初始化项目,由ModelHub XC社区提供模型
Model: zhangchenxu/TinyV-1.5B Source: Original Platform
This commit is contained in:
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
fn_tinyv_combine.png filter=lfs diff=lfs merge=lfs -text
|
||||
51
README.md
Normal file
51
README.md
Normal file
@@ -0,0 +1,51 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: Qwen2.5-1.5B-Instruct-SFT-BigmathV_Simple_Balanced-LR1.0e-5-EPOCHS2
|
||||
results: []
|
||||
---
|
||||
|
||||
[**TinyV**]((https://arxiv.org/abs/2505.14625)) is a reward system for efficient RL post-training that detects false negatives in current rule-based verifiers and provides more accurate reward signals via a small LLM during RL training. Experiments show that TinyV incurs only 6% additional computational cost while significantly increasing both RL efficiency and final model performance.
|
||||
|
||||
- 📄 [Technical Report](https://arxiv.org/abs/2505.14625) - Including false negative analysis and theotical insights behind TinyV
|
||||
- 💾 [Github Repo](https://github.com/uw-nsl/TinyV) - Access the complete pipeline for more efficient RL training via TinyV
|
||||
- 🤗 [HF Collection](https://huggingface.co/collections/zhangchenxu/tinyv-682d5840c7e309217df625df) - Training Data, Benchmarks, and Model Artifact
|
||||
|
||||
This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on [zhangchenxu/TinyV_Training_Data_Balanced](https://huggingface.co/datasets/zhangchenxu/TinyV_Training_Data_Balanced) dataset.
|
||||
|
||||
### Overview
|
||||

|
||||
|
||||
### How to use it?
|
||||
|
||||
Please refer to the codebase: [https://github.com/uw-nsl/TinyV](https://github.com/uw-nsl/TinyV) for details.
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 1e-05
|
||||
- train_batch_size: 8
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 512
|
||||
- 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: 2.0
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.48.3
|
||||
- Pytorch 2.5.0
|
||||
- Datasets 3.2.0
|
||||
- Tokenizers 0.21.0
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal 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
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.993968636911942,
|
||||
"total_flos": 7.073469349725471e+17,
|
||||
"train_loss": 0.04489339354387935,
|
||||
"train_runtime": 2537.7411,
|
||||
"train_samples_per_second": 125.415,
|
||||
"train_steps_per_second": 0.244
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.48.3",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
3
fn_tinyv_combine.png
Normal file
3
fn_tinyv_combine.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b8766db466d450dd2a664daa4fda25de769dbc56dc1d1f9d5878ee775798a31e
|
||||
size 1196036
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.48.3"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:495e04787b27d0a3c43b72bd186457775cb051f25cbf598cd74bde4bc6ea1192
|
||||
size 4996670464
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:557af986b956304f25e5db1423b500ef32f5eaf438da1ba0c61ead1aaa14a849
|
||||
size 1178224960
|
||||
345
model.safetensors.index.json
Normal file
345
model.safetensors.index.json
Normal file
@@ -0,0 +1,345 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 6174857216
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal 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
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
209
tokenizer_config.json
Normal file
209
tokenizer_config.json
Normal 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,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.993968636911942,
|
||||
"total_flos": 7.073469349725471e+17,
|
||||
"train_loss": 0.04489339354387935,
|
||||
"train_runtime": 2537.7411,
|
||||
"train_samples_per_second": 125.415,
|
||||
"train_steps_per_second": 0.244
|
||||
}
|
||||
620
trainer_log.jsonl
Normal file
620
trainer_log.jsonl
Normal file
@@ -0,0 +1,620 @@
|
||||
{"current_steps": 1, "total_steps": 620, "loss": 0.3558, "lr": 1.6129032258064518e-07, "epoch": 0.003216726980297547, "percentage": 0.16, "elapsed_time": "0:00:07", "remaining_time": "1:14:53"}
|
||||
{"current_steps": 2, "total_steps": 620, "loss": 0.4071, "lr": 3.2258064516129035e-07, "epoch": 0.006433453960595094, "percentage": 0.32, "elapsed_time": "0:00:12", "remaining_time": "1:06:47"}
|
||||
{"current_steps": 3, "total_steps": 620, "loss": 0.3576, "lr": 4.838709677419355e-07, "epoch": 0.009650180940892641, "percentage": 0.48, "elapsed_time": "0:00:18", "remaining_time": "1:02:48"}
|
||||
{"current_steps": 4, "total_steps": 620, "loss": 0.3627, "lr": 6.451612903225807e-07, "epoch": 0.012866907921190189, "percentage": 0.65, "elapsed_time": "0:00:22", "remaining_time": "0:58:27"}
|
||||
{"current_steps": 5, "total_steps": 620, "loss": 0.3581, "lr": 8.064516129032258e-07, "epoch": 0.016083634901487735, "percentage": 0.81, "elapsed_time": "0:00:26", "remaining_time": "0:55:00"}
|
||||
{"current_steps": 6, "total_steps": 620, "loss": 0.3392, "lr": 9.67741935483871e-07, "epoch": 0.019300361881785282, "percentage": 0.97, "elapsed_time": "0:00:30", "remaining_time": "0:52:50"}
|
||||
{"current_steps": 7, "total_steps": 620, "loss": 0.2786, "lr": 1.1290322580645162e-06, "epoch": 0.02251708886208283, "percentage": 1.13, "elapsed_time": "0:00:33", "remaining_time": "0:49:29"}
|
||||
{"current_steps": 8, "total_steps": 620, "loss": 0.27, "lr": 1.2903225806451614e-06, "epoch": 0.025733815842380377, "percentage": 1.29, "elapsed_time": "0:00:37", "remaining_time": "0:47:26"}
|
||||
{"current_steps": 9, "total_steps": 620, "loss": 0.1758, "lr": 1.4516129032258066e-06, "epoch": 0.028950542822677925, "percentage": 1.45, "elapsed_time": "0:00:41", "remaining_time": "0:46:35"}
|
||||
{"current_steps": 10, "total_steps": 620, "loss": 0.1723, "lr": 1.6129032258064516e-06, "epoch": 0.03216726980297547, "percentage": 1.61, "elapsed_time": "0:00:44", "remaining_time": "0:45:22"}
|
||||
{"current_steps": 11, "total_steps": 620, "loss": 0.1565, "lr": 1.774193548387097e-06, "epoch": 0.03538399678327302, "percentage": 1.77, "elapsed_time": "0:00:48", "remaining_time": "0:44:23"}
|
||||
{"current_steps": 12, "total_steps": 620, "loss": 0.1746, "lr": 1.935483870967742e-06, "epoch": 0.038600723763570564, "percentage": 1.94, "elapsed_time": "0:00:51", "remaining_time": "0:43:30"}
|
||||
{"current_steps": 13, "total_steps": 620, "loss": 0.1709, "lr": 2.096774193548387e-06, "epoch": 0.04181745074386811, "percentage": 2.1, "elapsed_time": "0:00:55", "remaining_time": "0:42:56"}
|
||||
{"current_steps": 14, "total_steps": 620, "loss": 0.1567, "lr": 2.2580645161290324e-06, "epoch": 0.04503417772416566, "percentage": 2.26, "elapsed_time": "0:00:58", "remaining_time": "0:42:18"}
|
||||
{"current_steps": 15, "total_steps": 620, "loss": 0.1344, "lr": 2.4193548387096776e-06, "epoch": 0.04825090470446321, "percentage": 2.42, "elapsed_time": "0:01:02", "remaining_time": "0:41:49"}
|
||||
{"current_steps": 16, "total_steps": 620, "loss": 0.1306, "lr": 2.580645161290323e-06, "epoch": 0.051467631684760755, "percentage": 2.58, "elapsed_time": "0:01:05", "remaining_time": "0:41:03"}
|
||||
{"current_steps": 17, "total_steps": 620, "loss": 0.1368, "lr": 2.7419354838709676e-06, "epoch": 0.0546843586650583, "percentage": 2.74, "elapsed_time": "0:01:07", "remaining_time": "0:39:57"}
|
||||
{"current_steps": 18, "total_steps": 620, "loss": 0.1767, "lr": 2.903225806451613e-06, "epoch": 0.05790108564535585, "percentage": 2.9, "elapsed_time": "0:01:12", "remaining_time": "0:40:24"}
|
||||
{"current_steps": 19, "total_steps": 620, "loss": 0.2103, "lr": 3.0645161290322584e-06, "epoch": 0.0611178126256534, "percentage": 3.06, "elapsed_time": "0:01:15", "remaining_time": "0:39:42"}
|
||||
{"current_steps": 20, "total_steps": 620, "loss": 0.1798, "lr": 3.225806451612903e-06, "epoch": 0.06433453960595094, "percentage": 3.23, "elapsed_time": "0:01:18", "remaining_time": "0:39:24"}
|
||||
{"current_steps": 21, "total_steps": 620, "loss": 0.1326, "lr": 3.3870967741935484e-06, "epoch": 0.06755126658624849, "percentage": 3.39, "elapsed_time": "0:01:22", "remaining_time": "0:39:11"}
|
||||
{"current_steps": 22, "total_steps": 620, "loss": 0.132, "lr": 3.548387096774194e-06, "epoch": 0.07076799356654603, "percentage": 3.55, "elapsed_time": "0:01:25", "remaining_time": "0:38:47"}
