_config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": null,
"initializer_range": 0.02,
"intermediate_size": 18944,
"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"
],
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "qwen2_5_vl_text",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": null,
"torch_dtype": "bfloat16",
"use_cache": false,
"use_sliding_window": false,
"video_token_id": null,
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
},
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.55.0",
"use_cache": false,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"depth": 32,
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "silu",
"hidden_size": 1280,
"in_channels": 3,
"in_chans": 3,
"initializer_range": 0.02,
"intermediate_size": 3420,
"model_type": "qwen2_5_vl",
"num_heads": 16,
"out_hidden_size": 3584,
"patch_size": 14,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"temporal_patch_size": 2,
"tokens_per_second": 2,
"torch_dtype": "bfloat16",
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}

12
generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 1e-06,
"transformers_version": "4.55.0"
}

151388
merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b390b66b04f359ee787d4ab809fcb8b7590846d01771826164c3dfe99c565908
size 4968243304

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:adaa52c7bd864beafea020de6bc3d81d53d34ac0a68d97815b2bac020e87887a
size 4991495816

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:87e10f12ab994fb9406bb4bf8d23a8ddf0dc65134ce91692869494bb1b55df4d
size 4932751040

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a35e51e34f5b6c3bd8213f176833cbb81b60f1aea376671a6658a27d80daa76
size 1691924384

View File

@@ -0,0 +1,737 @@
{
"metadata": {
"total_parameters": 8292166656,
"total_size": 16584333312
},
"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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00003-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00003-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00003-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_proj.bias": "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_proj.bias": "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.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00004-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00004-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-00004-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00004-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00004-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_proj.bias": "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_proj.bias": "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.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-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_proj.bias": "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_proj.bias": "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.bias": "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-00002-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00002-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors",
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
}
}

37
preprocessor_config.json Normal file
View File

@@ -0,0 +1,37 @@
{
"crop_size": null,
"data_format": "channels_first",
"default_to_square": true,
"device": null,
"disable_grouping": null,
"do_center_crop": null,
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessorFast",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"input_data_format": null,
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"return_tensors": null,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}

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
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
size 11421896

209
tokenizer_config.json Normal file
View File

@@ -0,0 +1,209 @@
{
"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
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"processor_class": "Qwen2_5_VLProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 5.0,
"total_flos": 5.81885338088951e+19,
"train_loss": 0.4002110935962461,
"train_runtime": 41268.2997,
"train_samples_per_second": 6.721,
"train_steps_per_second": 0.105
}