|
||||
{"current_steps": 23, "total_steps": 620, "loss": 0.1407, "lr": 3.7096774193548392e-06, "epoch": 0.07398472054684359, "percentage": 3.71, "elapsed_time": "0:01:28", "remaining_time": "0:38:06"}
|
||||
{"current_steps": 24, "total_steps": 620, "loss": 0.1198, "lr": 3.870967741935484e-06, "epoch": 0.07720144752714113, "percentage": 3.87, "elapsed_time": "0:01:31", "remaining_time": "0:37:57"}
|
||||
{"current_steps": 25, "total_steps": 620, "loss": 0.0861, "lr": 4.032258064516129e-06, "epoch": 0.08041817450743868, "percentage": 4.03, "elapsed_time": "0:01:34", "remaining_time": "0:37:30"}
|
||||
{"current_steps": 26, "total_steps": 620, "loss": 0.1043, "lr": 4.193548387096774e-06, "epoch": 0.08363490148773622, "percentage": 4.19, "elapsed_time": "0:01:37", "remaining_time": "0:37:08"}
|
||||
{"current_steps": 27, "total_steps": 620, "loss": 0.135, "lr": 4.35483870967742e-06, "epoch": 0.08685162846803378, "percentage": 4.35, "elapsed_time": "0:01:40", "remaining_time": "0:36:45"}
|
||||
{"current_steps": 28, "total_steps": 620, "loss": 0.1171, "lr": 4.516129032258065e-06, "epoch": 0.09006835544833132, "percentage": 4.52, "elapsed_time": "0:01:43", "remaining_time": "0:36:22"}
|
||||
{"current_steps": 29, "total_steps": 620, "loss": 0.089, "lr": 4.67741935483871e-06, "epoch": 0.09328508242862887, "percentage": 4.68, "elapsed_time": "0:01:45", "remaining_time": "0:35:55"}
|
||||
{"current_steps": 30, "total_steps": 620, "loss": 0.0881, "lr": 4.838709677419355e-06, "epoch": 0.09650180940892641, "percentage": 4.84, "elapsed_time": "0:01:48", "remaining_time": "0:35:38"}
|
||||
{"current_steps": 31, "total_steps": 620, "loss": 0.0965, "lr": 5e-06, "epoch": 0.09971853638922397, "percentage": 5.0, "elapsed_time": "0:01:51", "remaining_time": "0:35:11"}
|
||||
{"current_steps": 32, "total_steps": 620, "loss": 0.0849, "lr": 5.161290322580646e-06, "epoch": 0.10293526336952151, "percentage": 5.16, "elapsed_time": "0:01:54", "remaining_time": "0:34:58"}
|
||||
{"current_steps": 33, "total_steps": 620, "loss": 0.0786, "lr": 5.322580645161291e-06, "epoch": 0.10615199034981906, "percentage": 5.32, "elapsed_time": "0:01:57", "remaining_time": "0:34:45"}
|
||||
{"current_steps": 34, "total_steps": 620, "loss": 0.0675, "lr": 5.483870967741935e-06, "epoch": 0.1093687173301166, "percentage": 5.48, "elapsed_time": "0:02:00", "remaining_time": "0:34:35"}
|
||||
{"current_steps": 35, "total_steps": 620, "loss": 0.0977, "lr": 5.645161290322582e-06, "epoch": 0.11258544431041416, "percentage": 5.65, "elapsed_time": "0:02:03", "remaining_time": "0:34:17"}
|
||||
{"current_steps": 36, "total_steps": 620, "loss": 0.0648, "lr": 5.806451612903226e-06, "epoch": 0.1158021712907117, "percentage": 5.81, "elapsed_time": "0:02:06", "remaining_time": "0:34:06"}
|
||||
{"current_steps": 37, "total_steps": 620, "loss": 0.082, "lr": 5.967741935483872e-06, "epoch": 0.11901889827100925, "percentage": 5.97, "elapsed_time": "0:02:08", "remaining_time": "0:33:51"}
|
||||
{"current_steps": 38, "total_steps": 620, "loss": 0.0758, "lr": 6.129032258064517e-06, "epoch": 0.1222356252513068, "percentage": 6.13, "elapsed_time": "0:02:11", "remaining_time": "0:33:41"}
|
||||
{"current_steps": 39, "total_steps": 620, "loss": 0.066, "lr": 6.290322580645162e-06, "epoch": 0.12545235223160434, "percentage": 6.29, "elapsed_time": "0:02:14", "remaining_time": "0:33:27"}
|
||||
{"current_steps": 40, "total_steps": 620, "loss": 0.0709, "lr": 6.451612903225806e-06, "epoch": 0.12866907921190188, "percentage": 6.45, "elapsed_time": "0:02:17", "remaining_time": "0:33:18"}
|
||||
{"current_steps": 41, "total_steps": 620, "loss": 0.0852, "lr": 6.612903225806452e-06, "epoch": 0.13188580619219945, "percentage": 6.61, "elapsed_time": "0:02:20", "remaining_time": "0:33:08"}
|
||||
{"current_steps": 42, "total_steps": 620, "loss": 0.0702, "lr": 6.774193548387097e-06, "epoch": 0.13510253317249699, "percentage": 6.77, "elapsed_time": "0:02:23", "remaining_time": "0:32:50"}
|
||||
{"current_steps": 43, "total_steps": 620, "loss": 0.0747, "lr": 6.935483870967743e-06, "epoch": 0.13831926015279453, "percentage": 6.94, "elapsed_time": "0:02:26", "remaining_time": "0:32:44"}
|
||||
{"current_steps": 44, "total_steps": 620, "loss": 0.0657, "lr": 7.096774193548388e-06, "epoch": 0.14153598713309207, "percentage": 7.1, "elapsed_time": "0:02:28", "remaining_time": "0:32:29"}
|
||||
{"current_steps": 45, "total_steps": 620, "loss": 0.0717, "lr": 7.258064516129033e-06, "epoch": 0.14475271411338964, "percentage": 7.26, "elapsed_time": "0:02:31", "remaining_time": "0:32:21"}
|
||||
{"current_steps": 46, "total_steps": 620, "loss": 0.066, "lr": 7.4193548387096784e-06, "epoch": 0.14796944109368718, "percentage": 7.42, "elapsed_time": "0:02:34", "remaining_time": "0:32:10"}
|
||||
{"current_steps": 47, "total_steps": 620, "loss": 0.0554, "lr": 7.580645161290323e-06, "epoch": 0.15118616807398472, "percentage": 7.58, "elapsed_time": "0:02:37", "remaining_time": "0:32:01"}
|
||||
{"current_steps": 48, "total_steps": 620, "loss": 0.075, "lr": 7.741935483870968e-06, "epoch": 0.15440289505428226, "percentage": 7.74, "elapsed_time": "0:02:40", "remaining_time": "0:31:53"}
|
||||
{"current_steps": 49, "total_steps": 620, "loss": 0.0583, "lr": 7.903225806451613e-06, "epoch": 0.15761962203457983, "percentage": 7.9, "elapsed_time": "0:02:43", "remaining_time": "0:31:44"}
|
||||
{"current_steps": 50, "total_steps": 620, "loss": 0.0832, "lr": 8.064516129032258e-06, "epoch": 0.16083634901487737, "percentage": 8.06, "elapsed_time": "0:02:45", "remaining_time": "0:31:31"}
|
||||
{"current_steps": 51, "total_steps": 620, "loss": 0.0772, "lr": 8.225806451612904e-06, "epoch": 0.1640530759951749, "percentage": 8.23, "elapsed_time": "0:02:48", "remaining_time": "0:31:19"}
|
||||
{"current_steps": 52, "total_steps": 620, "loss": 0.0734, "lr": 8.387096774193549e-06, "epoch": 0.16726980297547245, "percentage": 8.39, "elapsed_time": "0:02:51", "remaining_time": "0:31:12"}
|
||||
{"current_steps": 53, "total_steps": 620, "loss": 0.0541, "lr": 8.548387096774194e-06, "epoch": 0.17048652995577002, "percentage": 8.55, "elapsed_time": "0:02:54", "remaining_time": "0:31:05"}
|
||||
{"current_steps": 54, "total_steps": 620, "loss": 0.052, "lr": 8.70967741935484e-06, "epoch": 0.17370325693606756, "percentage": 8.71, "elapsed_time": "0:02:57", "remaining_time": "0:31:00"}
|
||||
{"current_steps": 55, "total_steps": 620, "loss": 0.0582, "lr": 8.870967741935484e-06, "epoch": 0.1769199839163651, "percentage": 8.87, "elapsed_time": "0:03:00", "remaining_time": "0:30:56"}
|
||||
{"current_steps": 56, "total_steps": 620, "loss": 0.065, "lr": 9.03225806451613e-06, "epoch": 0.18013671089666264, "percentage": 9.03, "elapsed_time": "0:03:03", "remaining_time": "0:30:45"}
|
||||
{"current_steps": 57, "total_steps": 620, "loss": 0.0624, "lr": 9.193548387096775e-06, "epoch": 0.18335343787696018, "percentage": 9.19, "elapsed_time": "0:03:05", "remaining_time": "0:30:33"}
|
||||
{"current_steps": 58, "total_steps": 620, "loss": 0.0503, "lr": 9.35483870967742e-06, "epoch": 0.18657016485725775, "percentage": 9.35, "elapsed_time": "0:03:08", "remaining_time": "0:30:27"}
|
||||
{"current_steps": 59, "total_steps": 620, "loss": 0.051, "lr": 9.516129032258065e-06, "epoch": 0.1897868918375553, "percentage": 9.52, "elapsed_time": "0:03:11", "remaining_time": "0:30:22"}
|
||||
{"current_steps": 60, "total_steps": 620, "loss": 0.0537, "lr": 9.67741935483871e-06, "epoch": 0.19300361881785283, "percentage": 9.68, "elapsed_time": "0:03:14", "remaining_time": "0:30:11"}
|
||||
{"current_steps": 61, "total_steps": 620, "loss": 0.0528, "lr": 9.838709677419356e-06, "epoch": 0.19622034579815037, "percentage": 9.84, "elapsed_time": "0:03:16", "remaining_time": "0:30:01"}
|
||||
{"current_steps": 62, "total_steps": 620, "loss": 0.0505, "lr": 1e-05, "epoch": 0.19943707277844794, "percentage": 10.0, "elapsed_time": "0:03:18", "remaining_time": "0:29:50"}
|
||||
{"current_steps": 63, "total_steps": 620, "loss": 0.0696, "lr": 9.999920755303033e-06, "epoch": 0.20265379975874548, "percentage": 10.16, "elapsed_time": "0:03:22", "remaining_time": "0:29:46"}
|
||||