434
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,434 @@
{"current_steps": 10, "total_steps": 4335, "loss": 0.8031, "lr": 2.0737327188940094e-07, "epoch": 0.011534025374855825, "percentage": 0.23, "elapsed_time": "0:01:42", "remaining_time": "12:17:17"}
{"current_steps": 20, "total_steps": 4335, "loss": 0.7755, "lr": 4.3778801843317976e-07, "epoch": 0.02306805074971165, "percentage": 0.46, "elapsed_time": "0:03:14", "remaining_time": "11:40:01"}
{"current_steps": 30, "total_steps": 4335, "loss": 0.7024, "lr": 6.682027649769586e-07, "epoch": 0.03460207612456748, "percentage": 0.69, "elapsed_time": "0:04:46", "remaining_time": "11:24:04"}
{"current_steps": 40, "total_steps": 4335, "loss": 0.6456, "lr": 8.986175115207374e-07, "epoch": 0.0461361014994233, "percentage": 0.92, "elapsed_time": "0:06:17", "remaining_time": "11:15:43"}
{"current_steps": 50, "total_steps": 4335, "loss": 0.6185, "lr": 1.1290322580645162e-06, "epoch": 0.05767012687427912, "percentage": 1.15, "elapsed_time": "0:07:50", "remaining_time": "11:12:29"}
{"current_steps": 60, "total_steps": 4335, "loss": 0.5842, "lr": 1.359447004608295e-06, "epoch": 0.06920415224913495, "percentage": 1.38, "elapsed_time": "0:09:24", "remaining_time": "11:10:32"}
{"current_steps": 70, "total_steps": 4335, "loss": 0.5822, "lr": 1.5898617511520738e-06, "epoch": 0.08073817762399077, "percentage": 1.61, "elapsed_time": "0:10:58", "remaining_time": "11:09:11"}
{"current_steps": 80, "total_steps": 4335, "loss": 0.577, "lr": 1.8202764976958525e-06, "epoch": 0.0922722029988466, "percentage": 1.85, "elapsed_time": "0:12:31", "remaining_time": "11:05:49"}
{"current_steps": 90, "total_steps": 4335, "loss": 0.5708, "lr": 2.0506912442396317e-06, "epoch": 0.10380622837370242, "percentage": 2.08, "elapsed_time": "0:14:02", "remaining_time": "11:02:02"}
{"current_steps": 100, "total_steps": 4335, "loss": 0.5756, "lr": 2.2811059907834106e-06, "epoch": 0.11534025374855825, "percentage": 2.31, "elapsed_time": "0:15:32", "remaining_time": "10:58:23"}
{"current_steps": 110, "total_steps": 4335, "loss": 0.5651, "lr": 2.5115207373271895e-06, "epoch": 0.12687427912341406, "percentage": 2.54, "elapsed_time": "0:17:03", "remaining_time": "10:55:27"}
{"current_steps": 120, "total_steps": 4335, "loss": 0.5626, "lr": 2.7419354838709676e-06, "epoch": 0.1384083044982699, "percentage": 2.77, "elapsed_time": "0:18:33", "remaining_time": "10:52:02"}
{"current_steps": 130, "total_steps": 4335, "loss": 0.5579, "lr": 2.9723502304147465e-06, "epoch": 0.14994232987312572, "percentage": 3.0, "elapsed_time": "0:20:03", "remaining_time": "10:49:04"}
{"current_steps": 140, "total_steps": 4335, "loss": 0.5558, "lr": 3.2027649769585254e-06, "epoch": 0.16147635524798154, "percentage": 3.23, "elapsed_time": "0:21:34", "remaining_time": "10:46:30"}
{"current_steps": 150, "total_steps": 4335, "loss": 0.5572, "lr": 3.4331797235023043e-06, "epoch": 0.17301038062283736, "percentage": 3.46, "elapsed_time": "0:23:08", "remaining_time": "10:45:41"}
{"current_steps": 160, "total_steps": 4335, "loss": 0.5512, "lr": 3.6635944700460837e-06, "epoch": 0.1845444059976932, "percentage": 3.69, "elapsed_time": "0:24:39", "remaining_time": "10:43:24"}
{"current_steps": 170, "total_steps": 4335, "loss": 0.5589, "lr": 3.894009216589862e-06, "epoch": 0.19607843137254902, "percentage": 3.92, "elapsed_time": "0:26:13", "remaining_time": "10:42:29"}
{"current_steps": 180, "total_steps": 4335, "loss": 0.5511, "lr": 4.124423963133641e-06, "epoch": 0.20761245674740483, "percentage": 4.15, "elapsed_time": "0:27:47", "remaining_time": "10:41:33"}
{"current_steps": 190, "total_steps": 4335, "loss": 0.5459, "lr": 4.35483870967742e-06, "epoch": 0.21914648212226068, "percentage": 4.38, "elapsed_time": "0:29:21", "remaining_time": "10:40:25"}
{"current_steps": 200, "total_steps": 4335, "loss": 0.5572, "lr": 4.585253456221199e-06, "epoch": 0.2306805074971165, "percentage": 4.61, "elapsed_time": "0:30:54", "remaining_time": "10:38:51"}
{"current_steps": 210, "total_steps": 4335, "loss": 0.5477, "lr": 4.8156682027649774e-06, "epoch": 0.2422145328719723, "percentage": 4.84, "elapsed_time": "0:32:26", "remaining_time": "10:37:22"}
{"current_steps": 220, "total_steps": 4335, "loss": 0.5468, "lr": 5.046082949308756e-06, "epoch": 0.2537485582468281, "percentage": 5.07, "elapsed_time": "0:34:01", "remaining_time": "10:36:22"}
{"current_steps": 230, "total_steps": 4335, "loss": 0.5546, "lr": 5.276497695852535e-06, "epoch": 0.26528258362168394, "percentage": 5.31, "elapsed_time": "0:35:33", "remaining_time": "10:34:38"}
{"current_steps": 240, "total_steps": 4335, "loss": 0.5516, "lr": 5.506912442396314e-06, "epoch": 0.2768166089965398, "percentage": 5.54, "elapsed_time": "0:37:06", "remaining_time": "10:33:04"}
{"current_steps": 250, "total_steps": 4335, "loss": 0.5649, "lr": 5.737327188940093e-06, "epoch": 0.28835063437139563, "percentage": 5.77, "elapsed_time": "0:38:37", "remaining_time": "10:31:08"}
{"current_steps": 260, "total_steps": 4335, "loss": 0.5624, "lr": 5.967741935483872e-06, "epoch": 0.29988465974625145, "percentage": 6.0, "elapsed_time": "0:40:11", "remaining_time": "10:29:51"}
{"current_steps": 270, "total_steps": 4335, "loss": 0.561, "lr": 6.198156682027651e-06, "epoch": 0.31141868512110726, "percentage": 6.23, "elapsed_time": "0:41:43", "remaining_time": "10:28:11"}
{"current_steps": 280, "total_steps": 4335, "loss": 0.5585, "lr": 6.4285714285714295e-06, "epoch": 0.3229527104959631, "percentage": 6.46, "elapsed_time": "0:43:16", "remaining_time": "10:26:36"}
{"current_steps": 290, "total_steps": 4335, "loss": 0.5652, "lr": 6.658986175115207e-06, "epoch": 0.3344867358708189, "percentage": 6.69, "elapsed_time": "0:44:49", "remaining_time": "10:25:19"}
{"current_steps": 300, "total_steps": 4335, "loss": 0.5589, "lr": 6.8894009216589865e-06, "epoch": 0.3460207612456747, "percentage": 6.92, "elapsed_time": "0:46:21", "remaining_time": "10:23:24"}
{"current_steps": 310, "total_steps": 4335, "loss": 0.5646, "lr": 7.119815668202765e-06, "epoch": 0.3575547866205306, "percentage": 7.15, "elapsed_time": "0:47:52", "remaining_time": "10:21:41"}
{"current_steps": 320, "total_steps": 4335, "loss": 0.5542, "lr": 7.350230414746544e-06, "epoch": 0.3690888119953864, "percentage": 7.38, "elapsed_time": "0:49:26", "remaining_time": "10:20:18"}
{"current_steps": 330, "total_steps": 4335, "loss": 0.5448, "lr": 7.580645161290323e-06, "epoch": 0.3806228373702422, "percentage": 7.61, "elapsed_time": "0:50:59", "remaining_time": "10:18:52"}
{"current_steps": 340, "total_steps": 4335, "loss": 0.5622, "lr": 7.811059907834102e-06, "epoch": 0.39215686274509803, "percentage": 7.84, "elapsed_time": "0:52:33", "remaining_time": "10:17:32"}
{"current_steps": 350, "total_steps": 4335, "loss": 0.5609, "lr": 8.041474654377881e-06, "epoch": 0.40369088811995385, "percentage": 8.07, "elapsed_time": "0:54:05", "remaining_time": "10:15:51"}
{"current_steps": 360, "total_steps": 4335, "loss": 0.5686, "lr": 8.271889400921659e-06, "epoch": 0.41522491349480967, "percentage": 8.3, "elapsed_time": "0:55:38", "remaining_time": "10:14:18"}
{"current_steps": 370, "total_steps": 4335, "loss": 0.5613, "lr": 8.502304147465438e-06, "epoch": 0.42675893886966554, "percentage": 8.54, "elapsed_time": "0:57:08", "remaining_time": "10:12:19"}
{"current_steps": 380, "total_steps": 4335, "loss": 0.5544, "lr": 8.732718894009218e-06, "epoch": 0.43829296424452135, "percentage": 8.77, "elapsed_time": "0:58:41", "remaining_time": "10:10:48"}
{"current_steps": 390, "total_steps": 4335, "loss": 0.5618, "lr": 8.963133640552995e-06, "epoch": 0.44982698961937717, "percentage": 9.0, "elapsed_time": "1:00:12", "remaining_time": "10:08:57"}
{"current_steps": 400, "total_steps": 4335, "loss": 0.5666, "lr": 9.193548387096775e-06, "epoch": 0.461361014994233, "percentage": 9.23, "elapsed_time": "1:01:45", "remaining_time": "10:07:34"}
{"current_steps": 410, "total_steps": 4335, "loss": 0.5611, "lr": 9.423963133640554e-06, "epoch": 0.4728950403690888, "percentage": 9.46, "elapsed_time": "1:03:15", "remaining_time": "10:05:38"}
{"current_steps": 420, "total_steps": 4335, "loss": 0.5683, "lr": 9.654377880184332e-06, "epoch": 0.4844290657439446, "percentage": 9.69, "elapsed_time": "1:04:46", "remaining_time": "10:03:43"}
{"current_steps": 430, "total_steps": 4335, "loss": 0.5696, "lr": 9.884792626728111e-06, "epoch": 0.49596309111880044, "percentage": 9.92, "elapsed_time": "1:06:16", "remaining_time": "10:01:53"}
{"current_steps": 440, "total_steps": 4335, "loss": 0.5783, "lr": 9.999959465270863e-06, "epoch": 0.5074971164936563, "percentage": 10.15, "elapsed_time": "1:07:48", "remaining_time": "10:00:11"}
{"current_steps": 450, "total_steps": 4335, "loss": 0.5717, "lr": 9.999635191381105e-06, "epoch": 0.5190311418685121, "percentage": 10.38, "elapsed_time": "1:09:19", "remaining_time": "9:58:33"}
{"current_steps": 460, "total_steps": 4335, "loss": 0.5621, "lr": 9.998986664632473e-06, "epoch": 0.5305651672433679, "percentage": 10.61, "elapsed_time": "1:10:51", "remaining_time": "9:56:50"}
{"current_steps": 470, "total_steps": 4335, "loss": 0.5645, "lr": 9.998013927085362e-06, "epoch": 0.5420991926182238, "percentage": 10.84, "elapsed_time": "1:12:24", "remaining_time": "9:55:22"}
{"current_steps": 480, "total_steps": 4335, "loss": 0.5645, "lr": 9.996717041826965e-06, "epoch": 0.5536332179930796, "percentage": 11.07, "elapsed_time": "1:13:56", "remaining_time": "9:53:50"}
{"current_steps": 490, "total_steps": 4335, "loss": 0.5604, "lr": 9.995096092967168e-06, "epoch": 0.5651672433679354, "percentage": 11.3, "elapsed_time": "1:15:28", "remaining_time": "9:52:14"}
{"current_steps": 500, "total_steps": 4335, "loss": 0.5724, "lr": 9.993151185633098e-06, "epoch": 0.5767012687427913, "percentage": 11.53, "elapsed_time": "1:17:01", "remaining_time": "9:50:43"}
{"current_steps": 510, "total_steps": 4335, "loss": 0.5555, "lr": 9.990882445962318e-06, "epoch": 0.5882352941176471, "percentage": 11.76, "elapsed_time": "1:20:29", "remaining_time": "10:03:41"}
{"current_steps": 520, "total_steps": 4335, "loss": 0.5628, "lr": 9.988290021094624e-06, "epoch": 0.5997693194925029, "percentage": 12.0, "elapsed_time": "1:22:03", "remaining_time": "10:02:00"}
{"current_steps": 530, "total_steps": 4335, "loss": 0.5688, "lr": 9.985374079162518e-06, "epoch": 0.6113033448673587, "percentage": 12.23, "elapsed_time": "1:23:33", "remaining_time": "9:59:52"}
{"current_steps": 540, "total_steps": 4335, "loss": 0.5687, "lr": 9.982134809280301e-06, "epoch": 0.6228373702422145, "percentage": 12.46, "elapsed_time": "1:25:02", "remaining_time": "9:57:39"}
{"current_steps": 550, "total_steps": 4335, "loss": 0.5606, "lr": 9.978572421531804e-06, "epoch": 0.6343713956170703, "percentage": 12.69, "elapsed_time": "1:26:32", "remaining_time": "9:55:35"}
{"current_steps": 560, "total_steps": 4335, "loss": 0.5739, "lr": 9.974687146956768e-06, "epoch": 0.6459054209919262, "percentage": 12.92, "elapsed_time": "1:28:05", "remaining_time": "9:53:48"}
{"current_steps": 570, "total_steps": 4335, "loss": 0.5667, "lr": 9.970479237535855e-06, "epoch": 0.657439446366782, "percentage": 13.15, "elapsed_time": "1:29:38", "remaining_time": "9:52:04"}
{"current_steps": 580, "total_steps": 4335, "loss": 0.5757, "lr": 9.965948966174308e-06, "epoch": 0.6689734717416378, "percentage": 13.38, "elapsed_time": "1:31:08", "remaining_time": "9:50:03"}
{"current_steps": 590, "total_steps": 4335, "loss": 0.5677, "lr": 9.961096626684252e-06, "epoch": 0.6805074971164936, "percentage": 13.61, "elapsed_time": "1:32:40", "remaining_time": "9:48:13"}
{"current_steps": 600, "total_steps": 4335, "loss": 0.561, "lr": 9.95592253376564e-06, "epoch": 0.6920415224913494, "percentage": 13.84, "elapsed_time": "1:34:10", "remaining_time": "9:46:12"}
{"current_steps": 610, "total_steps": 4335, "loss": 0.576, "lr": 9.950427022985838e-06, "epoch": 0.7035755478662054, "percentage": 14.07, "elapsed_time": "1:35:40", "remaining_time": "9:44:16"}
{"current_steps": 620, "total_steps": 4335, "loss": 0.5667, "lr": 9.944610450757865e-06, "epoch": 0.7151095732410612, "percentage": 14.3, "elapsed_time": "1:37:11", "remaining_time": "9:42:22"}
{"current_steps": 630, "total_steps": 4335, "loss": 0.5649, "lr": 9.938473194317284e-06, "epoch": 0.726643598615917, "percentage": 14.53, "elapsed_time": "1:38:42", "remaining_time": "9:40:30"}
{"current_steps": 640, "total_steps": 4335, "loss": 0.5551, "lr": 9.932015651697724e-06, "epoch": 0.7381776239907728, "percentage": 14.76, "elapsed_time": "1:40:16", "remaining_time": "9:38:54"}
{"current_steps": 650, "total_steps": 4335, "loss": 0.5625, "lr": 9.925238241705071e-06, "epoch": 0.7497116493656286, "percentage": 14.99, "elapsed_time": "1:41:49", "remaining_time": "9:37:18"}
{"current_steps": 660, "total_steps": 4335, "loss": 0.5643, "lr": 9.918141403890312e-06, "epoch": 0.7612456747404844, "percentage": 15.22, "elapsed_time": "1:43:22", "remaining_time": "9:35:33"}
{"current_steps": 670, "total_steps": 4335, "loss": 0.5656, "lr": 9.910725598521014e-06, "epoch": 0.7727797001153403, "percentage": 15.46, "elapsed_time": "1:44:56", "remaining_time": "9:34:01"}
{"current_steps": 680, "total_steps": 4335, "loss": 0.5611, "lr": 9.90299130655149e-06, "epoch": 0.7843137254901961, "percentage": 15.69, "elapsed_time": "1:46:28", "remaining_time": "9:32:17"}
{"current_steps": 690, "total_steps": 4335, "loss": 0.5684, "lr": 9.894939029591597e-06, "epoch": 0.7958477508650519, "percentage": 15.92, "elapsed_time": "1:47:56", "remaining_time": "9:30:12"}
{"current_steps": 700, "total_steps": 4335, "loss": 0.5583, "lr": 9.886569289874198e-06, "epoch": 0.8073817762399077, "percentage": 16.15, "elapsed_time": "1:49:29", "remaining_time": "9:28:34"}
{"current_steps": 710, "total_steps": 4335, "loss": 0.5594, "lr": 9.877882630221307e-06, "epoch": 0.8189158016147635, "percentage": 16.38, "elapsed_time": "1:51:02", "remaining_time": "9:26:58"}
{"current_steps": 720, "total_steps": 4335, "loss": 0.5609, "lr": 9.868879614008875e-06, "epoch": 0.8304498269896193, "percentage": 16.61, "elapsed_time": "1:52:35", "remaining_time": "9:25:17"}
{"current_steps": 730, "total_steps": 4335, "loss": 0.5556, "lr": 9.859560825130253e-06, "epoch": 0.8419838523644751, "percentage": 16.84, "elapsed_time": "1:54:08", "remaining_time": "9:23:40"}
{"current_steps": 740, "total_steps": 4335, "loss": 0.5606, "lr": 9.84992686795832e-06, "epoch": 0.8535178777393311, "percentage": 17.07, "elapsed_time": "1:55:39", "remaining_time": "9:21:50"}
{"current_steps": 750, "total_steps": 4335, "loss": 0.562, "lr": 9.8399783673063e-06, "epoch": 0.8650519031141869, "percentage": 17.3, "elapsed_time": "1:57:09", "remaining_time": "9:20:02"}
{"current_steps": 760, "total_steps": 4335, "loss": 0.5718, "lr": 9.829715968387222e-06, "epoch": 0.8765859284890427, "percentage": 17.53, "elapsed_time": "1:58:41", "remaining_time": "9:18:19"}
{"current_steps": 770, "total_steps": 4335, "loss": 0.5604, "lr": 9.819140336772084e-06, "epoch": 0.8881199538638985, "percentage": 17.76, "elapsed_time": "2:00:13", "remaining_time": "9:16:36"}
{"current_steps": 780, "total_steps": 4335, "loss": 0.5631, "lr": 9.808252158346686e-06, "epoch": 0.8996539792387543, "percentage": 17.99, "elapsed_time": "2:01:46", "remaining_time": "9:15:00"}
{"current_steps": 790, "total_steps": 4335, "loss": 0.5568, "lr": 9.797052139267152e-06, "epoch": 0.9111880046136102, "percentage": 18.22, "elapsed_time": "2:03:17", "remaining_time": "9:13:13"}
{"current_steps": 800, "total_steps": 4335, "loss": 0.5657, "lr": 9.785541005914115e-06, "epoch": 0.922722029988466, "percentage": 18.45, "elapsed_time": "2:04:50", "remaining_time": "9:11:39"}
{"current_steps": 810, "total_steps": 4335, "loss": 0.5718, "lr": 9.773719504845627e-06, "epoch": 0.9342560553633218, "percentage": 18.69, "elapsed_time": "2:06:22", "remaining_time": "9:09:58"}
{"current_steps": 820, "total_steps": 4335, "loss": 0.5557, "lr": 9.761588402748732e-06, "epoch": 0.9457900807381776, "percentage": 18.92, "elapsed_time": "2:07:54", "remaining_time": "9:08:16"}
{"current_steps": 830, "total_steps": 4335, "loss": 0.5654, "lr": 9.74914848638974e-06, "epoch": 0.9573241061130334, "percentage": 19.15, "elapsed_time": "2:09:25", "remaining_time": "9:06:31"}
{"current_steps": 840, "total_steps": 4335, "loss": 0.5713, "lr": 9.736400562563202e-06, "epoch": 0.9688581314878892, "percentage": 19.38, "elapsed_time": "2:10:54", "remaining_time": "9:04:42"}
{"current_steps": 850, "total_steps": 4335, "loss": 0.5623, "lr": 9.723345458039595e-06, "epoch": 0.9803921568627451, "percentage": 19.61, "elapsed_time": "2:12:27", "remaining_time": "9:03:03"}
{"current_steps": 860, "total_steps": 4335, "loss": 0.567, "lr": 9.709984019511685e-06, "epoch": 0.9919261822376009, "percentage": 19.84, "elapsed_time": "2:13:57", "remaining_time": "9:01:16"}
{"current_steps": 870, "total_steps": 4335, "loss": 0.5578, "lr": 9.696317113539626e-06, "epoch": 1.0034602076124568, "percentage": 20.07, "elapsed_time": "2:15:33", "remaining_time": "8:59:53"}
{"current_steps": 880, "total_steps": 4335, "loss": 0.496, "lr": 9.682345626494755e-06, "epoch": 1.0149942329873125, "percentage": 20.3, "elapsed_time": "2:17:07", "remaining_time": "8:58:22"}
{"current_steps": 890, "total_steps": 4335, "loss": 0.5167, "lr": 9.668070464502112e-06, "epoch": 1.0265282583621684, "percentage": 20.53, "elapsed_time": "2:18:39", "remaining_time": "8:56:43"}
{"current_steps": 900, "total_steps": 4335, "loss": 0.5085, "lr": 9.653492553381659e-06, "epoch": 1.0380622837370241, "percentage": 20.76, "elapsed_time": "2:20:13", "remaining_time": "8:55:11"}
{"current_steps": 910, "total_steps": 4335, "loss": 0.5072, "lr": 9.638612838588253e-06, "epoch": 1.04959630911188, "percentage": 20.99, "elapsed_time": "2:21:48", "remaining_time": "8:53:42"}
{"current_steps": 920, "total_steps": 4335, "loss": 0.505, "lr": 9.623432285150314e-06, "epoch": 1.0611303344867358, "percentage": 21.22, "elapsed_time": "2:23:22", "remaining_time": "8:52:12"}
{"current_steps": 930, "total_steps": 4335, "loss": 0.5062, "lr": 9.607951877607246e-06, "epoch": 1.0726643598615917, "percentage": 21.45, "elapsed_time": "2:24:55", "remaining_time": "8:50:37"}
{"current_steps": 940, "total_steps": 4335, "loss": 0.5112, "lr": 9.592172619945584e-06, "epoch": 1.0841983852364474, "percentage": 21.68, "elapsed_time": "2:26:28", "remaining_time": "8:49:00"}
{"current_steps": 950, "total_steps": 4335, "loss": 0.5214, "lr": 9.576095535533873e-06, "epoch": 1.0957324106113033, "percentage": 21.91, "elapsed_time": "2:27:59", "remaining_time": "8:47:20"}
{"current_steps": 960, "total_steps": 4335, "loss": 0.5146, "lr": 9.55972166705631e-06, "epoch": 1.1072664359861593, "percentage": 22.15, "elapsed_time": "2:29:33", "remaining_time": "8:45:47"}
{"current_steps": 970, "total_steps": 4335, "loss": 0.5155, "lr": 9.543052076445105e-06, "epoch": 1.118800461361015, "percentage": 22.38, "elapsed_time": "2:31:07", "remaining_time": "8:44:17"}
{"current_steps": 980, "total_steps": 4335, "loss": 0.5119, "lr": 9.526087844811622e-06, "epoch": 1.130334486735871, "percentage": 22.61, "elapsed_time": "2:32:41", "remaining_time": "8:42:42"}
{"current_steps": 990, "total_steps": 4335, "loss": 0.5219, "lr": 9.508830072376255e-06, "epoch": 1.1418685121107266, "percentage": 22.84, "elapsed_time": "2:34:13", "remaining_time": "8:41:07"}
{"current_steps": 1000, "total_steps": 4335, "loss": 0.4995, "lr": 9.491279878397077e-06, "epoch": 1.1534025374855825, "percentage": 23.07, "elapsed_time": "2:35:47", "remaining_time": "8:39:33"}
{"current_steps": 1010, "total_steps": 4335, "loss": 0.5151, "lr": 9.47343840109725e-06, "epoch": 1.1649365628604382, "percentage": 23.3, "elapsed_time": "2:39:15", "remaining_time": "8:44:16"}
{"current_steps": 1020, "total_steps": 4335, "loss": 0.5139, "lr": 9.455306797591201e-06, "epoch": 1.1764705882352942, "percentage": 23.53, "elapsed_time": "2:40:47", "remaining_time": "8:42:35"}
{"current_steps": 1030, "total_steps": 4335, "loss": 0.5098, "lr": 9.436886243809587e-06, "epoch": 1.1880046136101499, "percentage": 23.76, "elapsed_time": "2:42:18", "remaining_time": "8:40:49"}
{"current_steps": 1040, "total_steps": 4335, "loss": 0.5192, "lr": 9.418177934423015e-06, "epoch": 1.1995386389850058, "percentage": 23.99, "elapsed_time": "2:43:51", "remaining_time": "8:39:08"}
{"current_steps": 1050, "total_steps": 4335, "loss": 0.5192, "lr": 9.399183082764572e-06, "epoch": 1.2110726643598615, "percentage": 24.22, "elapsed_time": "2:45:25", "remaining_time": "8:37:31"}
{"current_steps": 1060, "total_steps": 4335, "loss": 0.5172, "lr": 9.379902920751133e-06, "epoch": 1.2226066897347174, "percentage": 24.45, "elapsed_time": "2:46:58", "remaining_time": "8:35:53"}
{"current_steps": 1070, "total_steps": 4335, "loss": 0.5168, "lr": 9.36033869880346e-06, "epoch": 1.2341407151095733, "percentage": 24.68, "elapsed_time": "2:48:33", "remaining_time": "8:34:19"}
{"current_steps": 1080, "total_steps": 4335, "loss": 0.5141, "lr": 9.340491685765111e-06, "epoch": 1.245674740484429, "percentage": 24.91, "elapsed_time": "2:50:05", "remaining_time": "8:32:38"}
{"current_steps": 1090, "total_steps": 4335, "loss": 0.5205, "lr": 9.320363168820146e-06, "epoch": 1.2572087658592848, "percentage": 25.14, "elapsed_time": "2:51:38", "remaining_time": "8:31:00"}
{"current_steps": 1100, "total_steps": 4335, "loss": 0.5229, "lr": 9.299954453409644e-06, "epoch": 1.2687427912341407, "percentage": 25.37, "elapsed_time": "2:53:12", "remaining_time": "8:29:22"}
{"current_steps": 1110, "total_steps": 4335, "loss": 0.5114, "lr": 9.279266863147039e-06, "epoch": 1.2802768166089966, "percentage": 25.61, "elapsed_time": "2:54:45", "remaining_time": "8:27:45"}
{"current_steps": 1120, "total_steps": 4335, "loss": 0.52, "lr": 9.258301739732284e-06, "epoch": 1.2918108419838523, "percentage": 25.84, "elapsed_time": "2:56:17", "remaining_time": "8:26:01"}
{"current_steps": 1130, "total_steps": 4335, "loss": 0.5064, "lr": 9.237060442864826e-06, "epoch": 1.3033448673587082, "percentage": 26.07, "elapsed_time": "2:57:52", "remaining_time": "8:24:29"}
{"current_steps": 1140, "total_steps": 4335, "loss": 0.5195, "lr": 9.215544350155423e-06, "epoch": 1.314878892733564, "percentage": 26.3, "elapsed_time": "2:59:24", "remaining_time": "8:22:49"}
{"current_steps": 1150, "total_steps": 4335, "loss": 0.5132, "lr": 9.193754857036804e-06, "epoch": 1.3264129181084199, "percentage": 26.53, "elapsed_time": "3:00:57", "remaining_time": "8:21:09"}
{"current_steps": 1160, "total_steps": 4335, "loss": 0.5208, "lr": 9.171693376673163e-06, "epoch": 1.3379469434832756, "percentage": 26.76, "elapsed_time": "3:02:32", "remaining_time": "8:19:36"}
{"current_steps": 1170, "total_steps": 4335, "loss": 0.5209, "lr": 9.149361339868508e-06, "epoch": 1.3494809688581315, "percentage": 26.99, "elapsed_time": "3:04:06", "remaining_time": "8:18:00"}
{"current_steps": 1180, "total_steps": 4335, "loss": 0.5145, "lr": 9.126760194973873e-06, "epoch": 1.3610149942329874, "percentage": 27.22, "elapsed_time": "3:05:39", "remaining_time": "8:16:24"}
{"current_steps": 1190, "total_steps": 4335, "loss": 0.5084, "lr": 9.10389140779337e-06, "epoch": 1.3725490196078431, "percentage": 27.45, "elapsed_time": "3:07:12", "remaining_time": "8:14:47"}
{"current_steps": 1200, "total_steps": 4335, "loss": 0.5208, "lr": 9.080756461489141e-06, "epoch": 1.3840830449826989, "percentage": 27.68, "elapsed_time": "3:08:45", "remaining_time": "8:13:06"}
{"current_steps": 1210, "total_steps": 4335, "loss": 0.5105, "lr": 9.057356856485156e-06, "epoch": 1.3956170703575548, "percentage": 27.91, "elapsed_time": "3:10:19", "remaining_time": "8:11:31"}
{"current_steps": 1220, "total_steps": 4335, "loss": 0.5131, "lr": 9.0336941103699e-06, "epoch": 1.4071510957324107, "percentage": 28.14, "elapsed_time": "3:11:52", "remaining_time": "8:09:53"}
{"current_steps": 1230, "total_steps": 4335, "loss": 0.5168, "lr": 9.009769757797963e-06, "epoch": 1.4186851211072664, "percentage": 28.37, "elapsed_time": "3:13:21", "remaining_time": "8:08:07"}
{"current_steps": 1240, "total_steps": 4335, "loss": 0.5153, "lr": 8.9855853503905e-06, "epoch": 1.4302191464821223, "percentage": 28.6, "elapsed_time": "3:14:54", "remaining_time": "8:06:30"}
{"current_steps": 1250, "total_steps": 4335, "loss": 0.5277, "lr": 8.961142456634592e-06, "epoch": 1.441753171856978, "percentage": 28.84, "elapsed_time": "3:16:28", "remaining_time": "8:04:53"}