{"current_steps": 64, "total_steps": 620, "loss": 0.0502, "lr": 9.999683023724021e-06, "epoch": 0.20587052673904302, "percentage": 10.32, "elapsed_time": "0:03:25", "remaining_time": "0:29:46"}
|
||||
{"current_steps": 65, "total_steps": 620, "loss": 0.0536, "lr": 9.99928681279855e-06, "epoch": 0.20908725371934056, "percentage": 10.48, "elapsed_time": "0:03:28", "remaining_time": "0:29:42"}
|
||||
{"current_steps": 66, "total_steps": 620, "loss": 0.0634, "lr": 9.998732135085665e-06, "epoch": 0.21230398069963813, "percentage": 10.65, "elapsed_time": "0:03:31", "remaining_time": "0:29:36"}
|
||||
{"current_steps": 67, "total_steps": 620, "loss": 0.0472, "lr": 9.998019008167476e-06, "epoch": 0.21552070767993567, "percentage": 10.81, "elapsed_time": "0:03:34", "remaining_time": "0:29:26"}
|
||||
{"current_steps": 68, "total_steps": 620, "loss": 0.0714, "lr": 9.99714745464859e-06, "epoch": 0.2187374346602332, "percentage": 10.97, "elapsed_time": "0:03:36", "remaining_time": "0:29:21"}
|
||||
{"current_steps": 69, "total_steps": 620, "loss": 0.0686, "lr": 9.99611750215541e-06, "epoch": 0.22195416164053075, "percentage": 11.13, "elapsed_time": "0:03:39", "remaining_time": "0:29:15"}
|
||||
{"current_steps": 70, "total_steps": 620, "loss": 0.0707, "lr": 9.994929183335237e-06, "epoch": 0.22517088862082832, "percentage": 11.29, "elapsed_time": "0:03:42", "remaining_time": "0:29:08"}
|
||||
{"current_steps": 71, "total_steps": 620, "loss": 0.0596, "lr": 9.993582535855265e-06, "epoch": 0.22838761560112586, "percentage": 11.45, "elapsed_time": "0:03:44", "remaining_time": "0:28:59"}
|
||||
{"current_steps": 72, "total_steps": 620, "loss": 0.0644, "lr": 9.992077602401358e-06, "epoch": 0.2316043425814234, "percentage": 11.61, "elapsed_time": "0:03:48", "remaining_time": "0:28:55"}
|
||||
{"current_steps": 73, "total_steps": 620, "loss": 0.0566, "lr": 9.990414430676716e-06, "epoch": 0.23482106956172094, "percentage": 11.77, "elapsed_time": "0:03:51", "remaining_time": "0:28:51"}
|
||||
{"current_steps": 74, "total_steps": 620, "loss": 0.0518, "lr": 9.988593073400354e-06, "epoch": 0.2380377965420185, "percentage": 11.94, "elapsed_time": "0:03:53", "remaining_time": "0:28:42"}
|
||||
{"current_steps": 75, "total_steps": 620, "loss": 0.0481, "lr": 9.986613588305435e-06, "epoch": 0.24125452352231605, "percentage": 12.1, "elapsed_time": "0:03:56", "remaining_time": "0:28:38"}
|
||||
{"current_steps": 76, "total_steps": 620, "loss": 0.0458, "lr": 9.984476038137437e-06, "epoch": 0.2444712505026136, "percentage": 12.26, "elapsed_time": "0:03:59", "remaining_time": "0:28:33"}
|
||||
{"current_steps": 77, "total_steps": 620, "loss": 0.0663, "lr": 9.982180490652165e-06, "epoch": 0.24768797748291113, "percentage": 12.42, "elapsed_time": "0:04:01", "remaining_time": "0:28:25"}
|
||||
{"current_steps": 78, "total_steps": 620, "loss": 0.0439, "lr": 9.979727018613607e-06, "epoch": 0.25090470446320867, "percentage": 12.58, "elapsed_time": "0:04:04", "remaining_time": "0:28:17"}
|
||||
{"current_steps": 79, "total_steps": 620, "loss": 0.0668, "lr": 9.977115699791622e-06, "epoch": 0.25412143144350624, "percentage": 12.74, "elapsed_time": "0:04:07", "remaining_time": "0:28:12"}
|
||||
{"current_steps": 80, "total_steps": 620, "loss": 0.0612, "lr": 9.974346616959476e-06, "epoch": 0.25733815842380375, "percentage": 12.9, "elapsed_time": "0:04:10", "remaining_time": "0:28:07"}
|
||||
{"current_steps": 81, "total_steps": 620, "loss": 0.0602, "lr": 9.971419857891223e-06, "epoch": 0.2605548854041013, "percentage": 13.06, "elapsed_time": "0:04:12", "remaining_time": "0:28:00"}
|
||||
{"current_steps": 82, "total_steps": 620, "loss": 0.0623, "lr": 9.968335515358916e-06, "epoch": 0.2637716123843989, "percentage": 13.23, "elapsed_time": "0:04:14", "remaining_time": "0:27:52"}
|
||||
{"current_steps": 83, "total_steps": 620, "loss": 0.0611, "lr": 9.965093687129669e-06, "epoch": 0.2669883393646964, "percentage": 13.39, "elapsed_time": "0:04:17", "remaining_time": "0:27:44"}
|
||||
{"current_steps": 84, "total_steps": 620, "loss": 0.0623, "lr": 9.961694475962562e-06, "epoch": 0.27020506634499397, "percentage": 13.55, "elapsed_time": "0:04:20", "remaining_time": "0:27:40"}
|
||||
{"current_steps": 85, "total_steps": 620, "loss": 0.0758, "lr": 9.95813798960538e-06, "epoch": 0.27342179332529154, "percentage": 13.71, "elapsed_time": "0:04:23", "remaining_time": "0:27:36"}
|
||||
{"current_steps": 86, "total_steps": 620, "loss": 0.0675, "lr": 9.954424340791195e-06, "epoch": 0.27663852030558905, "percentage": 13.87, "elapsed_time": "0:04:25", "remaining_time": "0:27:29"}
|
||||
{"current_steps": 87, "total_steps": 620, "loss": 0.0713, "lr": 9.950553647234798e-06, "epoch": 0.2798552472858866, "percentage": 14.03, "elapsed_time": "0:04:28", "remaining_time": "0:27:22"}
|
||||
{"current_steps": 88, "total_steps": 620, "loss": 0.0577, "lr": 9.94652603162896e-06, "epoch": 0.28307197426618413, "percentage": 14.19, "elapsed_time": "0:04:31", "remaining_time": "0:27:19"}
|
||||
{"current_steps": 89, "total_steps": 620, "loss": 0.062, "lr": 9.942341621640558e-06, "epoch": 0.2862887012464817, "percentage": 14.35, "elapsed_time": "0:04:33", "remaining_time": "0:27:12"}
|
||||
{"current_steps": 90, "total_steps": 620, "loss": 0.0594, "lr": 9.938000549906509e-06, "epoch": 0.28950542822677927, "percentage": 14.52, "elapsed_time": "0:04:36", "remaining_time": "0:27:06"}
|
||||
{"current_steps": 91, "total_steps": 620, "loss": 0.0601, "lr": 9.93350295402958e-06, "epoch": 0.2927221552070768, "percentage": 14.68, "elapsed_time": "0:04:39", "remaining_time": "0:27:02"}
|
||||
{"current_steps": 92, "total_steps": 620, "loss": 0.0654, "lr": 9.92884897657402e-06, "epoch": 0.29593888218737435, "percentage": 14.84, "elapsed_time": "0:04:42", "remaining_time": "0:26:58"}
|
||||
{"current_steps": 93, "total_steps": 620, "loss": 0.0645, "lr": 9.924038765061042e-06, "epoch": 0.2991556091676719, "percentage": 15.0, "elapsed_time": "0:04:44", "remaining_time": "0:26:53"}
|
||||
{"current_steps": 94, "total_steps": 620, "loss": 0.0502, "lr": 9.919072471964146e-06, "epoch": 0.30237233614796943, "percentage": 15.16, "elapsed_time": "0:04:47", "remaining_time": "0:26:49"}
|
||||
{"current_steps": 95, "total_steps": 620, "loss": 0.0601, "lr": 9.913950254704291e-06, "epoch": 0.305589063128267, "percentage": 15.32, "elapsed_time": "0:04:50", "remaining_time": "0:26:43"}
|
||||
{"current_steps": 96, "total_steps": 620, "loss": 0.0552, "lr": 9.908672275644898e-06, "epoch": 0.3088057901085645, "percentage": 15.48, "elapsed_time": "0:04:53", "remaining_time": "0:26:39"}
|
||||
{"current_steps": 97, "total_steps": 620, "loss": 0.0534, "lr": 9.903238702086707e-06, "epoch": 0.3120225170888621, "percentage": 15.65, "elapsed_time": "0:04:56", "remaining_time": "0:26:36"}
|
||||
{"current_steps": 98, "total_steps": 620, "loss": 0.0516, "lr": 9.897649706262474e-06, "epoch": 0.31523924406915965, "percentage": 15.81, "elapsed_time": "0:04:59", "remaining_time": "0:26:34"}
|
||||
{"current_steps": 99, "total_steps": 620, "loss": 0.0544, "lr": 9.89190546533151e-06, "epoch": 0.31845597104945716, "percentage": 15.97, "elapsed_time": "0:05:02", "remaining_time": "0:26:31"}
|
||||
{"current_steps": 100, "total_steps": 620, "loss": 0.0493, "lr": 9.88600616137407e-06, "epoch": 0.32167269802975473, "percentage": 16.13, "elapsed_time": "0:05:05", "remaining_time": "0:26:28"}
|
||||
{"current_steps": 101, "total_steps": 620, "loss": 0.0628, "lr": 9.879951981385577e-06, "epoch": 0.32488942501005225, "percentage": 16.29, "elapsed_time": "0:05:08", "remaining_time": "0:26:25"}
|
||||
{"current_steps": 102, "total_steps": 620, "loss": 0.0426, "lr": 9.873743117270691e-06, "epoch": 0.3281061519903498, "percentage": 16.45, "elapsed_time": "0:05:11", "remaining_time": "0:26:23"}
|
||||
{"current_steps": 103, "total_steps": 620, "loss": 0.0579, "lr": 9.867379765837237e-06, "epoch": 0.3313228789706474, "percentage": 16.61, "elapsed_time": "0:05:14", "remaining_time": "0:26:16"}
|
||||
{"current_steps": 104, "total_steps": 620, "loss": 0.0537, "lr": 9.860862128789954e-06, "epoch": 0.3345396059509449, "percentage": 16.77, "elapsed_time": "0:05:16", "remaining_time": "0:26:10"}
|
||||
{"current_steps": 105, "total_steps": 620, "loss": 0.0406, "lr": 9.854190412724114e-06, "epoch": 0.33775633293124246, "percentage": 16.94, "elapsed_time": "0:05:19", "remaining_time": "0:26:05"}