{"current_steps": 1260, "total_steps": 4335, "loss": 0.5246, "lr": 8.936442661781544e-06, "epoch": 1.453287197231834, "percentage": 29.07, "elapsed_time": "3:18:01", "remaining_time": "8:03:17"}
{"current_steps": 1270, "total_steps": 4335, "loss": 0.5201, "lr": 8.911487567744049e-06, "epoch": 1.4648212226066897, "percentage": 29.3, "elapsed_time": "3:19:34", "remaining_time": "8:01:39"}
{"current_steps": 1280, "total_steps": 4335, "loss": 0.5223, "lr": 8.886278792992313e-06, "epoch": 1.4763552479815456, "percentage": 29.53, "elapsed_time": "3:21:07", "remaining_time": "8:00:02"}
{"current_steps": 1290, "total_steps": 4335, "loss": 0.5256, "lr": 8.860817972449077e-06, "epoch": 1.4878892733564013, "percentage": 29.76, "elapsed_time": "3:22:41", "remaining_time": "7:58:26"}
{"current_steps": 1300, "total_steps": 4335, "loss": 0.5228, "lr": 8.835106757383594e-06, "epoch": 1.4994232987312572, "percentage": 29.99, "elapsed_time": "3:24:13", "remaining_time": "7:56:46"}
{"current_steps": 1310, "total_steps": 4335, "loss": 0.5159, "lr": 8.80914681530452e-06, "epoch": 1.510957324106113, "percentage": 30.22, "elapsed_time": "3:25:42", "remaining_time": "7:55:01"}
{"current_steps": 1320, "total_steps": 4335, "loss": 0.5289, "lr": 8.782939829851792e-06, "epoch": 1.5224913494809689, "percentage": 30.45, "elapsed_time": "3:27:16", "remaining_time": "7:53:26"}
{"current_steps": 1330, "total_steps": 4335, "loss": 0.5202, "lr": 8.756487500687405e-06, "epoch": 1.5340253748558248, "percentage": 30.68, "elapsed_time": "3:28:49", "remaining_time": "7:51:48"}
{"current_steps": 1340, "total_steps": 4335, "loss": 0.5146, "lr": 8.729791543385205e-06, "epoch": 1.5455594002306805, "percentage": 30.91, "elapsed_time": "3:30:23", "remaining_time": "7:50:13"}
{"current_steps": 1350, "total_steps": 4335, "loss": 0.5157, "lr": 8.702853689319608e-06, "epoch": 1.5570934256055362, "percentage": 31.14, "elapsed_time": "3:31:55", "remaining_time": "7:48:35"}
{"current_steps": 1360, "total_steps": 4335, "loss": 0.5272, "lr": 8.675675685553321e-06, "epoch": 1.5686274509803921, "percentage": 31.37, "elapsed_time": "3:33:27", "remaining_time": "7:46:56"}
{"current_steps": 1370, "total_steps": 4335, "loss": 0.5136, "lr": 8.648259294724038e-06, "epoch": 1.580161476355248, "percentage": 31.6, "elapsed_time": "3:34:59", "remaining_time": "7:45:18"}
{"current_steps": 1380, "total_steps": 4335, "loss": 0.5241, "lr": 8.620606294930108e-06, "epoch": 1.5916955017301038, "percentage": 31.83, "elapsed_time": "3:36:31", "remaining_time": "7:43:38"}
{"current_steps": 1390, "total_steps": 4335, "loss": 0.5278, "lr": 8.592718479615233e-06, "epoch": 1.6032295271049595, "percentage": 32.06, "elapsed_time": "3:38:05", "remaining_time": "7:42:03"}
{"current_steps": 1400, "total_steps": 4335, "loss": 0.5088, "lr": 8.564597657452147e-06, "epoch": 1.6147635524798154, "percentage": 32.3, "elapsed_time": "3:39:40", "remaining_time": "7:40:31"}
{"current_steps": 1410, "total_steps": 4335, "loss": 0.5188, "lr": 8.536245652225313e-06, "epoch": 1.6262975778546713, "percentage": 32.53, "elapsed_time": "3:41:13", "remaining_time": "7:38:54"}
{"current_steps": 1420, "total_steps": 4335, "loss": 0.5203, "lr": 8.50766430271264e-06, "epoch": 1.637831603229527, "percentage": 32.76, "elapsed_time": "3:42:45", "remaining_time": "7:37:17"}
{"current_steps": 1430, "total_steps": 4335, "loss": 0.5214, "lr": 8.47885546256623e-06, "epoch": 1.649365628604383, "percentage": 32.99, "elapsed_time": "3:44:17", "remaining_time": "7:35:37"}
{"current_steps": 1440, "total_steps": 4335, "loss": 0.5204, "lr": 8.449821000192167e-06, "epoch": 1.6608996539792389, "percentage": 33.22, "elapsed_time": "3:45:48", "remaining_time": "7:33:57"}
{"current_steps": 1450, "total_steps": 4335, "loss": 0.5181, "lr": 8.420562798629319e-06, "epoch": 1.6724336793540946, "percentage": 33.45, "elapsed_time": "3:47:22", "remaining_time": "7:32:23"}
{"current_steps": 1460, "total_steps": 4335, "loss": 0.5179, "lr": 8.39108275542724e-06, "epoch": 1.6839677047289503, "percentage": 33.68, "elapsed_time": "3:48:56", "remaining_time": "7:30:49"}
{"current_steps": 1470, "total_steps": 4335, "loss": 0.5249, "lr": 8.361382782523084e-06, "epoch": 1.6955017301038062, "percentage": 33.91, "elapsed_time": "3:50:29", "remaining_time": "7:29:13"}
{"current_steps": 1480, "total_steps": 4335, "loss": 0.521, "lr": 8.331464806117615e-06, "epoch": 1.7070357554786622, "percentage": 34.14, "elapsed_time": "3:52:04", "remaining_time": "7:27:40"}
{"current_steps": 1490, "total_steps": 4335, "loss": 0.5081, "lr": 8.301330766550279e-06, "epoch": 1.7185697808535179, "percentage": 34.37, "elapsed_time": "3:53:36", "remaining_time": "7:26:02"}
{"current_steps": 1500, "total_steps": 4335, "loss": 0.5241, "lr": 8.270982618173366e-06, "epoch": 1.7301038062283736, "percentage": 34.6, "elapsed_time": "3:55:09", "remaining_time": "7:24:26"}
{"current_steps": 1510, "total_steps": 4335, "loss": 0.522, "lr": 8.240422329225256e-06, "epoch": 1.7416378316032295, "percentage": 34.83, "elapsed_time": "3:58:33", "remaining_time": "7:26:19"}
{"current_steps": 1520, "total_steps": 4335, "loss": 0.5122, "lr": 8.209651881702771e-06, "epoch": 1.7531718569780854, "percentage": 35.06, "elapsed_time": "4:00:05", "remaining_time": "7:24:38"}
{"current_steps": 1530, "total_steps": 4335, "loss": 0.5044, "lr": 8.17867327123263e-06, "epoch": 1.7647058823529411, "percentage": 35.29, "elapsed_time": "4:01:38", "remaining_time": "7:23:00"}
{"current_steps": 1540, "total_steps": 4335, "loss": 0.5212, "lr": 8.147488506942026e-06, "epoch": 1.776239907727797, "percentage": 35.52, "elapsed_time": "4:03:08", "remaining_time": "7:21:16"}
{"current_steps": 1550, "total_steps": 4335, "loss": 0.5219, "lr": 8.116099611328317e-06, "epoch": 1.787773933102653, "percentage": 35.76, "elapsed_time": "4:04:38", "remaining_time": "7:19:34"}
{"current_steps": 1560, "total_steps": 4335, "loss": 0.5143, "lr": 8.084508620127863e-06, "epoch": 1.7993079584775087, "percentage": 35.99, "elapsed_time": "4:06:12", "remaining_time": "7:17:57"}
{"current_steps": 1570, "total_steps": 4335, "loss": 0.5203, "lr": 8.052717582183993e-06, "epoch": 1.8108419838523644, "percentage": 36.22, "elapsed_time": "4:07:46", "remaining_time": "7:16:21"}
{"current_steps": 1580, "total_steps": 4335, "loss": 0.5236, "lr": 8.020728559314128e-06, "epoch": 1.8223760092272203, "percentage": 36.45, "elapsed_time": "4:09:19", "remaining_time": "7:14:45"}
{"current_steps": 1590, "total_steps": 4335, "loss": 0.5185, "lr": 7.988543626176065e-06, "epoch": 1.8339100346020762, "percentage": 36.68, "elapsed_time": "4:10:52", "remaining_time": "7:13:06"}
{"current_steps": 1600, "total_steps": 4335, "loss": 0.5122, "lr": 7.956164870133414e-06, "epoch": 1.845444059976932, "percentage": 36.91, "elapsed_time": "4:12:25", "remaining_time": "7:11:29"}
{"current_steps": 1610, "total_steps": 4335, "loss": 0.5221, "lr": 7.923594391120237e-06, "epoch": 1.8569780853517877, "percentage": 37.14, "elapsed_time": "4:13:55", "remaining_time": "7:09:47"}
{"current_steps": 1620, "total_steps": 4335, "loss": 0.5217, "lr": 7.890834301504839e-06, "epoch": 1.8685121107266436, "percentage": 37.37, "elapsed_time": "4:15:27", "remaining_time": "7:08:07"}
{"current_steps": 1630, "total_steps": 4335, "loss": 0.5117, "lr": 7.857886725952784e-06, "epoch": 1.8800461361014995, "percentage": 37.6, "elapsed_time": "4:17:01", "remaining_time": "7:06:31"}
{"current_steps": 1640, "total_steps": 4335, "loss": 0.5203, "lr": 7.824753801289092e-06, "epoch": 1.8915801614763552, "percentage": 37.83, "elapsed_time": "4:18:32", "remaining_time": "7:04:52"}
{"current_steps": 1650, "total_steps": 4335, "loss": 0.5114, "lr": 7.791437676359655e-06, "epoch": 1.903114186851211, "percentage": 38.06, "elapsed_time": "4:20:02", "remaining_time": "7:03:09"}
{"current_steps": 1660, "total_steps": 4335, "loss": 0.5153, "lr": 7.757940511891875e-06, "epoch": 1.9146482122260668, "percentage": 38.29, "elapsed_time": "4:21:34", "remaining_time": "7:01:30"}
{"current_steps": 1670, "total_steps": 4335, "loss": 0.5185, "lr": 7.724264480354527e-06, "epoch": 1.9261822376009228, "percentage": 38.52, "elapsed_time": "4:23:01", "remaining_time": "6:59:44"}
{"current_steps": 1680, "total_steps": 4335, "loss": 0.5114, "lr": 7.690411765816864e-06, "epoch": 1.9377162629757785, "percentage": 38.75, "elapsed_time": "4:24:36", "remaining_time": "6:58:10"}
{"current_steps": 1690, "total_steps": 4335, "loss": 0.5189, "lr": 7.656384563806971e-06, "epoch": 1.9492502883506344, "percentage": 38.99, "elapsed_time": "4:26:11", "remaining_time": "6:56:36"}
{"current_steps": 1700, "total_steps": 4335, "loss": 0.5224, "lr": 7.6221850811693685e-06, "epoch": 1.9607843137254903, "percentage": 39.22, "elapsed_time": "4:27:44", "remaining_time": "6:55:00"}
{"current_steps": 1710, "total_steps": 4335, "loss": 0.5169, "lr": 7.587815535921892e-06, "epoch": 1.972318339100346, "percentage": 39.45, "elapsed_time": "4:29:18", "remaining_time": "6:53:23"}
{"current_steps": 1720, "total_steps": 4335, "loss": 0.5204, "lr": 7.553278157111834e-06, "epoch": 1.9838523644752017, "percentage": 39.68, "elapsed_time": "4:30:50", "remaining_time": "6:51:47"}
{"current_steps": 1730, "total_steps": 4335, "loss": 0.5191, "lr": 7.5185751846713914e-06, "epoch": 1.9953863898500577, "percentage": 39.91, "elapsed_time": "4:32:23", "remaining_time": "6:50:09"}
{"current_steps": 1740, "total_steps": 4335, "loss": 0.4617, "lr": 7.4837088692723794e-06, "epoch": 2.0069204152249136, "percentage": 40.14, "elapsed_time": "4:34:00", "remaining_time": "6:48:38"}
{"current_steps": 1750, "total_steps": 4335, "loss": 0.4139, "lr": 7.448681472180275e-06, "epoch": 2.0184544405997693, "percentage": 40.37, "elapsed_time": "4:35:36", "remaining_time": "6:47:06"}
{"current_steps": 1760, "total_steps": 4335, "loss": 0.4167, "lr": 7.413495265107553e-06, "epoch": 2.029988465974625, "percentage": 40.6, "elapsed_time": "4:37:09", "remaining_time": "6:45:30"}
{"current_steps": 1770, "total_steps": 4335, "loss": 0.4171, "lr": 7.378152530066363e-06, "epoch": 2.041522491349481, "percentage": 40.83, "elapsed_time": "4:38:43", "remaining_time": "6:43:55"}
{"current_steps": 1780, "total_steps": 4335, "loss": 0.4291, "lr": 7.3426555592205185e-06, "epoch": 2.053056516724337, "percentage": 41.06, "elapsed_time": "4:40:15", "remaining_time": "6:42:16"}
{"current_steps": 1790, "total_steps": 4335, "loss": 0.4158, "lr": 7.307006654736845e-06, "epoch": 2.0645905420991926, "percentage": 41.29, "elapsed_time": "4:41:48", "remaining_time": "6:40:40"}
{"current_steps": 1800, "total_steps": 4335, "loss": 0.4204, "lr": 7.271208128635874e-06, "epoch": 2.0761245674740483, "percentage": 41.52, "elapsed_time": "4:43:21", "remaining_time": "6:39:03"}
{"current_steps": 1810, "total_steps": 4335, "loss": 0.4136, "lr": 7.235262302641886e-06, "epoch": 2.0876585928489044, "percentage": 41.75, "elapsed_time": "4:44:55", "remaining_time": "6:37:28"}
{"current_steps": 1820, "total_steps": 4335, "loss": 0.4101, "lr": 7.199171508032343e-06, "epoch": 2.09919261822376, "percentage": 41.98, "elapsed_time": "4:46:29", "remaining_time": "6:35:53"}
{"current_steps": 1830, "total_steps": 4335, "loss": 0.4227, "lr": 7.162938085486693e-06, "epoch": 2.110726643598616, "percentage": 42.21, "elapsed_time": "4:48:01", "remaining_time": "6:34:16"}
{"current_steps": 1840, "total_steps": 4335, "loss": 0.4187, "lr": 7.126564384934559e-06, "epoch": 2.1222606689734715, "percentage": 42.45, "elapsed_time": "4:49:36", "remaining_time": "6:32:42"}
{"current_steps": 1850, "total_steps": 4335, "loss": 0.4195, "lr": 7.090052765403339e-06, "epoch": 2.1337946943483277, "percentage": 42.68, "elapsed_time": "4:51:11", "remaining_time": "6:31:08"}
{"current_steps": 1860, "total_steps": 4335, "loss": 0.4242, "lr": 7.053405594865209e-06, "epoch": 2.1453287197231834, "percentage": 42.91, "elapsed_time": "4:52:45", "remaining_time": "6:29:33"}
{"current_steps": 1870, "total_steps": 4335, "loss": 0.4197, "lr": 7.016625250083541e-06, "epoch": 2.156862745098039, "percentage": 43.14, "elapsed_time": "4:54:20", "remaining_time": "6:27:59"}
{"current_steps": 1880, "total_steps": 4335, "loss": 0.4266, "lr": 6.97971411645877e-06, "epoch": 2.168396770472895, "percentage": 43.37, "elapsed_time": "4:55:54", "remaining_time": "6:26:25"}
{"current_steps": 1890, "total_steps": 4335, "loss": 0.4188, "lr": 6.942674587873678e-06, "epoch": 2.179930795847751, "percentage": 43.6, "elapsed_time": "4:57:28", "remaining_time": "6:24:49"}
{"current_steps": 1900, "total_steps": 4335, "loss": 0.4213, "lr": 6.905509066538141e-06, "epoch": 2.1914648212226067, "percentage": 43.83, "elapsed_time": "4:59:02", "remaining_time": "6:23:15"}
{"current_steps": 1910, "total_steps": 4335, "loss": 0.4229, "lr": 6.868219962833334e-06, "epoch": 2.2029988465974624, "percentage": 44.06, "elapsed_time": "5:00:35", "remaining_time": "6:21:39"}
{"current_steps": 1920, "total_steps": 4335, "loss": 0.422, "lr": 6.830809695155402e-06, "epoch": 2.2145328719723185, "percentage": 44.29, "elapsed_time": "5:02:09", "remaining_time": "6:20:03"}
{"current_steps": 1930, "total_steps": 4335, "loss": 0.4165, "lr": 6.793280689758619e-06, "epoch": 2.2260668973471742, "percentage": 44.52, "elapsed_time": "5:03:42", "remaining_time": "6:18:27"}
{"current_steps": 1940, "total_steps": 4335, "loss": 0.4207, "lr": 6.755635380598029e-06, "epoch": 2.23760092272203, "percentage": 44.75, "elapsed_time": "5:05:17", "remaining_time": "6:16:53"}
{"current_steps": 1950, "total_steps": 4335, "loss": 0.4173, "lr": 6.717876209171591e-06, "epoch": 2.2491349480968856, "percentage": 44.98, "elapsed_time": "5:06:50", "remaining_time": "6:15:17"}
{"current_steps": 1960, "total_steps": 4335, "loss": 0.4265, "lr": 6.6800056243618386e-06, "epoch": 2.260668973471742, "percentage": 45.21, "elapsed_time": "5:08:24", "remaining_time": "6:13:42"}
{"current_steps": 1970, "total_steps": 4335, "loss": 0.4194, "lr": 6.642026082277048e-06, "epoch": 2.2722029988465975, "percentage": 45.44, "elapsed_time": "5:09:58", "remaining_time": "6:12:07"}
{"current_steps": 1980, "total_steps": 4335, "loss": 0.4201, "lr": 6.603940046091959e-06, "epoch": 2.283737024221453, "percentage": 45.67, "elapsed_time": "5:11:31", "remaining_time": "6:10:30"}
{"current_steps": 1990, "total_steps": 4335, "loss": 0.4139, "lr": 6.565749985888018e-06, "epoch": 2.295271049596309, "percentage": 45.91, "elapsed_time": "5:13:03", "remaining_time": "6:08:54"}
{"current_steps": 2000, "total_steps": 4335, "loss": 0.4184, "lr": 6.527458378493174e-06, "epoch": 2.306805074971165, "percentage": 46.14, "elapsed_time": "5:14:38", "remaining_time": "6:07:21"}
{"current_steps": 2010, "total_steps": 4335, "loss": 0.4198, "lr": 6.489067707321262e-06, "epoch": 2.3183391003460208, "percentage": 46.37, "elapsed_time": "5:18:06", "remaining_time": "6:07:57"}
{"current_steps": 2020, "total_steps": 4335, "loss": 0.4142, "lr": 6.450580462210914e-06, "epoch": 2.3298731257208765, "percentage": 46.6, "elapsed_time": "5:19:39", "remaining_time": "6:06:21"}
{"current_steps": 2030, "total_steps": 4335, "loss": 0.4205, "lr": 6.411999139264106e-06, "epoch": 2.3414071510957326, "percentage": 46.83, "elapsed_time": "5:21:10", "remaining_time": "6:04:41"}
{"current_steps": 2040, "total_steps": 4335, "loss": 0.421, "lr": 6.373326240684254e-06, "epoch": 2.3529411764705883, "percentage": 47.06, "elapsed_time": "5:22:42", "remaining_time": "6:03:02"}
{"current_steps": 2050, "total_steps": 4335, "loss": 0.4197, "lr": 6.3345642746139414e-06, "epoch": 2.364475201845444, "percentage": 47.29, "elapsed_time": "5:24:13", "remaining_time": "6:01:23"}
{"current_steps": 2060, "total_steps": 4335, "loss": 0.4181, "lr": 6.295715754972254e-06, "epoch": 2.3760092272202997, "percentage": 47.52, "elapsed_time": "5:25:47", "remaining_time": "5:59:48"}
{"current_steps": 2070, "total_steps": 4335, "loss": 0.4229, "lr": 6.256783201291727e-06, "epoch": 2.387543252595156, "percentage": 47.75, "elapsed_time": "5:27:18", "remaining_time": "5:58:08"}
{"current_steps": 2080, "total_steps": 4335, "loss": 0.423, "lr": 6.2177691385549595e-06, "epoch": 2.3990772779700116, "percentage": 47.98, "elapsed_time": "5:28:49", "remaining_time": "5:56:29"}
{"current_steps": 2090, "total_steps": 4335, "loss": 0.4201, "lr": 6.17867609703084e-06, "epoch": 2.4106113033448673, "percentage": 48.21, "elapsed_time": "5:30:20", "remaining_time": "5:54:50"}
{"current_steps": 2100, "total_steps": 4335, "loss": 0.4181, "lr": 6.1395066121104456e-06, "epoch": 2.422145328719723, "percentage": 48.44, "elapsed_time": "5:31:56", "remaining_time": "5:53:16"}
{"current_steps": 2110, "total_steps": 4335, "loss": 0.4221, "lr": 6.100263224142622e-06, "epoch": 2.433679354094579, "percentage": 48.67, "elapsed_time": "5:33:27", "remaining_time": "5:51:38"}
{"current_steps": 2120, "total_steps": 4335, "loss": 0.4256, "lr": 6.060948478269213e-06, "epoch": 2.445213379469435, "percentage": 48.9, "elapsed_time": "5:35:01", "remaining_time": "5:50:02"}
{"current_steps": 2130, "total_steps": 4335, "loss": 0.4159, "lr": 6.021564924260003e-06, "epoch": 2.4567474048442905, "percentage": 49.13, "elapsed_time": "5:36:36", "remaining_time": "5:48:27"}
{"current_steps": 2140, "total_steps": 4335, "loss": 0.4273, "lr": 5.982115116347351e-06, "epoch": 2.4682814302191467, "percentage": 49.37, "elapsed_time": "5:38:07", "remaining_time": "5:46:48"}
{"current_steps": 2150, "total_steps": 4335, "loss": 0.4268, "lr": 5.94260161306053e-06, "epoch": 2.4798154555940024, "percentage": 49.6, "elapsed_time": "5:39:38", "remaining_time": "5:45:09"}
{"current_steps": 2160, "total_steps": 4335, "loss": 0.4185, "lr": 5.9030269770598005e-06, "epoch": 2.491349480968858, "percentage": 49.83, "elapsed_time": "5:41:12", "remaining_time": "5:43:34"}
{"current_steps": 2170, "total_steps": 4335, "loss": 0.4245, "lr": 5.863393774970194e-06, "epoch": 2.502883506343714, "percentage": 50.06, "elapsed_time": "5:42:46", "remaining_time": "5:41:58"}
{"current_steps": 2180, "total_steps": 4335, "loss": 0.4251, "lr": 5.823704577215075e-06, "epoch": 2.5144175317185695, "percentage": 50.29, "elapsed_time": "5:44:17", "remaining_time": "5:40:21"}
{"current_steps": 2190, "total_steps": 4335, "loss": 0.4195, "lr": 5.7839619578494165e-06, "epoch": 2.5259515570934257, "percentage": 50.52, "elapsed_time": "5:45:51", "remaining_time": "5:38:45"}
{"current_steps": 2200, "total_steps": 4335, "loss": 0.4182, "lr": 5.7441684943928685e-06, "epoch": 2.5374855824682814, "percentage": 50.75, "elapsed_time": "5:47:24", "remaining_time": "5:37:08"}
{"current_steps": 2210, "total_steps": 4335, "loss": 0.4217, "lr": 5.704326767662592e-06, "epoch": 2.549019607843137, "percentage": 50.98, "elapsed_time": "5:48:55", "remaining_time": "5:35:30"}
{"current_steps": 2220, "total_steps": 4335, "loss": 0.4189, "lr": 5.664439361605872e-06, "epoch": 2.5605536332179932, "percentage": 51.21, "elapsed_time": "5:50:28", "remaining_time": "5:33:53"}
{"current_steps": 2230, "total_steps": 4335, "loss": 0.423, "lr": 5.624508863132546e-06, "epoch": 2.572087658592849, "percentage": 51.44, "elapsed_time": "5:52:00", "remaining_time": "5:32:16"}
{"current_steps": 2240, "total_steps": 4335, "loss": 0.419, "lr": 5.584537861947219e-06, "epoch": 2.5836216839677046, "percentage": 51.67, "elapsed_time": "5:53:32", "remaining_time": "5:30:39"}
{"current_steps": 2250, "total_steps": 4335, "loss": 0.4296, "lr": 5.544528950381314e-06, "epoch": 2.595155709342561, "percentage": 51.9, "elapsed_time": "5:55:06", "remaining_time": "5:29:03"}
{"current_steps": 2260, "total_steps": 4335, "loss": 0.4185, "lr": 5.5044847232249425e-06, "epoch": 2.6066897347174165, "percentage": 52.13, "elapsed_time": "5:56:39", "remaining_time": "5:27:27"}
{"current_steps": 2270, "total_steps": 4335, "loss": 0.4231, "lr": 5.464407777558618e-06, "epoch": 2.618223760092272, "percentage": 52.36, "elapsed_time": "5:58:12", "remaining_time": "5:25:51"}
{"current_steps": 2280, "total_steps": 4335, "loss": 0.418, "lr": 5.424300712584827e-06, "epoch": 2.629757785467128, "percentage": 52.6, "elapsed_time": "5:59:45", "remaining_time": "5:24:15"}
{"current_steps": 2290, "total_steps": 4335, "loss": 0.418, "lr": 5.384166129459447e-06, "epoch": 2.6412918108419836, "percentage": 52.83, "elapsed_time": "6:01:17", "remaining_time": "5:22:38"}
{"current_steps": 2300, "total_steps": 4335, "loss": 0.4237, "lr": 5.344006631123059e-06, "epoch": 2.6528258362168398, "percentage": 53.06, "elapsed_time": "6:02:49", "remaining_time": "5:21:01"}
{"current_steps": 2310, "total_steps": 4335, "loss": 0.4209, "lr": 5.303824822132124e-06, "epoch": 2.6643598615916955, "percentage": 53.29, "elapsed_time": "6:04:17", "remaining_time": "5:19:21"}
{"current_steps": 2320, "total_steps": 4335, "loss": 0.4252, "lr": 5.263623308490069e-06, "epoch": 2.675893886966551, "percentage": 53.52, "elapsed_time": "6:05:50", "remaining_time": "5:17:45"}
{"current_steps": 2330, "total_steps": 4335, "loss": 0.4232, "lr": 5.2234046974782715e-06, "epoch": 2.6874279123414073, "percentage": 53.75, "elapsed_time": "6:07:24", "remaining_time": "5:16:09"}
{"current_steps": 2340, "total_steps": 4335, "loss": 0.4221, "lr": 5.183171597486964e-06, "epoch": 2.698961937716263, "percentage": 53.98, "elapsed_time": "6:08:54", "remaining_time": "5:14:31"}
{"current_steps": 2350, "total_steps": 4335, "loss": 0.4234, "lr": 5.142926617846068e-06, "epoch": 2.7104959630911187, "percentage": 54.21, "elapsed_time": "6:10:25", "remaining_time": "5:12:53"}
{"current_steps": 2360, "total_steps": 4335, "loss": 0.4198, "lr": 5.10267236865596e-06, "epoch": 2.722029988465975, "percentage": 54.44, "elapsed_time": "6:11:57", "remaining_time": "5:11:16"}
{"current_steps": 2370, "total_steps": 4335, "loss": 0.4203, "lr": 5.062411460618197e-06, "epoch": 2.7335640138408306, "percentage": 54.67, "elapsed_time": "6:13:28", "remaining_time": "5:09:38"}
{"current_steps": 2380, "total_steps": 4335, "loss": 0.4202, "lr": 5.022146504866201e-06, "epoch": 2.7450980392156863, "percentage": 54.9, "elapsed_time": "6:15:00", "remaining_time": "5:08:02"}
{"current_steps": 2390, "total_steps": 4335, "loss": 0.4247, "lr": 4.981880112795903e-06, "epoch": 2.756632064590542, "percentage": 55.13, "elapsed_time": "6:16:30", "remaining_time": "5:06:24"}
{"current_steps": 2400, "total_steps": 4335, "loss": 0.424, "lr": 4.941614895896397e-06, "epoch": 2.7681660899653977, "percentage": 55.36, "elapsed_time": "6:18:03", "remaining_time": "5:04:48"}
{"current_steps": 2410, "total_steps": 4335, "loss": 0.423, "lr": 4.901353465580548e-06, "epoch": 2.779700115340254, "percentage": 55.59, "elapsed_time": "6:19:37", "remaining_time": "5:03:13"}
{"current_steps": 2420, "total_steps": 4335, "loss": 0.4164, "lr": 4.861098433015651e-06, "epoch": 2.7912341407151096, "percentage": 55.82, "elapsed_time": "6:21:11", "remaining_time": "5:01:38"}
{"current_steps": 2430, "total_steps": 4335, "loss": 0.4176, "lr": 4.82085240895407e-06, "epoch": 2.8027681660899653, "percentage": 56.06, "elapsed_time": "6:22:45", "remaining_time": "5:00:03"}
{"current_steps": 2440, "total_steps": 4335, "loss": 0.418, "lr": 4.78061800356392e-06, "epoch": 2.8143021914648214, "percentage": 56.29, "elapsed_time": "6:24:20", "remaining_time": "4:58:29"}
{"current_steps": 2450, "total_steps": 4335, "loss": 0.4244, "lr": 4.74039782625978e-06, "epoch": 2.825836216839677, "percentage": 56.52, "elapsed_time": "6:25:53", "remaining_time": "4:56:54"}
{"current_steps": 2460, "total_steps": 4335, "loss": 0.4175, "lr": 4.700194485533466e-06, "epoch": 2.837370242214533, "percentage": 56.75, "elapsed_time": "6:27:26", "remaining_time": "4:55:18"}
{"current_steps": 2470, "total_steps": 4335, "loss": 0.4192, "lr": 4.660010588784854e-06, "epoch": 2.848904267589389, "percentage": 56.98, "elapsed_time": "6:28:58", "remaining_time": "4:53:42"}
{"current_steps": 2480, "total_steps": 4335, "loss": 0.4147, "lr": 4.619848742152771e-06, "epoch": 2.8604382929642447, "percentage": 57.21, "elapsed_time": "6:30:29", "remaining_time": "4:52:05"}
{"current_steps": 2490, "total_steps": 4335, "loss": 0.4161, "lr": 4.57971155034598e-06, "epoch": 2.8719723183391004, "percentage": 57.44, "elapsed_time": "6:32:00", "remaining_time": "4:50:27"}
{"current_steps": 2500, "total_steps": 4335, "loss": 0.4203, "lr": 4.539601616474245e-06, "epoch": 2.883506343713956, "percentage": 57.67, "elapsed_time": "6:33:33", "remaining_time": "4:48:52"}
{"current_steps": 2510, "total_steps": 4335, "loss": 0.4194, "lr": 4.499521541879508e-06, "epoch": 2.895040369088812, "percentage": 57.9, "elapsed_time": "6:37:01", "remaining_time": "4:48:40"}