|
||||
{"current_steps": 106, "total_steps": 620, "loss": 0.0603, "lr": 9.847364829118963e-06, "epoch": 0.34097305991154003, "percentage": 17.1, "elapsed_time": "0:05:22", "remaining_time": "0:26:02"}
|
||||
{"current_steps": 107, "total_steps": 620, "loss": 0.0635, "lr": 9.840385594331022e-06, "epoch": 0.34418978689183755, "percentage": 17.26, "elapsed_time": "0:05:24", "remaining_time": "0:25:56"}
|
||||
{"current_steps": 108, "total_steps": 620, "loss": 0.0538, "lr": 9.833252929587231e-06, "epoch": 0.3474065138721351, "percentage": 17.42, "elapsed_time": "0:05:27", "remaining_time": "0:25:54"}
|
||||
{"current_steps": 109, "total_steps": 620, "loss": 0.0503, "lr": 9.825967060977933e-06, "epoch": 0.3506232408524326, "percentage": 17.58, "elapsed_time": "0:05:30", "remaining_time": "0:25:48"}
|
||||
{"current_steps": 110, "total_steps": 620, "loss": 0.05, "lr": 9.818528219449705e-06, "epoch": 0.3538399678327302, "percentage": 17.74, "elapsed_time": "0:05:32", "remaining_time": "0:25:43"}
|
||||
{"current_steps": 111, "total_steps": 620, "loss": 0.0456, "lr": 9.810936640798046e-06, "epoch": 0.35705669481302776, "percentage": 17.9, "elapsed_time": "0:05:35", "remaining_time": "0:25:36"}
|
||||
{"current_steps": 112, "total_steps": 620, "loss": 0.0522, "lr": 9.803192565659898e-06, "epoch": 0.3602734217933253, "percentage": 18.06, "elapsed_time": "0:05:37", "remaining_time": "0:25:31"}
|
||||
{"current_steps": 113, "total_steps": 620, "loss": 0.0424, "lr": 9.795296239506011e-06, "epoch": 0.36349014877362285, "percentage": 18.23, "elapsed_time": "0:05:40", "remaining_time": "0:25:25"}
|
||||
{"current_steps": 114, "total_steps": 620, "loss": 0.0472, "lr": 9.78724791263318e-06, "epoch": 0.36670687575392036, "percentage": 18.39, "elapsed_time": "0:05:42", "remaining_time": "0:25:19"}
|
||||
{"current_steps": 115, "total_steps": 620, "loss": 0.0528, "lr": 9.779047840156288e-06, "epoch": 0.3699236027342179, "percentage": 18.55, "elapsed_time": "0:05:45", "remaining_time": "0:25:16"}
|
||||
{"current_steps": 116, "total_steps": 620, "loss": 0.0561, "lr": 9.770696282000245e-06, "epoch": 0.3731403297145155, "percentage": 18.71, "elapsed_time": "0:05:47", "remaining_time": "0:25:11"}
|
||||
{"current_steps": 117, "total_steps": 620, "loss": 0.0457, "lr": 9.762193502891726e-06, "epoch": 0.376357056694813, "percentage": 18.87, "elapsed_time": "0:05:50", "remaining_time": "0:25:06"}
|
||||
{"current_steps": 118, "total_steps": 620, "loss": 0.0467, "lr": 9.753539772350792e-06, "epoch": 0.3795737836751106, "percentage": 19.03, "elapsed_time": "0:05:53", "remaining_time": "0:25:03"}
|
||||
{"current_steps": 119, "total_steps": 620, "loss": 0.0406, "lr": 9.744735364682347e-06, "epoch": 0.38279051065540814, "percentage": 19.19, "elapsed_time": "0:05:56", "remaining_time": "0:25:00"}
|
||||
{"current_steps": 120, "total_steps": 620, "loss": 0.0487, "lr": 9.735780558967434e-06, "epoch": 0.38600723763570566, "percentage": 19.35, "elapsed_time": "0:05:58", "remaining_time": "0:24:55"}
|
||||
{"current_steps": 121, "total_steps": 620, "loss": 0.0543, "lr": 9.726675639054403e-06, "epoch": 0.3892239646160032, "percentage": 19.52, "elapsed_time": "0:06:02", "remaining_time": "0:24:52"}
|
||||
{"current_steps": 122, "total_steps": 620, "loss": 0.0493, "lr": 9.717420893549902e-06, "epoch": 0.39244069159630074, "percentage": 19.68, "elapsed_time": "0:06:04", "remaining_time": "0:24:49"}
|
||||
{"current_steps": 123, "total_steps": 620, "loss": 0.0437, "lr": 9.70801661580973e-06, "epoch": 0.3956574185765983, "percentage": 19.84, "elapsed_time": "0:06:07", "remaining_time": "0:24:44"}
|
||||
{"current_steps": 124, "total_steps": 620, "loss": 0.0455, "lr": 9.698463103929542e-06, "epoch": 0.3988741455568959, "percentage": 20.0, "elapsed_time": "0:06:10", "remaining_time": "0:24:41"}
|
||||
{"current_steps": 125, "total_steps": 620, "loss": 0.0569, "lr": 9.688760660735403e-06, "epoch": 0.4020908725371934, "percentage": 20.16, "elapsed_time": "0:06:13", "remaining_time": "0:24:38"}
|
||||
{"current_steps": 126, "total_steps": 620, "loss": 0.0576, "lr": 9.67890959377418e-06, "epoch": 0.40530759951749096, "percentage": 20.32, "elapsed_time": "0:06:16", "remaining_time": "0:24:34"}
|
||||
{"current_steps": 127, "total_steps": 620, "loss": 0.0514, "lr": 9.668910215303797e-06, "epoch": 0.4085243264977885, "percentage": 20.48, "elapsed_time": "0:06:18", "remaining_time": "0:24:31"}
|
||||
{"current_steps": 128, "total_steps": 620, "loss": 0.0444, "lr": 9.658762842283343e-06, "epoch": 0.41174105347808604, "percentage": 20.65, "elapsed_time": "0:06:22", "remaining_time": "0:24:31"}
|
||||
{"current_steps": 129, "total_steps": 620, "loss": 0.0493, "lr": 9.648467796363019e-06, "epoch": 0.4149577804583836, "percentage": 20.81, "elapsed_time": "0:06:25", "remaining_time": "0:24:26"}
|
||||
{"current_steps": 130, "total_steps": 620, "loss": 0.0576, "lr": 9.638025403873939e-06, "epoch": 0.4181745074386811, "percentage": 20.97, "elapsed_time": "0:06:28", "remaining_time": "0:24:24"}
|
||||
{"current_steps": 131, "total_steps": 620, "loss": 0.0599, "lr": 9.627435995817799e-06, "epoch": 0.4213912344189787, "percentage": 21.13, "elapsed_time": "0:06:31", "remaining_time": "0:24:21"}
|
||||
{"current_steps": 132, "total_steps": 620, "loss": 0.0625, "lr": 9.616699907856368e-06, "epoch": 0.42460796139927626, "percentage": 21.29, "elapsed_time": "0:06:34", "remaining_time": "0:24:18"}
|
||||
{"current_steps": 133, "total_steps": 620, "loss": 0.0536, "lr": 9.605817480300863e-06, "epoch": 0.42782468837957377, "percentage": 21.45, "elapsed_time": "0:06:37", "remaining_time": "0:24:14"}
|
||||
{"current_steps": 134, "total_steps": 620, "loss": 0.0636, "lr": 9.594789058101154e-06, "epoch": 0.43104141535987134, "percentage": 21.61, "elapsed_time": "0:06:40", "remaining_time": "0:24:11"}
|
||||
{"current_steps": 135, "total_steps": 620, "loss": 0.0602, "lr": 9.58361499083483e-06, "epoch": 0.43425814234016885, "percentage": 21.77, "elapsed_time": "0:06:43", "remaining_time": "0:24:09"}
|
||||
{"current_steps": 136, "total_steps": 620, "loss": 0.0543, "lr": 9.57229563269612e-06, "epoch": 0.4374748693204664, "percentage": 21.94, "elapsed_time": "0:06:46", "remaining_time": "0:24:06"}
|
||||
{"current_steps": 137, "total_steps": 620, "loss": 0.0456, "lr": 9.560831342484668e-06, "epoch": 0.440691596300764, "percentage": 22.1, "elapsed_time": "0:06:49", "remaining_time": "0:24:02"}
|
||||
{"current_steps": 138, "total_steps": 620, "loss": 0.0868, "lr": 9.549222483594154e-06, "epoch": 0.4439083232810615, "percentage": 22.26, "elapsed_time": "0:06:51", "remaining_time": "0:23:58"}
|
||||
{"current_steps": 139, "total_steps": 620, "loss": 0.0646, "lr": 9.53746942400078e-06, "epoch": 0.44712505026135907, "percentage": 22.42, "elapsed_time": "0:06:55", "remaining_time": "0:23:56"}
|
||||
{"current_steps": 140, "total_steps": 620, "loss": 0.068, "lr": 9.525572536251608e-06, "epoch": 0.45034177724165664, "percentage": 22.58, "elapsed_time": "0:06:58", "remaining_time": "0:23:54"}
|
||||
{"current_steps": 141, "total_steps": 620, "loss": 0.0539, "lr": 9.513532197452737e-06, "epoch": 0.45355850422195415, "percentage": 22.74, "elapsed_time": "0:07:00", "remaining_time": "0:23:49"}
|
||||
{"current_steps": 142, "total_steps": 620, "loss": 0.0515, "lr": 9.501348789257373e-06, "epoch": 0.4567752312022517, "percentage": 22.9, "elapsed_time": "0:07:03", "remaining_time": "0:23:46"}
|
||||
{"current_steps": 143, "total_steps": 620, "loss": 0.0754, "lr": 9.48902269785371e-06, "epoch": 0.45999195818254923, "percentage": 23.06, "elapsed_time": "0:07:06", "remaining_time": "0:23:44"}
|
||||
{"current_steps": 144, "total_steps": 620, "loss": 0.0651, "lr": 9.476554313952697e-06, "epoch": 0.4632086851628468, "percentage": 23.23, "elapsed_time": "0:07:09", "remaining_time": "0:23:39"}
|
||||
{"current_steps": 145, "total_steps": 620, "loss": 0.0578, "lr": 9.46394403277566e-06, "epoch": 0.46642541214314437, "percentage": 23.39, "elapsed_time": "0:07:11", "remaining_time": "0:23:34"}
|
||||
{"current_steps": 146, "total_steps": 620, "loss": 0.0466, "lr": 9.451192254041759e-06, "epoch": 0.4696421391234419, "percentage": 23.55, "elapsed_time": "0:07:14", "remaining_time": "0:23:29"}