{"current_steps": 2520, "total_steps": 4335, "loss": 0.4237, "lr": 4.459473925967186e-06, "epoch": 2.906574394463668, "percentage": 58.13, "elapsed_time": "6:38:36", "remaining_time": "4:47:05"}
{"current_steps": 2530, "total_steps": 4335, "loss": 0.4151, "lr": 4.419461366037567e-06, "epoch": 2.9181084198385236, "percentage": 58.36, "elapsed_time": "6:40:09", "remaining_time": "4:45:29"}
{"current_steps": 2540, "total_steps": 4335, "loss": 0.4129, "lr": 4.379486457117383e-06, "epoch": 2.9296424452133794, "percentage": 58.59, "elapsed_time": "6:41:40", "remaining_time": "4:43:51"}
{"current_steps": 2550, "total_steps": 4335, "loss": 0.4192, "lr": 4.33955179179149e-06, "epoch": 2.9411764705882355, "percentage": 58.82, "elapsed_time": "6:43:12", "remaining_time": "4:42:14"}
{"current_steps": 2560, "total_steps": 4335, "loss": 0.4246, "lr": 4.299659960034737e-06, "epoch": 2.952710495963091, "percentage": 59.05, "elapsed_time": "6:44:45", "remaining_time": "4:40:38"}
{"current_steps": 2570, "total_steps": 4335, "loss": 0.4076, "lr": 4.259813549043991e-06, "epoch": 2.964244521337947, "percentage": 59.28, "elapsed_time": "6:46:18", "remaining_time": "4:39:02"}
{"current_steps": 2580, "total_steps": 4335, "loss": 0.422, "lr": 4.220015143070338e-06, "epoch": 2.9757785467128026, "percentage": 59.52, "elapsed_time": "6:47:53", "remaining_time": "4:37:27"}
{"current_steps": 2590, "total_steps": 4335, "loss": 0.4171, "lr": 4.180267323251488e-06, "epoch": 2.9873125720876583, "percentage": 59.75, "elapsed_time": "6:49:27", "remaining_time": "4:35:52"}
{"current_steps": 2600, "total_steps": 4335, "loss": 0.4178, "lr": 4.140572667444365e-06, "epoch": 2.9988465974625145, "percentage": 59.98, "elapsed_time": "6:51:00", "remaining_time": "4:34:15"}
{"current_steps": 2610, "total_steps": 4335, "loss": 0.3198, "lr": 4.1009337500579275e-06, "epoch": 3.01038062283737, "percentage": 60.21, "elapsed_time": "6:52:40", "remaining_time": "4:32:45"}
{"current_steps": 2620, "total_steps": 4335, "loss": 0.2973, "lr": 4.061353141886204e-06, "epoch": 3.021914648212226, "percentage": 60.44, "elapsed_time": "6:54:15", "remaining_time": "4:31:09"}
{"current_steps": 2630, "total_steps": 4335, "loss": 0.2995, "lr": 4.021833409941558e-06, "epoch": 3.033448673587082, "percentage": 60.67, "elapsed_time": "6:55:48", "remaining_time": "4:29:34"}
{"current_steps": 2640, "total_steps": 4335, "loss": 0.2931, "lr": 3.982377117288211e-06, "epoch": 3.0449826989619377, "percentage": 60.9, "elapsed_time": "6:57:23", "remaining_time": "4:27:58"}
{"current_steps": 2650, "total_steps": 4335, "loss": 0.2959, "lr": 3.942986822876003e-06, "epoch": 3.0565167243367934, "percentage": 61.13, "elapsed_time": "6:58:57", "remaining_time": "4:26:23"}
{"current_steps": 2660, "total_steps": 4335, "loss": 0.2894, "lr": 3.903665081374444e-06, "epoch": 3.0680507497116496, "percentage": 61.36, "elapsed_time": "7:00:31", "remaining_time": "4:24:48"}
{"current_steps": 2670, "total_steps": 4335, "loss": 0.2929, "lr": 3.864414443007022e-06, "epoch": 3.0795847750865053, "percentage": 61.59, "elapsed_time": "7:02:06", "remaining_time": "4:23:13"}
{"current_steps": 2680, "total_steps": 4335, "loss": 0.2961, "lr": 3.8252374533858096e-06, "epoch": 3.091118800461361, "percentage": 61.82, "elapsed_time": "7:03:39", "remaining_time": "4:21:37"}
{"current_steps": 2690, "total_steps": 4335, "loss": 0.293, "lr": 3.7861366533463708e-06, "epoch": 3.1026528258362167, "percentage": 62.05, "elapsed_time": "7:05:14", "remaining_time": "4:20:02"}
{"current_steps": 2700, "total_steps": 4335, "loss": 0.3025, "lr": 3.7471145787829645e-06, "epoch": 3.114186851211073, "percentage": 62.28, "elapsed_time": "7:06:48", "remaining_time": "4:18:27"}
{"current_steps": 2710, "total_steps": 4335, "loss": 0.293, "lr": 3.7081737604840895e-06, "epoch": 3.1257208765859286, "percentage": 62.51, "elapsed_time": "7:08:22", "remaining_time": "4:16:52"}
{"current_steps": 2720, "total_steps": 4335, "loss": 0.284, "lr": 3.669316723968344e-06, "epoch": 3.1372549019607843, "percentage": 62.75, "elapsed_time": "7:09:57", "remaining_time": "4:15:17"}
{"current_steps": 2730, "total_steps": 4335, "loss": 0.2978, "lr": 3.630545989320635e-06, "epoch": 3.14878892733564, "percentage": 62.98, "elapsed_time": "7:11:31", "remaining_time": "4:13:41"}
{"current_steps": 2740, "total_steps": 4335, "loss": 0.2986, "lr": 3.5918640710287336e-06, "epoch": 3.160322952710496, "percentage": 63.21, "elapsed_time": "7:13:02", "remaining_time": "4:12:05"}
{"current_steps": 2750, "total_steps": 4335, "loss": 0.2983, "lr": 3.553273477820198e-06, "epoch": 3.171856978085352, "percentage": 63.44, "elapsed_time": "7:14:37", "remaining_time": "4:10:29"}
{"current_steps": 2760, "total_steps": 4335, "loss": 0.2933, "lr": 3.5147767124996724e-06, "epoch": 3.1833910034602075, "percentage": 63.67, "elapsed_time": "7:16:11", "remaining_time": "4:08:54"}
{"current_steps": 2770, "total_steps": 4335, "loss": 0.2919, "lr": 3.4763762717865623e-06, "epoch": 3.1949250288350632, "percentage": 63.9, "elapsed_time": "7:17:43", "remaining_time": "4:07:18"}
{"current_steps": 2780, "total_steps": 4335, "loss": 0.2823, "lr": 3.4380746461531176e-06, "epoch": 3.2064590542099194, "percentage": 64.13, "elapsed_time": "7:19:19", "remaining_time": "4:05:44"}
{"current_steps": 2790, "total_steps": 4335, "loss": 0.2973, "lr": 3.3998743196629015e-06, "epoch": 3.217993079584775, "percentage": 64.36, "elapsed_time": "7:20:53", "remaining_time": "4:04:09"}
{"current_steps": 2800, "total_steps": 4335, "loss": 0.2915, "lr": 3.361777769809688e-06, "epoch": 3.229527104959631, "percentage": 64.59, "elapsed_time": "7:22:28", "remaining_time": "4:02:34"}
{"current_steps": 2810, "total_steps": 4335, "loss": 0.2954, "lr": 3.3237874673567917e-06, "epoch": 3.2410611303344865, "percentage": 64.82, "elapsed_time": "7:24:03", "remaining_time": "4:00:59"}
{"current_steps": 2820, "total_steps": 4335, "loss": 0.2923, "lr": 3.2859058761768138e-06, "epoch": 3.2525951557093427, "percentage": 65.05, "elapsed_time": "7:25:37", "remaining_time": "3:59:24"}
{"current_steps": 2830, "total_steps": 4335, "loss": 0.2915, "lr": 3.2481354530918595e-06, "epoch": 3.2641291810841984, "percentage": 65.28, "elapsed_time": "7:27:13", "remaining_time": "3:57:50"}
{"current_steps": 2840, "total_steps": 4335, "loss": 0.2918, "lr": 3.210478647714189e-06, "epoch": 3.275663206459054, "percentage": 65.51, "elapsed_time": "7:28:48", "remaining_time": "3:56:15"}
{"current_steps": 2850, "total_steps": 4335, "loss": 0.291, "lr": 3.172937902287352e-06, "epoch": 3.28719723183391, "percentage": 65.74, "elapsed_time": "7:30:22", "remaining_time": "3:54:40"}
{"current_steps": 2860, "total_steps": 4335, "loss": 0.2941, "lr": 3.1355156515277956e-06, "epoch": 3.298731257208766, "percentage": 65.97, "elapsed_time": "7:31:55", "remaining_time": "3:53:04"}
{"current_steps": 2870, "total_steps": 4335, "loss": 0.285, "lr": 3.098214322466958e-06, "epoch": 3.3102652825836216, "percentage": 66.21, "elapsed_time": "7:33:30", "remaining_time": "3:51:29"}
{"current_steps": 2880, "total_steps": 4335, "loss": 0.2906, "lr": 3.0610363342938665e-06, "epoch": 3.3217993079584773, "percentage": 66.44, "elapsed_time": "7:35:06", "remaining_time": "3:49:55"}
{"current_steps": 2890, "total_steps": 4335, "loss": 0.2935, "lr": 3.023984098198237e-06, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "7:36:40", "remaining_time": "3:48:20"}
{"current_steps": 2900, "total_steps": 4335, "loss": 0.2945, "lr": 2.987060017214094e-06, "epoch": 3.344867358708189, "percentage": 66.9, "elapsed_time": "7:38:11", "remaining_time": "3:46:43"}
{"current_steps": 2910, "total_steps": 4335, "loss": 0.2938, "lr": 2.9502664860639236e-06, "epoch": 3.356401384083045, "percentage": 67.13, "elapsed_time": "7:39:45", "remaining_time": "3:45:08"}
{"current_steps": 2920, "total_steps": 4335, "loss": 0.2947, "lr": 2.913605891003365e-06, "epoch": 3.3679354094579006, "percentage": 67.36, "elapsed_time": "7:41:20", "remaining_time": "3:43:33"}
{"current_steps": 2930, "total_steps": 4335, "loss": 0.296, "lr": 2.877080609666446e-06, "epoch": 3.3794694348327567, "percentage": 67.59, "elapsed_time": "7:42:53", "remaining_time": "3:41:57"}
{"current_steps": 2940, "total_steps": 4335, "loss": 0.2919, "lr": 2.8406930109113812e-06, "epoch": 3.3910034602076125, "percentage": 67.82, "elapsed_time": "7:44:25", "remaining_time": "3:40:21"}
{"current_steps": 2950, "total_steps": 4335, "loss": 0.2946, "lr": 2.80444545466694e-06, "epoch": 3.402537485582468, "percentage": 68.05, "elapsed_time": "7:45:59", "remaining_time": "3:38:46"}
{"current_steps": 2960, "total_steps": 4335, "loss": 0.2903, "lr": 2.7683402917793923e-06, "epoch": 3.4140715109573243, "percentage": 68.28, "elapsed_time": "7:47:33", "remaining_time": "3:37:11"}
{"current_steps": 2970, "total_steps": 4335, "loss": 0.2879, "lr": 2.7323798638600423e-06, "epoch": 3.42560553633218, "percentage": 68.51, "elapsed_time": "7:49:08", "remaining_time": "3:35:36"}
{"current_steps": 2980, "total_steps": 4335, "loss": 0.2965, "lr": 2.6965665031333665e-06, "epoch": 3.4371395617070357, "percentage": 68.74, "elapsed_time": "7:50:42", "remaining_time": "3:34:01"}
{"current_steps": 2990, "total_steps": 4335, "loss": 0.2973, "lr": 2.660902532285751e-06, "epoch": 3.4486735870818914, "percentage": 68.97, "elapsed_time": "7:52:17", "remaining_time": "3:32:26"}
{"current_steps": 3000, "total_steps": 4335, "loss": 0.2883, "lr": 2.625390264314859e-06, "epoch": 3.4602076124567476, "percentage": 69.2, "elapsed_time": "7:53:51", "remaining_time": "3:30:52"}
{"current_steps": 3010, "total_steps": 4335, "loss": 0.2916, "lr": 2.590032002379614e-06, "epoch": 3.4717416378316033, "percentage": 69.43, "elapsed_time": "7:57:18", "remaining_time": "3:30:06"}
{"current_steps": 3020, "total_steps": 4335, "loss": 0.2933, "lr": 2.554830039650834e-06, "epoch": 3.483275663206459, "percentage": 69.67, "elapsed_time": "7:58:49", "remaining_time": "3:28:29"}
{"current_steps": 3030, "total_steps": 4335, "loss": 0.2968, "lr": 2.519786659162504e-06, "epoch": 3.4948096885813147, "percentage": 69.9, "elapsed_time": "8:00:19", "remaining_time": "3:26:52"}
{"current_steps": 3040, "total_steps": 4335, "loss": 0.299, "lr": 2.48490413366371e-06, "epoch": 3.506343713956171, "percentage": 70.13, "elapsed_time": "8:01:49", "remaining_time": "3:25:15"}
{"current_steps": 3050, "total_steps": 4335, "loss": 0.2907, "lr": 2.4501847254712364e-06, "epoch": 3.5178777393310265, "percentage": 70.36, "elapsed_time": "8:03:20", "remaining_time": "3:23:38"}
{"current_steps": 3060, "total_steps": 4335, "loss": 0.2852, "lr": 2.4156306863228474e-06, "epoch": 3.5294117647058822, "percentage": 70.59, "elapsed_time": "8:04:56", "remaining_time": "3:22:03"}
{"current_steps": 3070, "total_steps": 4335, "loss": 0.2863, "lr": 2.3812442572312473e-06, "epoch": 3.5409457900807384, "percentage": 70.82, "elapsed_time": "8:06:25", "remaining_time": "3:20:26"}
{"current_steps": 3080, "total_steps": 4335, "loss": 0.2892, "lr": 2.347027668338739e-06, "epoch": 3.552479815455594, "percentage": 71.05, "elapsed_time": "8:08:00", "remaining_time": "3:18:50"}
{"current_steps": 3090, "total_steps": 4335, "loss": 0.2909, "lr": 2.3129831387725882e-06, "epoch": 3.56401384083045, "percentage": 71.28, "elapsed_time": "8:09:32", "remaining_time": "3:17:14"}
{"current_steps": 3100, "total_steps": 4335, "loss": 0.2936, "lr": 2.2791128765010996e-06, "epoch": 3.5755478662053055, "percentage": 71.51, "elapsed_time": "8:11:05", "remaining_time": "3:15:38"}
{"current_steps": 3110, "total_steps": 4335, "loss": 0.2925, "lr": 2.24541907819042e-06, "epoch": 3.587081891580161, "percentage": 71.74, "elapsed_time": "8:12:38", "remaining_time": "3:14:02"}
{"current_steps": 3120, "total_steps": 4335, "loss": 0.297, "lr": 2.2119039290620732e-06, "epoch": 3.5986159169550174, "percentage": 71.97, "elapsed_time": "8:14:08", "remaining_time": "3:12:25"}
{"current_steps": 3130, "total_steps": 4335, "loss": 0.2902, "lr": 2.1785696027512355e-06, "epoch": 3.610149942329873, "percentage": 72.2, "elapsed_time": "8:15:41", "remaining_time": "3:10:49"}