|
||||
{"current_steps": 147, "total_steps": 620, "loss": 0.0452, "lr": 9.438299381955333e-06, "epoch": 0.47285886610373945, "percentage": 23.71, "elapsed_time": "0:07:16", "remaining_time": "0:23:25"}
|
||||
{"current_steps": 148, "total_steps": 620, "loss": 0.0445, "lr": 9.425265825193077e-06, "epoch": 0.476075593084037, "percentage": 23.87, "elapsed_time": "0:07:19", "remaining_time": "0:23:22"}
|
||||
{"current_steps": 149, "total_steps": 620, "loss": 0.051, "lr": 9.412091996891097e-06, "epoch": 0.47929232006433453, "percentage": 24.03, "elapsed_time": "0:07:23", "remaining_time": "0:23:21"}
|
||||
{"current_steps": 150, "total_steps": 620, "loss": 0.0473, "lr": 9.398778314631801e-06, "epoch": 0.4825090470446321, "percentage": 24.19, "elapsed_time": "0:07:26", "remaining_time": "0:23:19"}
|
||||
{"current_steps": 151, "total_steps": 620, "loss": 0.0525, "lr": 9.385325200430679e-06, "epoch": 0.4857257740249296, "percentage": 24.35, "elapsed_time": "0:07:29", "remaining_time": "0:23:17"}
|
||||
{"current_steps": 152, "total_steps": 620, "loss": 0.0548, "lr": 9.371733080722911e-06, "epoch": 0.4889425010052272, "percentage": 24.52, "elapsed_time": "0:07:32", "remaining_time": "0:23:14"}
|
||||
{"current_steps": 153, "total_steps": 620, "loss": 0.0379, "lr": 9.358002386349862e-06, "epoch": 0.49215922798552475, "percentage": 24.68, "elapsed_time": "0:07:35", "remaining_time": "0:23:09"}
|
||||
{"current_steps": 154, "total_steps": 620, "loss": 0.0477, "lr": 9.34413355254542e-06, "epoch": 0.49537595496582226, "percentage": 24.84, "elapsed_time": "0:07:38", "remaining_time": "0:23:06"}
|
||||
{"current_steps": 155, "total_steps": 620, "loss": 0.0524, "lr": 9.330127018922195e-06, "epoch": 0.49859268194611983, "percentage": 25.0, "elapsed_time": "0:07:40", "remaining_time": "0:23:02"}
|
||||
{"current_steps": 156, "total_steps": 620, "loss": 0.0508, "lr": 9.31598322945759e-06, "epoch": 0.5018094089264173, "percentage": 25.16, "elapsed_time": "0:07:43", "remaining_time": "0:22:59"}
|
||||
{"current_steps": 157, "total_steps": 620, "loss": 0.0482, "lr": 9.301702632479734e-06, "epoch": 0.505026135906715, "percentage": 25.32, "elapsed_time": "0:07:46", "remaining_time": "0:22:54"}
|
||||
{"current_steps": 158, "total_steps": 620, "loss": 0.0448, "lr": 9.287285680653254e-06, "epoch": 0.5082428628870125, "percentage": 25.48, "elapsed_time": "0:07:48", "remaining_time": "0:22:50"}
|
||||
{"current_steps": 159, "total_steps": 620, "loss": 0.0652, "lr": 9.272732830964948e-06, "epoch": 0.51145958986731, "percentage": 25.65, "elapsed_time": "0:07:51", "remaining_time": "0:22:45"}
|
||||
{"current_steps": 160, "total_steps": 620, "loss": 0.0432, "lr": 9.258044544709276e-06, "epoch": 0.5146763168476075, "percentage": 25.81, "elapsed_time": "0:07:53", "remaining_time": "0:22:41"}
|
||||
{"current_steps": 161, "total_steps": 620, "loss": 0.0389, "lr": 9.243221287473755e-06, "epoch": 0.5178930438279051, "percentage": 25.97, "elapsed_time": "0:07:56", "remaining_time": "0:22:37"}
|
||||
{"current_steps": 162, "total_steps": 620, "loss": 0.0407, "lr": 9.228263529124199e-06, "epoch": 0.5211097708082026, "percentage": 26.13, "elapsed_time": "0:07:58", "remaining_time": "0:22:33"}
|
||||
{"current_steps": 163, "total_steps": 620, "loss": 0.0489, "lr": 9.21317174378982e-06, "epoch": 0.5243264977885002, "percentage": 26.29, "elapsed_time": "0:08:01", "remaining_time": "0:22:29"}
|
||||
{"current_steps": 164, "total_steps": 620, "loss": 0.0448, "lr": 9.197946409848196e-06, "epoch": 0.5275432247687978, "percentage": 26.45, "elapsed_time": "0:08:03", "remaining_time": "0:22:24"}
|
||||
{"current_steps": 165, "total_steps": 620, "loss": 0.0487, "lr": 9.182588009910119e-06, "epoch": 0.5307599517490953, "percentage": 26.61, "elapsed_time": "0:08:06", "remaining_time": "0:22:20"}
|
||||
{"current_steps": 166, "total_steps": 620, "loss": 0.0468, "lr": 9.167097030804289e-06, "epoch": 0.5339766787293928, "percentage": 26.77, "elapsed_time": "0:08:08", "remaining_time": "0:22:16"}
|
||||
{"current_steps": 167, "total_steps": 620, "loss": 0.0589, "lr": 9.151473963561884e-06, "epoch": 0.5371934057096904, "percentage": 26.94, "elapsed_time": "0:08:11", "remaining_time": "0:22:12"}
|
||||
{"current_steps": 168, "total_steps": 620, "loss": 0.0405, "lr": 9.135719303400995e-06, "epoch": 0.5404101326899879, "percentage": 27.1, "elapsed_time": "0:08:14", "remaining_time": "0:22:10"}
|
||||
{"current_steps": 169, "total_steps": 620, "loss": 0.0635, "lr": 9.119833549710927e-06, "epoch": 0.5436268596702855, "percentage": 27.26, "elapsed_time": "0:08:17", "remaining_time": "0:22:07"}
|
||||
{"current_steps": 170, "total_steps": 620, "loss": 0.05, "lr": 9.103817206036383e-06, "epoch": 0.5468435866505831, "percentage": 27.42, "elapsed_time": "0:08:19", "remaining_time": "0:22:03"}
|
||||
{"current_steps": 171, "total_steps": 620, "loss": 0.0555, "lr": 9.087670780061477e-06, "epoch": 0.5500603136308806, "percentage": 27.58, "elapsed_time": "0:08:22", "remaining_time": "0:21:59"}
|
||||
{"current_steps": 172, "total_steps": 620, "loss": 0.0495, "lr": 9.071394783593664e-06, "epoch": 0.5532770406111781, "percentage": 27.74, "elapsed_time": "0:08:25", "remaining_time": "0:21:56"}
|
||||
{"current_steps": 173, "total_steps": 620, "loss": 0.0519, "lr": 9.054989732547507e-06, "epoch": 0.5564937675914756, "percentage": 27.9, "elapsed_time": "0:08:28", "remaining_time": "0:21:54"}
|
||||
{"current_steps": 174, "total_steps": 620, "loss": 0.047, "lr": 9.038456146928325e-06, "epoch": 0.5597104945717732, "percentage": 28.06, "elapsed_time": "0:08:31", "remaining_time": "0:21:51"}
|
||||
{"current_steps": 175, "total_steps": 620, "loss": 0.052, "lr": 9.021794550815713e-06, "epoch": 0.5629272215520708, "percentage": 28.23, "elapsed_time": "0:08:34", "remaining_time": "0:21:47"}
|
||||
{"current_steps": 176, "total_steps": 620, "loss": 0.0587, "lr": 9.005005472346923e-06, "epoch": 0.5661439485323683, "percentage": 28.39, "elapsed_time": "0:08:36", "remaining_time": "0:21:44"}
|
||||
{"current_steps": 177, "total_steps": 620, "loss": 0.0426, "lr": 8.988089443700131e-06, "epoch": 0.5693606755126659, "percentage": 28.55, "elapsed_time": "0:08:40", "remaining_time": "0:21:41"}
|
||||
{"current_steps": 178, "total_steps": 620, "loss": 0.0432, "lr": 8.971047001077561e-06, "epoch": 0.5725774024929634, "percentage": 28.71, "elapsed_time": "0:08:42", "remaining_time": "0:21:37"}
|
||||
{"current_steps": 179, "total_steps": 620, "loss": 0.0467, "lr": 8.953878684688492e-06, "epoch": 0.5757941294732609, "percentage": 28.87, "elapsed_time": "0:08:45", "remaining_time": "0:21:33"}
|
||||
{"current_steps": 180, "total_steps": 620, "loss": 0.0375, "lr": 8.936585038732143e-06, "epoch": 0.5790108564535585, "percentage": 29.03, "elapsed_time": "0:08:47", "remaining_time": "0:21:30"}
|
||||
{"current_steps": 181, "total_steps": 620, "loss": 0.065, "lr": 8.919166611380397e-06, "epoch": 0.582227583433856, "percentage": 29.19, "elapsed_time": "0:08:50", "remaining_time": "0:21:26"}
|
||||
{"current_steps": 182, "total_steps": 620, "loss": 0.0652, "lr": 8.90162395476046e-06, "epoch": 0.5854443104141536, "percentage": 29.35, "elapsed_time": "0:08:53", "remaining_time": "0:21:23"}
|
||||
{"current_steps": 183, "total_steps": 620, "loss": 0.0519, "lr": 8.883957624937333e-06, "epoch": 0.5886610373944512, "percentage": 29.52, "elapsed_time": "0:08:56", "remaining_time": "0:21:21"}
|
||||
{"current_steps": 184, "total_steps": 620, "loss": 0.0562, "lr": 8.866168181896198e-06, "epoch": 0.5918777643747487, "percentage": 29.68, "elapsed_time": "0:08:58", "remaining_time": "0:21:17"}
|
||||
{"current_steps": 185, "total_steps": 620, "loss": 0.0472, "lr": 8.848256189524661e-06, "epoch": 0.5950944913550462, "percentage": 29.84, "elapsed_time": "0:09:01", "remaining_time": "0:21:14"}
|
||||
{"current_steps": 186, "total_steps": 620, "loss": 0.0359, "lr": 8.83022221559489e-06, "epoch": 0.5983112183353438, "percentage": 30.0, "elapsed_time": "0:09:04", "remaining_time": "0:21:11"}
|
||||
{"current_steps": 187, "total_steps": 620, "loss": 0.0335, "lr": 8.812066831745602e-06, "epoch": 0.6015279453156414, "percentage": 30.16, "elapsed_time": "0:09:07", "remaining_time": "0:21:07"}
|
||||
{"current_steps": 188, "total_steps": 620, "loss": 0.0459, "lr": 8.793790613463956e-06, "epoch": 0.6047446722959389, "percentage": 30.32, "elapsed_time": "0:09:10", "remaining_time": "0:21:03"}
|
||||
{"current_steps": 189, "total_steps": 620, "loss": 0.0445, "lr": 8.775394140067299e-06, "epoch": 0.6079613992762364, "percentage": 30.48, "elapsed_time": "0:09:12", "remaining_time": "0:21:00"}
|
||||
{"current_steps": 190, "total_steps": 620, "loss": 0.0468, "lr": 8.756877994684818e-06, "epoch": 0.611178126256534, "percentage": 30.65, "elapsed_time": "0:09:15", "remaining_time": "0:20:57"}
|
||||
{"current_steps": 191, "total_steps": 620, "loss": 0.0433, "lr": 8.738242764239046e-06, "epoch": 0.6143948532368315, "percentage": 30.81, "elapsed_time": "0:09:19", "remaining_time": "0:20:56"}
|
||||
{"current_steps": 192, "total_steps": 620, "loss": 0.0467, "lr": 8.719489039427256e-06, "epoch": 0.617611580217129, "percentage": 30.97, "elapsed_time": "0:09:21", "remaining_time": "0:20:52"}
|
||||
{"current_steps": 193, "total_steps": 620, "loss": 0.0407, "lr": 8.700617414702746e-06, "epoch": 0.6208283071974267, "percentage": 31.13, "elapsed_time": "0:09:24", "remaining_time": "0:20:49"}
|
||||
{"current_steps": 194, "total_steps": 620, "loss": 0.0524, "lr": 8.681628488255986e-06, "epoch": 0.6240450341777242, "percentage": 31.29, "elapsed_time": "0:09:27", "remaining_time": "0:20:45"}
|
||||
{"current_steps": 195, "total_steps": 620, "loss": 0.0354, "lr": 8.66252286199567e-06, "epoch": 0.6272617611580217, "percentage": 31.45, "elapsed_time": "0:09:29", "remaining_time": "0:20:41"}
|
||||
{"current_steps": 196, "total_steps": 620, "loss": 0.0525, "lr": 8.643301141529619e-06, "epoch": 0.6304784881383193, "percentage": 31.61, "elapsed_time": "0:09:32", "remaining_time": "0:20:37"}
|
||||
{"current_steps": 197, "total_steps": 620, "loss": 0.0471, "lr": 8.6239639361456e-06, "epoch": 0.6336952151186168, "percentage": 31.77, "elapsed_time": "0:09:34", "remaining_time": "0:20:34"}
|
||||
{"current_steps": 198, "total_steps": 620, "loss": 0.0347, "lr": 8.604511858792006e-06, "epoch": 0.6369119420989143, "percentage": 31.94, "elapsed_time": "0:09:37", "remaining_time": "0:20:30"}
|
||||
{"current_steps": 199, "total_steps": 620, "loss": 0.0621, "lr": 8.584945526058426e-06, "epoch": 0.640128669079212, "percentage": 32.1, "elapsed_time": "0:09:40", "remaining_time": "0:20:28"}
|
||||
{"current_steps": 200, "total_steps": 620, "loss": 0.0444, "lr": 8.565265558156101e-06, "epoch": 0.6433453960595095, "percentage": 32.26, "elapsed_time": "0:09:43", "remaining_time": "0:20:26"}
|
||||
{"current_steps": 201, "total_steps": 620, "loss": 0.0505, "lr": 8.545472578898276e-06, "epoch": 0.646562123039807, "percentage": 32.42, "elapsed_time": "0:09:46", "remaining_time": "0:20:22"}
|
||||
{"current_steps": 202, "total_steps": 620, "loss": 0.0522, "lr": 8.525567215680397e-06, "epoch": 0.6497788500201045, "percentage": 32.58, "elapsed_time": "0:09:48", "remaining_time": "0:20:18"}
|
||||
{"current_steps": 203, "total_steps": 620, "loss": 0.0388, "lr": 8.505550099460264e-06, "epoch": 0.6529955770004021, "percentage": 32.74, "elapsed_time": "0:09:51", "remaining_time": "0:20:14"}
|
||||
{"current_steps": 204, "total_steps": 620, "loss": 0.0557, "lr": 8.485421864737997e-06, "epoch": 0.6562123039806996, "percentage": 32.9, "elapsed_time": "0:09:53", "remaining_time": "0:20:10"}
|
||||
{"current_steps": 205, "total_steps": 620, "loss": 0.0539, "lr": 8.465183149535939e-06, "epoch": 0.6594290309609971, "percentage": 33.06, "elapsed_time": "0:09:56", "remaining_time": "0:20:08"}
|
||||
{"current_steps": 206, "total_steps": 620, "loss": 0.0526, "lr": 8.444834595378434e-06, "epoch": 0.6626457579412948, "percentage": 33.23, "elapsed_time": "0:09:59", "remaining_time": "0:20:04"}
|
||||
{"current_steps": 207, "total_steps": 620, "loss": 0.0523, "lr": 8.424376847271483e-06, "epoch": 0.6658624849215923, "percentage": 33.39, "elapsed_time": "0:10:02", "remaining_time": "0:20:01"}
|
||||
{"current_steps": 208, "total_steps": 620, "loss": 0.0482, "lr": 8.403810553682307e-06, "epoch": 0.6690792119018898, "percentage": 33.55, "elapsed_time": "0:10:04", "remaining_time": "0:19:57"}
|
||||
{"current_steps": 209, "total_steps": 620, "loss": 0.0477, "lr": 8.383136366518788e-06, "epoch": 0.6722959388821874, "percentage": 33.71, "elapsed_time": "0:10:07", "remaining_time": "0:19:53"}
|
||||
{"current_steps": 210, "total_steps": 620, "loss": 0.05, "lr": 8.362354941108803e-06, "epoch": 0.6755126658624849, "percentage": 33.87, "elapsed_time": "0:10:09", "remaining_time": "0:19:50"}
|
||||
{"current_steps": 211, "total_steps": 620, "loss": 0.0532, "lr": 8.341466936179457e-06, "epoch": 0.6787293928427824, "percentage": 34.03, "elapsed_time": "0:10:12", "remaining_time": "0:19:47"}
|
||||
{"current_steps": 212, "total_steps": 620, "loss": 0.0385, "lr": 8.320473013836197e-06, "epoch": 0.6819461198230801, "percentage": 34.19, "elapsed_time": "0:10:15", "remaining_time": "0:19:44"}
|
||||
{"current_steps": 213, "total_steps": 620, "loss": 0.0345, "lr": 8.299373839541829e-06, "epoch": 0.6851628468033776, "percentage": 34.35, "elapsed_time": "0:10:17", "remaining_time": "0:19:40"}
|
||||
{"current_steps": 214, "total_steps": 620, "loss": 0.0549, "lr": 8.278170082095422e-06, "epoch": 0.6883795737836751, "percentage": 34.52, "elapsed_time": "0:10:20", "remaining_time": "0:19:37"}
|
||||
{"current_steps": 215, "total_steps": 620, "loss": 0.0368, "lr": 8.256862413611113e-06, "epoch": 0.6915963007639726, "percentage": 34.68, "elapsed_time": "0:10:23", "remaining_time": "0:19:34"}
|
||||
{"current_steps": 216, "total_steps": 620, "loss": 0.0396, "lr": 8.23545150949679e-06, "epoch": 0.6948130277442702, "percentage": 34.84, "elapsed_time": "0:10:25", "remaining_time": "0:19:30"}
|
||||
{"current_steps": 217, "total_steps": 620, "loss": 0.0534, "lr": 8.213938048432697e-06, "epoch": 0.6980297547245677, "percentage": 35.0, "elapsed_time": "0:10:28", "remaining_time": "0:19:27"}
|
||||
{"current_steps": 218, "total_steps": 620, "loss": 0.0463, "lr": 8.192322712349917e-06, "epoch": 0.7012464817048653, "percentage": 35.16, "elapsed_time": "0:10:31", "remaining_time": "0:19:24"}
|
||||
{"current_steps": 219, "total_steps": 620, "loss": 0.0392, "lr": 8.170606186408756e-06, "epoch": 0.7044632086851629, "percentage": 35.32, "elapsed_time": "0:10:33", "remaining_time": "0:19:20"}
|
||||
{"current_steps": 220, "total_steps": 620, "loss": 0.056, "lr": 8.148789158977012e-06, "epoch": 0.7076799356654604, "percentage": 35.48, "elapsed_time": "0:10:38", "remaining_time": "0:19:20"}
|
||||
{"current_steps": 221, "total_steps": 620, "loss": 0.059, "lr": 8.126872321608185e-06, "epoch": 0.7108966626457579, "percentage": 35.65, "elapsed_time": "0:10:41", "remaining_time": "0:19:17"}
|
||||
{"current_steps": 222, "total_steps": 620, "loss": 0.0493, "lr": 8.104856369019525e-06, "epoch": 0.7141133896260555, "percentage": 35.81, "elapsed_time": "0:10:43", "remaining_time": "0:19:14"}
|
||||
{"current_steps": 223, "total_steps": 620, "loss": 0.0411, "lr": 8.08274199907003e-06, "epoch": 0.717330116606353, "percentage": 35.97, "elapsed_time": "0:10:46", "remaining_time": "0:19:10"}
|
||||
{"current_steps": 224, "total_steps": 620, "loss": 0.0419, "lr": 8.060529912738316e-06, "epoch": 0.7205468435866506, "percentage": 36.13, "elapsed_time": "0:10:48", "remaining_time": "0:19:06"}
|
||||
{"current_steps": 225, "total_steps": 620, "loss": 0.0504, "lr": 8.038220814100403e-06, "epoch": 0.7237635705669482, "percentage": 36.29, "elapsed_time": "0:10:51", "remaining_time": "0:19:02"}
|
||||
{"current_steps": 226, "total_steps": 620, "loss": 0.0512, "lr": 8.0158154103074e-06, "epoch": 0.7269802975472457, "percentage": 36.45, "elapsed_time": "0:10:53", "remaining_time": "0:18:59"}
|
||||
{"current_steps": 227, "total_steps": 620, "loss": 0.0559, "lr": 7.993314411563075e-06, "epoch": 0.7301970245275432, "percentage": 36.61, "elapsed_time": "0:10:55", "remaining_time": "0:18:55"}
|
||||
{"current_steps": 228, "total_steps": 620, "loss": 0.0439, "lr": 7.970718531101365e-06, "epoch": 0.7334137515078407, "percentage": 36.77, "elapsed_time": "0:10:58", "remaining_time": "0:18:52"}
|
||||