{"current_steps": 3140, "total_steps": 4335, "loss": 0.2917, "lr": 2.145418261165764e-06, "epoch": 3.621683967704729, "percentage": 72.43, "elapsed_time": "8:17:14", "remaining_time": "3:09:14"}
{"current_steps": 3150, "total_steps": 4335, "loss": 0.2935, "lr": 2.1124520543459863e-06, "epoch": 3.633217993079585, "percentage": 72.66, "elapsed_time": "8:18:48", "remaining_time": "3:07:38"}
{"current_steps": 3160, "total_steps": 4335, "loss": 0.2868, "lr": 2.079673120325259e-06, "epoch": 3.6447520184544406, "percentage": 72.9, "elapsed_time": "8:20:21", "remaining_time": "3:06:03"}
{"current_steps": 3170, "total_steps": 4335, "loss": 0.2949, "lr": 2.047083584991304e-06, "epoch": 3.6562860438292963, "percentage": 73.13, "elapsed_time": "8:21:56", "remaining_time": "3:04:28"}
{"current_steps": 3180, "total_steps": 4335, "loss": 0.2928, "lr": 2.014685561948333e-06, "epoch": 3.6678200692041525, "percentage": 73.36, "elapsed_time": "8:23:30", "remaining_time": "3:02:52"}
{"current_steps": 3190, "total_steps": 4335, "loss": 0.2945, "lr": 1.9824811523799712e-06, "epoch": 3.679354094579008, "percentage": 73.59, "elapsed_time": "8:25:02", "remaining_time": "3:01:16"}
{"current_steps": 3200, "total_steps": 4335, "loss": 0.2901, "lr": 1.950472444912983e-06, "epoch": 3.690888119953864, "percentage": 73.82, "elapsed_time": "8:26:36", "remaining_time": "2:59:41"}
{"current_steps": 3210, "total_steps": 4335, "loss": 0.2834, "lr": 1.918661515481813e-06, "epoch": 3.7024221453287196, "percentage": 74.05, "elapsed_time": "8:28:10", "remaining_time": "2:58:05"}
{"current_steps": 3220, "total_steps": 4335, "loss": 0.2886, "lr": 1.8870504271939504e-06, "epoch": 3.7139561707035753, "percentage": 74.28, "elapsed_time": "8:29:41", "remaining_time": "2:56:29"}
{"current_steps": 3230, "total_steps": 4335, "loss": 0.2925, "lr": 1.8556412301961285e-06, "epoch": 3.7254901960784315, "percentage": 74.51, "elapsed_time": "8:31:11", "remaining_time": "2:54:52"}
{"current_steps": 3240, "total_steps": 4335, "loss": 0.2936, "lr": 1.8244359615413582e-06, "epoch": 3.737024221453287, "percentage": 74.74, "elapsed_time": "8:32:46", "remaining_time": "2:53:17"}
{"current_steps": 3250, "total_steps": 4335, "loss": 0.2848, "lr": 1.793436645056816e-06, "epoch": 3.748558246828143, "percentage": 74.97, "elapsed_time": "8:34:19", "remaining_time": "2:51:42"}
{"current_steps": 3260, "total_steps": 4335, "loss": 0.2876, "lr": 1.762645291212588e-06, "epoch": 3.760092272202999, "percentage": 75.2, "elapsed_time": "8:35:51", "remaining_time": "2:50:06"}
{"current_steps": 3270, "total_steps": 4335, "loss": 0.2887, "lr": 1.7320638969912795e-06, "epoch": 3.7716262975778547, "percentage": 75.43, "elapsed_time": "8:37:21", "remaining_time": "2:48:30"}
{"current_steps": 3280, "total_steps": 4335, "loss": 0.2954, "lr": 1.7016944457585021e-06, "epoch": 3.7831603229527104, "percentage": 75.66, "elapsed_time": "8:38:53", "remaining_time": "2:46:53"}
{"current_steps": 3290, "total_steps": 4335, "loss": 0.2859, "lr": 1.6715389071342393e-06, "epoch": 3.7946943483275666, "percentage": 75.89, "elapsed_time": "8:40:25", "remaining_time": "2:45:18"}
{"current_steps": 3300, "total_steps": 4335, "loss": 0.297, "lr": 1.6415992368651068e-06, "epoch": 3.8062283737024223, "percentage": 76.12, "elapsed_time": "8:41:59", "remaining_time": "2:43:42"}
{"current_steps": 3310, "total_steps": 4335, "loss": 0.2907, "lr": 1.611877376697515e-06, "epoch": 3.817762399077278, "percentage": 76.36, "elapsed_time": "8:43:31", "remaining_time": "2:42:07"}
{"current_steps": 3320, "total_steps": 4335, "loss": 0.2889, "lr": 1.5823752542517313e-06, "epoch": 3.8292964244521337, "percentage": 76.59, "elapsed_time": "8:45:03", "remaining_time": "2:40:31"}
{"current_steps": 3330, "total_steps": 4335, "loss": 0.2907, "lr": 1.5530947828968685e-06, "epoch": 3.8408304498269894, "percentage": 76.82, "elapsed_time": "8:46:34", "remaining_time": "2:38:55"}
{"current_steps": 3340, "total_steps": 4335, "loss": 0.2969, "lr": 1.5240378616267887e-06, "epoch": 3.8523644752018456, "percentage": 77.05, "elapsed_time": "8:48:06", "remaining_time": "2:37:19"}
{"current_steps": 3350, "total_steps": 4335, "loss": 0.2876, "lr": 1.4952063749369471e-06, "epoch": 3.8638985005767013, "percentage": 77.28, "elapsed_time": "8:49:40", "remaining_time": "2:35:44"}
{"current_steps": 3360, "total_steps": 4335, "loss": 0.2916, "lr": 1.4666021927021695e-06, "epoch": 3.875432525951557, "percentage": 77.51, "elapsed_time": "8:51:14", "remaining_time": "2:34:09"}
{"current_steps": 3370, "total_steps": 4335, "loss": 0.2867, "lr": 1.4382271700553834e-06, "epoch": 3.886966551326413, "percentage": 77.74, "elapsed_time": "8:52:48", "remaining_time": "2:32:34"}
{"current_steps": 3380, "total_steps": 4335, "loss": 0.29, "lr": 1.4100831472673e-06, "epoch": 3.898500576701269, "percentage": 77.97, "elapsed_time": "8:54:19", "remaining_time": "2:30:58"}
{"current_steps": 3390, "total_steps": 4335, "loss": 0.286, "lr": 1.3821719496270675e-06, "epoch": 3.9100346020761245, "percentage": 78.2, "elapsed_time": "8:55:51", "remaining_time": "2:29:22"}
{"current_steps": 3400, "total_steps": 4335, "loss": 0.2876, "lr": 1.3544953873238815e-06, "epoch": 3.9215686274509802, "percentage": 78.43, "elapsed_time": "8:57:22", "remaining_time": "2:27:46"}
{"current_steps": 3410, "total_steps": 4335, "loss": 0.2905, "lr": 1.3270552553296006e-06, "epoch": 3.9331026528258364, "percentage": 78.66, "elapsed_time": "8:58:52", "remaining_time": "2:26:10"}
{"current_steps": 3420, "total_steps": 4335, "loss": 0.2924, "lr": 1.2998533332823193e-06, "epoch": 3.944636678200692, "percentage": 78.89, "elapsed_time": "9:00:26", "remaining_time": "2:24:35"}
{"current_steps": 3430, "total_steps": 4335, "loss": 0.2898, "lr": 1.272891385370953e-06, "epoch": 3.956170703575548, "percentage": 79.12, "elapsed_time": "9:01:59", "remaining_time": "2:23:00"}
{"current_steps": 3440, "total_steps": 4335, "loss": 0.2782, "lr": 1.2461711602208243e-06, "epoch": 3.9677047289504035, "percentage": 79.35, "elapsed_time": "9:03:31", "remaining_time": "2:21:24"}
{"current_steps": 3450, "total_steps": 4335, "loss": 0.2795, "lr": 1.2196943907802467e-06, "epoch": 3.9792387543252596, "percentage": 79.58, "elapsed_time": "9:05:04", "remaining_time": "2:19:49"}
{"current_steps": 3460, "total_steps": 4335, "loss": 0.2885, "lr": 1.1934627942081484e-06, "epoch": 3.9907727797001153, "percentage": 79.82, "elapsed_time": "9:06:37", "remaining_time": "2:18:14"}
{"current_steps": 3470, "total_steps": 4335, "loss": 0.2777, "lr": 1.1674780717626916e-06, "epoch": 4.002306805074971, "percentage": 80.05, "elapsed_time": "9:08:12", "remaining_time": "2:16:39"}
{"current_steps": 3480, "total_steps": 4335, "loss": 0.2053, "lr": 1.1417419086909432e-06, "epoch": 4.013840830449827, "percentage": 80.28, "elapsed_time": "9:09:47", "remaining_time": "2:15:04"}
{"current_steps": 3490, "total_steps": 4335, "loss": 0.2011, "lr": 1.1162559741195733e-06, "epoch": 4.0253748558246825, "percentage": 80.51, "elapsed_time": "9:11:21", "remaining_time": "2:13:29"}
{"current_steps": 3500, "total_steps": 4335, "loss": 0.2025, "lr": 1.0910219209466105e-06, "epoch": 4.036908881199539, "percentage": 80.74, "elapsed_time": "9:12:55", "remaining_time": "2:11:54"}
{"current_steps": 3510, "total_steps": 4335, "loss": 0.2022, "lr": 1.0660413857342394e-06, "epoch": 4.048442906574395, "percentage": 80.97, "elapsed_time": "9:16:22", "remaining_time": "2:10:46"}
{"current_steps": 3520, "total_steps": 4335, "loss": 0.2038, "lr": 1.041315988602658e-06, "epoch": 4.05997693194925, "percentage": 81.2, "elapsed_time": "9:17:56", "remaining_time": "2:09:11"}
{"current_steps": 3530, "total_steps": 4335, "loss": 0.203, "lr": 1.0168473331250073e-06, "epoch": 4.071510957324106, "percentage": 81.43, "elapsed_time": "9:19:29", "remaining_time": "2:07:35"}
{"current_steps": 3540, "total_steps": 4335, "loss": 0.2018, "lr": 9.926370062233687e-07, "epoch": 4.083044982698962, "percentage": 81.66, "elapsed_time": "9:21:02", "remaining_time": "2:05:59"}
{"current_steps": 3550, "total_steps": 4335, "loss": 0.1957, "lr": 9.686865780658462e-07, "epoch": 4.094579008073818, "percentage": 81.89, "elapsed_time": "9:22:35", "remaining_time": "2:04:24"}
{"current_steps": 3560, "total_steps": 4335, "loss": 0.1988, "lr": 9.449976019647345e-07, "epoch": 4.106113033448674, "percentage": 82.12, "elapsed_time": "9:24:09", "remaining_time": "2:02:48"}
{"current_steps": 3570, "total_steps": 4335, "loss": 0.1968, "lr": 9.215716142757735e-07, "epoch": 4.117647058823529, "percentage": 82.35, "elapsed_time": "9:25:42", "remaining_time": "2:01:13"}
{"current_steps": 3580, "total_steps": 4335, "loss": 0.2019, "lr": 8.984101342985108e-07, "epoch": 4.129181084198385, "percentage": 82.58, "elapsed_time": "9:27:15", "remaining_time": "1:59:37"}
{"current_steps": 3590, "total_steps": 4335, "loss": 0.2029, "lr": 8.755146641777623e-07, "epoch": 4.140715109573241, "percentage": 82.81, "elapsed_time": "9:28:47", "remaining_time": "1:58:02"}
{"current_steps": 3600, "total_steps": 4335, "loss": 0.2043, "lr": 8.528866888061971e-07, "epoch": 4.1522491349480966, "percentage": 83.04, "elapsed_time": "9:30:21", "remaining_time": "1:56:26"}
{"current_steps": 3610, "total_steps": 4335, "loss": 0.2015, "lr": 8.305276757280328e-07, "epoch": 4.163783160322953, "percentage": 83.28, "elapsed_time": "9:31:55", "remaining_time": "1:54:51"}
{"current_steps": 3620, "total_steps": 4335, "loss": 0.2008, "lr": 8.084390750438532e-07, "epoch": 4.175317185697809, "percentage": 83.51, "elapsed_time": "9:33:27", "remaining_time": "1:53:16"}
{"current_steps": 3630, "total_steps": 4335, "loss": 0.2015, "lr": 7.866223193165646e-07, "epoch": 4.186851211072664, "percentage": 83.74, "elapsed_time": "9:34:58", "remaining_time": "1:51:40"}
{"current_steps": 3640, "total_steps": 4335, "loss": 0.2003, "lr": 7.65078823478485e-07, "epoch": 4.19838523644752, "percentage": 83.97, "elapsed_time": "9:36:33", "remaining_time": "1:50:04"}
{"current_steps": 3650, "total_steps": 4335, "loss": 0.2035, "lr": 7.438099847395813e-07, "epoch": 4.209919261822376, "percentage": 84.2, "elapsed_time": "9:38:06", "remaining_time": "1:48:29"}
{"current_steps": 3660, "total_steps": 4335, "loss": 0.204, "lr": 7.228171824968478e-07, "epoch": 4.221453287197232, "percentage": 84.43, "elapsed_time": "9:39:38", "remaining_time": "1:46:54"}
{"current_steps": 3670, "total_steps": 4335, "loss": 0.2033, "lr": 7.021017782448536e-07, "epoch": 4.232987312572088, "percentage": 84.66, "elapsed_time": "9:41:11", "remaining_time": "1:45:18"}
{"current_steps": 3680, "total_steps": 4335, "loss": 0.2008, "lr": 6.816651154874327e-07, "epoch": 4.244521337946943, "percentage": 84.89, "elapsed_time": "9:42:44", "remaining_time": "1:43:43"}
{"current_steps": 3690, "total_steps": 4335, "loss": 0.2022, "lr": 6.615085196505533e-07, "epoch": 4.256055363321799, "percentage": 85.12, "elapsed_time": "9:44:16", "remaining_time": "1:42:07"}
{"current_steps": 3700, "total_steps": 4335, "loss": 0.2023, "lr": 6.416332979963614e-07, "epoch": 4.267589388696655, "percentage": 85.35, "elapsed_time": "9:45:50", "remaining_time": "1:40:32"}
{"current_steps": 3710, "total_steps": 4335, "loss": 0.2019, "lr": 6.220407395383937e-07, "epoch": 4.279123414071511, "percentage": 85.58, "elapsed_time": "9:47:24", "remaining_time": "1:38:57"}
{"current_steps": 3720, "total_steps": 4335, "loss": 0.1952, "lr": 6.027321149579812e-07, "epoch": 4.290657439446367, "percentage": 85.81, "elapsed_time": "9:48:59", "remaining_time": "1:37:22"}
{"current_steps": 3730, "total_steps": 4335, "loss": 0.2005, "lr": 5.837086765218364e-07, "epoch": 4.302191464821223, "percentage": 86.04, "elapsed_time": "9:50:34", "remaining_time": "1:35:47"}
{"current_steps": 3740, "total_steps": 4335, "loss": 0.2032, "lr": 5.649716580008346e-07, "epoch": 4.313725490196078, "percentage": 86.27, "elapsed_time": "9:52:08", "remaining_time": "1:34:12"}
{"current_steps": 3750, "total_steps": 4335, "loss": 0.2041, "lr": 5.46522274590004e-07, "epoch": 4.325259515570934, "percentage": 86.51, "elapsed_time": "9:53:42", "remaining_time": "1:32:37"}
{"current_steps": 3760, "total_steps": 4335, "loss": 0.2014, "lr": 5.283617228297083e-07, "epoch": 4.33679354094579, "percentage": 86.74, "elapsed_time": "9:55:15", "remaining_time": "1:31:01"}