{"current_steps": 229, "total_steps": 620, "loss": 0.0399, "lr": 7.948028485163744e-06, "epoch": 0.7366304784881383, "percentage": 36.94, "elapsed_time": "0:11:01", "remaining_time": "0:18:49"}
|
||||
{"current_steps": 230, "total_steps": 620, "loss": 0.0573, "lr": 7.925244992976538e-06, "epoch": 0.7398472054684359, "percentage": 37.1, "elapsed_time": "0:11:06", "remaining_time": "0:18:49"}
|
||||
{"current_steps": 231, "total_steps": 620, "loss": 0.0464, "lr": 7.902368776728125e-06, "epoch": 0.7430639324487334, "percentage": 37.26, "elapsed_time": "0:11:08", "remaining_time": "0:18:46"}
|
||||
{"current_steps": 232, "total_steps": 620, "loss": 0.0453, "lr": 7.879400561546033e-06, "epoch": 0.746280659429031, "percentage": 37.42, "elapsed_time": "0:11:11", "remaining_time": "0:18:42"}
|
||||
{"current_steps": 233, "total_steps": 620, "loss": 0.0467, "lr": 7.856341075473963e-06, "epoch": 0.7494973864093285, "percentage": 37.58, "elapsed_time": "0:11:15", "remaining_time": "0:18:41"}
|
||||
{"current_steps": 234, "total_steps": 620, "loss": 0.0377, "lr": 7.833191049448706e-06, "epoch": 0.752714113389626, "percentage": 37.74, "elapsed_time": "0:11:17", "remaining_time": "0:18:37"}
|
||||
{"current_steps": 235, "total_steps": 620, "loss": 0.0427, "lr": 7.809951217276986e-06, "epoch": 0.7559308403699236, "percentage": 37.9, "elapsed_time": "0:11:19", "remaining_time": "0:18:33"}
|
||||
{"current_steps": 236, "total_steps": 620, "loss": 0.0433, "lr": 7.786622315612182e-06, "epoch": 0.7591475673502212, "percentage": 38.06, "elapsed_time": "0:11:22", "remaining_time": "0:18:31"}
|
||||
{"current_steps": 237, "total_steps": 620, "loss": 0.0394, "lr": 7.763205083930995e-06, "epoch": 0.7623642943305187, "percentage": 38.23, "elapsed_time": "0:11:25", "remaining_time": "0:18:27"}
|
||||
{"current_steps": 238, "total_steps": 620, "loss": 0.0379, "lr": 7.739700264509993e-06, "epoch": 0.7655810213108163, "percentage": 38.39, "elapsed_time": "0:11:27", "remaining_time": "0:18:23"}
|
||||
{"current_steps": 239, "total_steps": 620, "loss": 0.0599, "lr": 7.716108602402094e-06, "epoch": 0.7687977482911138, "percentage": 38.55, "elapsed_time": "0:11:30", "remaining_time": "0:18:20"}
|
||||
{"current_steps": 240, "total_steps": 620, "loss": 0.0465, "lr": 7.692430845412946e-06, "epoch": 0.7720144752714113, "percentage": 38.71, "elapsed_time": "0:11:32", "remaining_time": "0:18:16"}
|
||||
{"current_steps": 241, "total_steps": 620, "loss": 0.0478, "lr": 7.668667744077215e-06, "epoch": 0.7752312022517089, "percentage": 38.87, "elapsed_time": "0:11:35", "remaining_time": "0:18:13"}
|
||||
{"current_steps": 242, "total_steps": 620, "loss": 0.0503, "lr": 7.644820051634813e-06, "epoch": 0.7784479292320065, "percentage": 39.03, "elapsed_time": "0:11:37", "remaining_time": "0:18:10"}
|
||||
{"current_steps": 243, "total_steps": 620, "loss": 0.0412, "lr": 7.6208885240069995e-06, "epoch": 0.781664656212304, "percentage": 39.19, "elapsed_time": "0:11:40", "remaining_time": "0:18:06"}
|
||||
{"current_steps": 244, "total_steps": 620, "loss": 0.0436, "lr": 7.596873919772438e-06, "epoch": 0.7848813831926015, "percentage": 39.35, "elapsed_time": "0:11:43", "remaining_time": "0:18:03"}
|
||||
{"current_steps": 245, "total_steps": 620, "loss": 0.0347, "lr": 7.572777000143145e-06, "epoch": 0.7880981101728991, "percentage": 39.52, "elapsed_time": "0:11:45", "remaining_time": "0:18:00"}
|
||||
{"current_steps": 246, "total_steps": 620, "loss": 0.0478, "lr": 7.548598528940354e-06, "epoch": 0.7913148371531966, "percentage": 39.68, "elapsed_time": "0:11:48", "remaining_time": "0:17:56"}
|
||||
{"current_steps": 247, "total_steps": 620, "loss": 0.0511, "lr": 7.524339272570317e-06, "epoch": 0.7945315641334941, "percentage": 39.84, "elapsed_time": "0:11:50", "remaining_time": "0:17:53"}
|
||||
{"current_steps": 248, "total_steps": 620, "loss": 0.055, "lr": 7.500000000000001e-06, "epoch": 0.7977482911137918, "percentage": 40.0, "elapsed_time": "0:11:53", "remaining_time": "0:17:50"}
|
||||
{"current_steps": 249, "total_steps": 620, "loss": 0.0557, "lr": 7.475581482732717e-06, "epoch": 0.8009650180940893, "percentage": 40.16, "elapsed_time": "0:11:56", "remaining_time": "0:17:47"}
|
||||
{"current_steps": 250, "total_steps": 620, "loss": 0.0469, "lr": 7.451084494783668e-06, "epoch": 0.8041817450743868, "percentage": 40.32, "elapsed_time": "0:11:58", "remaining_time": "0:17:43"}
|
||||
{"current_steps": 251, "total_steps": 620, "loss": 0.0489, "lr": 7.4265098126554065e-06, "epoch": 0.8073984720546844, "percentage": 40.48, "elapsed_time": "0:12:02", "remaining_time": "0:17:41"}
|
||||
{"current_steps": 252, "total_steps": 620, "loss": 0.0501, "lr": 7.401858215313228e-06, "epoch": 0.8106151990349819, "percentage": 40.65, "elapsed_time": "0:12:05", "remaining_time": "0:17:38"}
|
||||
{"current_steps": 253, "total_steps": 620, "loss": 0.0317, "lr": 7.3771304841604764e-06, "epoch": 0.8138319260152794, "percentage": 40.81, "elapsed_time": "0:12:07", "remaining_time": "0:17:35"}
|
||||
{"current_steps": 254, "total_steps": 620, "loss": 0.0414, "lr": 7.352327403013779e-06, "epoch": 0.817048652995577, "percentage": 40.97, "elapsed_time": "0:12:09", "remaining_time": "0:17:31"}
|
||||
{"current_steps": 255, "total_steps": 620, "loss": 0.0413, "lr": 7.327449758078194e-06, "epoch": 0.8202653799758746, "percentage": 41.13, "elapsed_time": "0:12:13", "remaining_time": "0:17:29"}
|
||||
{"current_steps": 256, "total_steps": 620, "loss": 0.0406, "lr": 7.302498337922293e-06, "epoch": 0.8234821069561721, "percentage": 41.29, "elapsed_time": "0:12:15", "remaining_time": "0:17:25"}
|
||||
{"current_steps": 257, "total_steps": 620, "loss": 0.0386, "lr": 7.27747393345317e-06, "epoch": 0.8266988339364696, "percentage": 41.45, "elapsed_time": "0:12:18", "remaining_time": "0:17:23"}
|
||||
{"current_steps": 258, "total_steps": 620, "loss": 0.0554, "lr": 7.2523773378913655e-06, "epoch": 0.8299155609167672, "percentage": 41.61, "elapsed_time": "0:12:21", "remaining_time": "0:17:19"}
|
||||
{"current_steps": 259, "total_steps": 620, "loss": 0.0434, "lr": 7.2272093467457226e-06, "epoch": 0.8331322878970647, "percentage": 41.77, "elapsed_time": "0:12:23", "remaining_time": "0:17:16"}
|
||||
{"current_steps": 260, "total_steps": 620, "loss": 0.0486, "lr": 7.201970757788172e-06, "epoch": 0.8363490148773622, "percentage": 41.94, "elapsed_time": "0:12:26", "remaining_time": "0:17:13"}
|
||||
{"current_steps": 261, "total_steps": 620, "loss": 0.0448, "lr": 7.17666237102845e-06, "epoch": 0.8395657418576599, "percentage": 42.1, "elapsed_time": "0:12:29", "remaining_time": "0:17:10"}
|
||||
{"current_steps": 262, "total_steps": 620, "loss": 0.044, "lr": 7.151284988688731e-06, "epoch": 0.8427824688379574, "percentage": 42.26, "elapsed_time": "0:12:31", "remaining_time": "0:17:07"}
|
||||
{"current_steps": 263, "total_steps": 620, "loss": 0.0477, "lr": 7.125839415178204e-06, "epoch": 0.8459991958182549, "percentage": 42.42, "elapsed_time": "0:12:34", "remaining_time": "0:17:04"}
|
||||
{"current_steps": 264, "total_steps": 620, "loss": 0.0396, "lr": 7.100326457067576e-06, "epoch": 0.8492159227985525, "percentage": 42.58, "elapsed_time": "0:12:37", "remaining_time": "0:17:01"}
|
||||
{"current_steps": 265, "total_steps": 620, "loss": 0.051, "lr": 7.074746923063497e-06, "epoch": 0.85243264977885, "percentage": 42.74, "elapsed_time": "0:12:40", "remaining_time": "0:16:58"}
|
||||
{"current_steps": 266, "total_steps": 620, "loss": 0.0445, "lr": 7.049101623982938e-06, "epoch": 0.8556493767591475, "percentage": 42.9, "elapsed_time": "0:12:43", "remaining_time": "0:16:56"}
|
||||
{"current_steps": 267, "total_steps": 620, "loss": 0.0378, "lr": 7.02339137272748e-06, "epoch": 0.8588661037394452, "percentage": 43.06, "elapsed_time": "0:12:46", "remaining_time": "0:16:54"}
|
||||
{"current_steps": 268, "total_steps": 620, "loss": 0.0395, "lr": 6.9976169842575526e-06, "epoch": 0.8620828307197427, "percentage": 43.23, "elapsed_time": "0:12:49", "remaining_time": "0:16:50"}
|
||||
{"current_steps": 269, "total_steps": 620, "loss": 0.032, "lr": 6.971779275566593e-06, "epoch": 0.8652995577000402, "percentage": 43.39, "elapsed_time": "0:12:51", "remaining_time": "0:16:47"}
|
||||