{"current_steps": 3770, "total_steps": 4335, "loss": 0.2036, "lr": 5.104911805280493e-07, "epoch": 4.348327566320646, "percentage": 86.97, "elapsed_time": "9:56:47", "remaining_time": "1:29:26"}
{"current_steps": 3780, "total_steps": 4335, "loss": 0.2001, "lr": 4.929118066844774e-07, "epoch": 4.359861591695502, "percentage": 87.2, "elapsed_time": "9:58:21", "remaining_time": "1:27:51"}
{"current_steps": 3790, "total_steps": 4335, "loss": 0.2026, "lr": 4.7562474141461925e-07, "epoch": 4.371395617070357, "percentage": 87.43, "elapsed_time": "9:59:51", "remaining_time": "1:26:15"}
{"current_steps": 3800, "total_steps": 4335, "loss": 0.1967, "lr": 4.586311058763443e-07, "epoch": 4.382929642445213, "percentage": 87.66, "elapsed_time": "10:01:24", "remaining_time": "1:24:40"}
{"current_steps": 3810, "total_steps": 4335, "loss": 0.2042, "lr": 4.419320021970469e-07, "epoch": 4.3944636678200695, "percentage": 87.89, "elapsed_time": "10:02:54", "remaining_time": "1:23:04"}
{"current_steps": 3820, "total_steps": 4335, "loss": 0.1987, "lr": 4.2552851340216974e-07, "epoch": 4.405997693194925, "percentage": 88.12, "elapsed_time": "10:04:25", "remaining_time": "1:21:29"}
{"current_steps": 3830, "total_steps": 4335, "loss": 0.1966, "lr": 4.094217033449605e-07, "epoch": 4.417531718569781, "percentage": 88.35, "elapsed_time": "10:05:56", "remaining_time": "1:19:53"}
{"current_steps": 3840, "total_steps": 4335, "loss": 0.2025, "lr": 3.936126166374765e-07, "epoch": 4.429065743944637, "percentage": 88.58, "elapsed_time": "10:07:27", "remaining_time": "1:18:18"}
{"current_steps": 3850, "total_steps": 4335, "loss": 0.1999, "lr": 3.7810227858283753e-07, "epoch": 4.440599769319492, "percentage": 88.81, "elapsed_time": "10:09:01", "remaining_time": "1:16:43"}
{"current_steps": 3860, "total_steps": 4335, "loss": 0.1955, "lr": 3.628916951087291e-07, "epoch": 4.4521337946943484, "percentage": 89.04, "elapsed_time": "10:10:36", "remaining_time": "1:15:08"}
{"current_steps": 3870, "total_steps": 4335, "loss": 0.2008, "lr": 3.4798185270216444e-07, "epoch": 4.463667820069205, "percentage": 89.27, "elapsed_time": "10:12:08", "remaining_time": "1:13:33"}
{"current_steps": 3880, "total_steps": 4335, "loss": 0.1967, "lr": 3.3337371834549994e-07, "epoch": 4.47520184544406, "percentage": 89.5, "elapsed_time": "10:13:43", "remaining_time": "1:11:58"}
{"current_steps": 3890, "total_steps": 4335, "loss": 0.1984, "lr": 3.190682394537259e-07, "epoch": 4.486735870818916, "percentage": 89.73, "elapsed_time": "10:15:17", "remaining_time": "1:10:23"}
{"current_steps": 3900, "total_steps": 4335, "loss": 0.2032, "lr": 3.050663438130208e-07, "epoch": 4.498269896193771, "percentage": 89.97, "elapsed_time": "10:16:49", "remaining_time": "1:08:47"}
{"current_steps": 3910, "total_steps": 4335, "loss": 0.1995, "lr": 2.913689395205799e-07, "epoch": 4.509803921568627, "percentage": 90.2, "elapsed_time": "10:18:23", "remaining_time": "1:07:13"}
{"current_steps": 3920, "total_steps": 4335, "loss": 0.2003, "lr": 2.779769149257178e-07, "epoch": 4.521337946943484, "percentage": 90.43, "elapsed_time": "10:19:56", "remaining_time": "1:05:37"}
{"current_steps": 3930, "total_steps": 4335, "loss": 0.1987, "lr": 2.648911385722597e-07, "epoch": 4.532871972318339, "percentage": 90.66, "elapsed_time": "10:21:29", "remaining_time": "1:04:02"}
{"current_steps": 3940, "total_steps": 4335, "loss": 0.2024, "lr": 2.521124591422025e-07, "epoch": 4.544405997693195, "percentage": 90.89, "elapsed_time": "10:23:02", "remaining_time": "1:02:27"}
{"current_steps": 3950, "total_steps": 4335, "loss": 0.1972, "lr": 2.396417054006839e-07, "epoch": 4.555940023068051, "percentage": 91.12, "elapsed_time": "10:24:35", "remaining_time": "1:00:52"}
{"current_steps": 3960, "total_steps": 4335, "loss": 0.194, "lr": 2.274796861422246e-07, "epoch": 4.567474048442906, "percentage": 91.35, "elapsed_time": "10:26:03", "remaining_time": "0:59:17"}
{"current_steps": 3970, "total_steps": 4335, "loss": 0.1985, "lr": 2.156271901382767e-07, "epoch": 4.5790080738177625, "percentage": 91.58, "elapsed_time": "10:27:36", "remaining_time": "0:57:42"}
{"current_steps": 3980, "total_steps": 4335, "loss": 0.1991, "lr": 2.0408498608607164e-07, "epoch": 4.590542099192618, "percentage": 91.81, "elapsed_time": "10:29:07", "remaining_time": "0:56:06"}
{"current_steps": 3990, "total_steps": 4335, "loss": 0.2035, "lr": 1.928538225587556e-07, "epoch": 4.602076124567474, "percentage": 92.04, "elapsed_time": "10:30:37", "remaining_time": "0:54:31"}
{"current_steps": 4000, "total_steps": 4335, "loss": 0.2021, "lr": 1.819344279568519e-07, "epoch": 4.61361014994233, "percentage": 92.27, "elapsed_time": "10:32:10", "remaining_time": "0:52:56"}
{"current_steps": 4010, "total_steps": 4335, "loss": 0.2038, "lr": 1.7132751046101405e-07, "epoch": 4.625144175317185, "percentage": 92.5, "elapsed_time": "10:35:36", "remaining_time": "0:51:30"}
{"current_steps": 4020, "total_steps": 4335, "loss": 0.1978, "lr": 1.610337579860971e-07, "epoch": 4.6366782006920415, "percentage": 92.73, "elapsed_time": "10:37:09", "remaining_time": "0:49:55"}
{"current_steps": 4030, "total_steps": 4335, "loss": 0.2039, "lr": 1.5105383813654562e-07, "epoch": 4.648212226066898, "percentage": 92.96, "elapsed_time": "10:38:38", "remaining_time": "0:48:20"}
{"current_steps": 4040, "total_steps": 4335, "loss": 0.1984, "lr": 1.4138839816309202e-07, "epoch": 4.659746251441753, "percentage": 93.19, "elapsed_time": "10:40:09", "remaining_time": "0:46:44"}
{"current_steps": 4050, "total_steps": 4335, "loss": 0.1973, "lr": 1.3203806492078085e-07, "epoch": 4.671280276816609, "percentage": 93.43, "elapsed_time": "10:41:42", "remaining_time": "0:45:09"}
{"current_steps": 4060, "total_steps": 4335, "loss": 0.2021, "lr": 1.230034448283146e-07, "epoch": 4.682814302191465, "percentage": 93.66, "elapsed_time": "10:43:15", "remaining_time": "0:43:34"}
{"current_steps": 4070, "total_steps": 4335, "loss": 0.2031, "lr": 1.1428512382872403e-07, "epoch": 4.6943483275663205, "percentage": 93.89, "elapsed_time": "10:44:46", "remaining_time": "0:41:58"}
{"current_steps": 4080, "total_steps": 4335, "loss": 0.194, "lr": 1.0588366735136635e-07, "epoch": 4.705882352941177, "percentage": 94.12, "elapsed_time": "10:46:18", "remaining_time": "0:40:23"}
{"current_steps": 4090, "total_steps": 4335, "loss": 0.1966, "lr": 9.779962027525124e-08, "epoch": 4.717416378316033, "percentage": 94.35, "elapsed_time": "10:47:51", "remaining_time": "0:38:48"}
{"current_steps": 4100, "total_steps": 4335, "loss": 0.1987, "lr": 9.00335068937086e-08, "epoch": 4.728950403690888, "percentage": 94.58, "elapsed_time": "10:49:24", "remaining_time": "0:37:13"}
{"current_steps": 4110, "total_steps": 4335, "loss": 0.2071, "lr": 8.258583088038008e-08, "epoch": 4.740484429065744, "percentage": 94.81, "elapsed_time": "10:50:56", "remaining_time": "0:35:38"}
{"current_steps": 4120, "total_steps": 4335, "loss": 0.2041, "lr": 7.545707525655533e-08, "epoch": 4.7520184544405994, "percentage": 95.04, "elapsed_time": "10:52:28", "remaining_time": "0:34:02"}
{"current_steps": 4130, "total_steps": 4335, "loss": 0.2005, "lr": 6.864770235984696e-08, "epoch": 4.763552479815456, "percentage": 95.27, "elapsed_time": "10:54:01", "remaining_time": "0:32:27"}
{"current_steps": 4140, "total_steps": 4335, "loss": 0.1933, "lr": 6.215815381420021e-08, "epoch": 4.775086505190312, "percentage": 95.5, "elapsed_time": "10:55:33", "remaining_time": "0:30:52"}
{"current_steps": 4150, "total_steps": 4335, "loss": 0.1969, "lr": 5.5988850501259015e-08, "epoch": 4.786620530565167, "percentage": 95.73, "elapsed_time": "10:57:07", "remaining_time": "0:29:17"}
{"current_steps": 4160, "total_steps": 4335, "loss": 0.1972, "lr": 5.0140192533062457e-08, "epoch": 4.798154555940023, "percentage": 95.96, "elapsed_time": "10:58:42", "remaining_time": "0:27:42"}
{"current_steps": 4170, "total_steps": 4335, "loss": 0.1991, "lr": 4.461255922609986e-08, "epoch": 4.809688581314878, "percentage": 96.19, "elapsed_time": "11:00:15", "remaining_time": "0:26:07"}
{"current_steps": 4180, "total_steps": 4335, "loss": 0.1979, "lr": 3.9406309076707725e-08, "epoch": 4.821222606689735, "percentage": 96.42, "elapsed_time": "11:01:49", "remaining_time": "0:24:32"}
{"current_steps": 4190, "total_steps": 4335, "loss": 0.199, "lr": 3.452177973782167e-08, "epoch": 4.832756632064591, "percentage": 96.66, "elapsed_time": "11:03:22", "remaining_time": "0:22:57"}
{"current_steps": 4200, "total_steps": 4335, "loss": 0.2127, "lr": 2.995928799707504e-08, "epoch": 4.844290657439446, "percentage": 96.89, "elapsed_time": "11:04:52", "remaining_time": "0:21:22"}
{"current_steps": 4210, "total_steps": 4335, "loss": 0.1973, "lr": 2.5719129756255346e-08, "epoch": 4.855824682814302, "percentage": 97.12, "elapsed_time": "11:06:27", "remaining_time": "0:19:47"}
{"current_steps": 4220, "total_steps": 4335, "loss": 0.1995, "lr": 2.180158001211352e-08, "epoch": 4.867358708189158, "percentage": 97.35, "elapsed_time": "11:08:00", "remaining_time": "0:18:12"}
{"current_steps": 4230, "total_steps": 4335, "loss": 0.1954, "lr": 1.8206892838527612e-08, "epoch": 4.8788927335640135, "percentage": 97.58, "elapsed_time": "11:09:33", "remaining_time": "0:16:37"}
{"current_steps": 4240, "total_steps": 4335, "loss": 0.2064, "lr": 1.4935301370026523e-08, "epoch": 4.89042675893887, "percentage": 97.81, "elapsed_time": "11:11:06", "remaining_time": "0:15:02"}
{"current_steps": 4250, "total_steps": 4335, "loss": 0.2025, "lr": 1.198701778666822e-08, "epoch": 4.901960784313726, "percentage": 98.04, "elapsed_time": "11:12:40", "remaining_time": "0:13:27"}
{"current_steps": 4260, "total_steps": 4335, "loss": 0.1995, "lr": 9.362233300280743e-09, "epoch": 4.913494809688581, "percentage": 98.27, "elapsed_time": "11:14:12", "remaining_time": "0:11:52"}
{"current_steps": 4270, "total_steps": 4335, "loss": 0.1953, "lr": 7.061118142058232e-09, "epoch": 4.925028835063437, "percentage": 98.5, "elapsed_time": "11:15:45", "remaining_time": "0:10:17"}
{"current_steps": 4280, "total_steps": 4335, "loss": 0.1979, "lr": 5.083821551523649e-09, "epoch": 4.936562860438293, "percentage": 98.73, "elapsed_time": "11:17:16", "remaining_time": "0:08:42"}
{"current_steps": 4290, "total_steps": 4335, "loss": 0.1989, "lr": 3.430471766848187e-09, "epoch": 4.948096885813149, "percentage": 98.96, "elapsed_time": "11:18:49", "remaining_time": "0:07:07"}
{"current_steps": 4300, "total_steps": 4335, "loss": 0.2055, "lr": 2.1011760165340343e-09, "epoch": 4.959630911188005, "percentage": 99.19, "elapsed_time": "11:20:23", "remaining_time": "0:05:32"}
{"current_steps": 4310, "total_steps": 4335, "loss": 0.2018, "lr": 1.096020512460494e-09, "epoch": 4.97116493656286, "percentage": 99.42, "elapsed_time": "11:21:56", "remaining_time": "0:03:57"}
{"current_steps": 4320, "total_steps": 4335, "loss": 0.1991, "lr": 4.150704442934528e-10, "epoch": 4.982698961937716, "percentage": 99.65, "elapsed_time": "11:23:28", "remaining_time": "0:02:22"}
{"current_steps": 4330, "total_steps": 4335, "loss": 0.2004, "lr": 5.836997525654475e-11, "epoch": 4.994232987312572, "percentage": 99.88, "elapsed_time": "11:25:02", "remaining_time": "0:00:47"}
{"current_steps": 4335, "total_steps": 4335, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "11:27:46", "remaining_time": "0:00:00"}

3074
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:a5f342a059bec85658805bddc64ec730e222db7c615039794742fd1026ef8369
size 7544

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 38 KiB

View File

@@ -0,0 +1,43 @@
{
"crop_size": null,
"data_format": "channels_first",
"default_to_square": true,
"device": null,
"do_center_crop": null,
"do_convert_rgb": true,
"do_normalize": true,
"do_pad": null,
"do_rescale": true,
"do_resize": true,
"do_sample_frames": false,
"fps": null,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"input_data_format": null,
"max_frames": 768,
"max_pixels": 12845056,
"merge_size": 2,
"min_frames": 4,
"min_pixels": 3136,
"num_frames": null,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"size_divisor": null,
"temporal_patch_size": 2,
"video_metadata": null,
"video_processor_type": "Qwen2VLVideoProcessor"
}

1
vocab.json Normal file

File diff suppressed because one or more lines are too long