{"current_steps": 270, "total_steps": 620, "loss": 0.0463, "lr": 6.945879065655164e-06, "epoch": 0.8685162846803377, "percentage": 43.55, "elapsed_time": "0:12:54", "remaining_time": "0:16:43"}
|
||||
{"current_steps": 271, "total_steps": 620, "loss": 0.0556, "lr": 6.919917175504978e-06, "epoch": 0.8717330116606353, "percentage": 43.71, "elapsed_time": "0:12:56", "remaining_time": "0:16:40"}
|
||||
{"current_steps": 272, "total_steps": 620, "loss": 0.0534, "lr": 6.893894428052881e-06, "epoch": 0.8749497386409328, "percentage": 43.87, "elapsed_time": "0:12:59", "remaining_time": "0:16:37"}
|
||||
{"current_steps": 273, "total_steps": 620, "loss": 0.0486, "lr": 6.867811648164769e-06, "epoch": 0.8781664656212304, "percentage": 44.03, "elapsed_time": "0:13:02", "remaining_time": "0:16:34"}
|
||||
{"current_steps": 274, "total_steps": 620, "loss": 0.0464, "lr": 6.841669662609437e-06, "epoch": 0.881383192601528, "percentage": 44.19, "elapsed_time": "0:13:04", "remaining_time": "0:16:30"}
|
||||
{"current_steps": 275, "total_steps": 620, "loss": 0.0338, "lr": 6.815469300032374e-06, "epoch": 0.8845999195818255, "percentage": 44.35, "elapsed_time": "0:13:07", "remaining_time": "0:16:28"}
|
||||
{"current_steps": 276, "total_steps": 620, "loss": 0.0283, "lr": 6.789211390929497e-06, "epoch": 0.887816646562123, "percentage": 44.52, "elapsed_time": "0:13:10", "remaining_time": "0:16:24"}
|
||||
{"current_steps": 277, "total_steps": 620, "loss": 0.0488, "lr": 6.762896767620827e-06, "epoch": 0.8910333735424206, "percentage": 44.68, "elapsed_time": "0:13:12", "remaining_time": "0:16:21"}
|
||||
{"current_steps": 278, "total_steps": 620, "loss": 0.0412, "lr": 6.736526264224101e-06, "epoch": 0.8942501005227181, "percentage": 44.84, "elapsed_time": "0:13:15", "remaining_time": "0:16:18"}
|
||||
{"current_steps": 279, "total_steps": 620, "loss": 0.0403, "lr": 6.710100716628345e-06, "epoch": 0.8974668275030157, "percentage": 45.0, "elapsed_time": "0:13:18", "remaining_time": "0:16:15"}
|
||||
{"current_steps": 280, "total_steps": 620, "loss": 0.0527, "lr": 6.6836209624673575e-06, "epoch": 0.9006835544833133, "percentage": 45.16, "elapsed_time": "0:13:20", "remaining_time": "0:16:12"}
|
||||
{"current_steps": 281, "total_steps": 620, "loss": 0.0517, "lr": 6.657087841093179e-06, "epoch": 0.9039002814636108, "percentage": 45.32, "elapsed_time": "0:13:23", "remaining_time": "0:16:08"}
|
||||
{"current_steps": 282, "total_steps": 620, "loss": 0.041, "lr": 6.6305021935494755e-06, "epoch": 0.9071170084439083, "percentage": 45.48, "elapsed_time": "0:13:27", "remaining_time": "0:16:07"}
|
||||
{"current_steps": 283, "total_steps": 620, "loss": 0.0474, "lr": 6.603864862544879e-06, "epoch": 0.9103337354242059, "percentage": 45.65, "elapsed_time": "0:13:30", "remaining_time": "0:16:05"}
|
||||
{"current_steps": 284, "total_steps": 620, "loss": 0.0418, "lr": 6.5771766924262795e-06, "epoch": 0.9135504624045034, "percentage": 45.81, "elapsed_time": "0:13:33", "remaining_time": "0:16:02"}
|
||||
{"current_steps": 285, "total_steps": 620, "loss": 0.0386, "lr": 6.5504385291520554e-06, "epoch": 0.916767189384801, "percentage": 45.97, "elapsed_time": "0:13:36", "remaining_time": "0:15:59"}
|
||||
{"current_steps": 286, "total_steps": 620, "loss": 0.0394, "lr": 6.523651220265269e-06, "epoch": 0.9199839163650985, "percentage": 46.13, "elapsed_time": "0:13:39", "remaining_time": "0:15:56"}
|
||||
{"current_steps": 287, "total_steps": 620, "loss": 0.0486, "lr": 6.496815614866792e-06, "epoch": 0.9232006433453961, "percentage": 46.29, "elapsed_time": "0:13:41", "remaining_time": "0:15:53"}
|
||||
{"current_steps": 288, "total_steps": 620, "loss": 0.0385, "lr": 6.469932563588386e-06, "epoch": 0.9264173703256936, "percentage": 46.45, "elapsed_time": "0:13:44", "remaining_time": "0:15:50"}
|
||||
{"current_steps": 289, "total_steps": 620, "loss": 0.05, "lr": 6.443002918565754e-06, "epoch": 0.9296340973059911, "percentage": 46.61, "elapsed_time": "0:13:46", "remaining_time": "0:15:46"}
|
||||
{"current_steps": 290, "total_steps": 620, "loss": 0.0439, "lr": 6.41602753341152e-06, "epoch": 0.9328508242862887, "percentage": 46.77, "elapsed_time": "0:13:49", "remaining_time": "0:15:44"}
|
||||
{"current_steps": 291, "total_steps": 620, "loss": 0.0472, "lr": 6.389007263188176e-06, "epoch": 0.9360675512665863, "percentage": 46.94, "elapsed_time": "0:13:52", "remaining_time": "0:15:41"}
|
||||
{"current_steps": 292, "total_steps": 620, "loss": 0.0454, "lr": 6.361942964380967e-06, "epoch": 0.9392842782468838, "percentage": 47.1, "elapsed_time": "0:13:55", "remaining_time": "0:15:38"}
|
||||
{"current_steps": 293, "total_steps": 620, "loss": 0.0351, "lr": 6.334835494870759e-06, "epoch": 0.9425010052271814, "percentage": 47.26, "elapsed_time": "0:13:58", "remaining_time": "0:15:35"}
|
||||
{"current_steps": 294, "total_steps": 620, "loss": 0.0344, "lr": 6.307685713906835e-06, "epoch": 0.9457177322074789, "percentage": 47.42, "elapsed_time": "0:14:00", "remaining_time": "0:15:32"}
|
||||
{"current_steps": 295, "total_steps": 620, "loss": 0.0308, "lr": 6.2804944820796596e-06, "epoch": 0.9489344591877764, "percentage": 47.58, "elapsed_time": "0:14:03", "remaining_time": "0:15:29"}
|
||||
{"current_steps": 296, "total_steps": 620, "loss": 0.0541, "lr": 6.2532626612936035e-06, "epoch": 0.952151186168074, "percentage": 47.74, "elapsed_time": "0:14:06", "remaining_time": "0:15:26"}
|
||||
{"current_steps": 297, "total_steps": 620, "loss": 0.0351, "lr": 6.225991114739622e-06, "epoch": 0.9553679131483716, "percentage": 47.9, "elapsed_time": "0:14:08", "remaining_time": "0:15:22"}
|
||||
{"current_steps": 298, "total_steps": 620, "loss": 0.0458, "lr": 6.1986807068678926e-06, "epoch": 0.9585846401286691, "percentage": 48.06, "elapsed_time": "0:14:10", "remaining_time": "0:15:19"}
|
||||
{"current_steps": 299, "total_steps": 620, "loss": 0.0349, "lr": 6.171332303360411e-06, "epoch": 0.9618013671089666, "percentage": 48.23, "elapsed_time": "0:14:13", "remaining_time": "0:15:16"}
|
||||
{"current_steps": 300, "total_steps": 620, "loss": 0.0553, "lr": 6.143946771103561e-06, "epoch": 0.9650180940892642, "percentage": 48.39, "elapsed_time": "0:14:17", "remaining_time": "0:15:14"}
|
||||
{"current_steps": 301, "total_steps": 620, "loss": 0.0372, "lr": 6.11652497816062e-06, "epoch": 0.9682348210695617, "percentage": 48.55, "elapsed_time": "0:14:19", "remaining_time": "0:15:11"}
|
||||
{"current_steps": 302, "total_steps": 620, "loss": 0.0386, "lr": 6.089067793744258e-06, "epoch": 0.9714515480498592, "percentage": 48.71, "elapsed_time": "0:14:22", "remaining_time": "0:15:07"}
|
||||
{"current_steps": 303, "total_steps": 620, "loss": 0.0407, "lr": 6.061576088188981e-06, "epoch": 0.9746682750301568, "percentage": 48.87, "elapsed_time": "0:14:24", "remaining_time": "0:15:04"}
|
||||
{"current_steps": 304, "total_steps": 620, "loss": 0.0405, "lr": 6.034050732923538e-06, "epoch": 0.9778850020104544, "percentage": 49.03, "elapsed_time": "0:14:27", "remaining_time": "0:15:01"}
|
||||
{"current_steps": 305, "total_steps": 620, "loss": 0.0456, "lr": 6.006492600443301e-06, "epoch": 0.9811017289907519, "percentage": 49.19, "elapsed_time": "0:14:29", "remaining_time": "0:14:58"}
|
||||
{"current_steps": 306, "total_steps": 620, "loss": 0.0476, "lr": 5.978902564282616e-06, "epoch": 0.9843184559710495, "percentage": 49.35, "elapsed_time": "0:14:32", "remaining_time": "0:14:55"}
|
||||
{"current_steps": 307, "total_steps": 620, "loss": 0.0431, "lr": 5.951281498987106e-06, "epoch": 0.987535182951347, "percentage": 49.52, "elapsed_time": "0:14:34", "remaining_time": "0:14:51"}
|
||||
{"current_steps": 308, "total_steps": 620, "loss": 0.0416, "lr": 5.923630280085948e-06, "epoch": 0.9907519099316445, "percentage": 49.68, "elapsed_time": "0:14:37", "remaining_time": "0:14:48"}
|
||||
{"current_steps": 309, "total_steps": 620, "loss": 0.0316, "lr": 5.895949784064126e-06, "epoch": 0.9939686369119421, "percentage": 49.84, "elapsed_time": "0:14:39", "remaining_time": "0:14:45"}
|
||||
{"current_steps": 310, "total_steps": 620, "loss": 0.0393, "lr": 5.8682408883346535e-06, "epoch": 0.9971853638922397, "percentage": 50.0, "elapsed_time": "0:14:42", "remaining_time": "0:14:42"}
|
||||
{"current_steps": 311, "total_steps": 620, "loss": 0.0507, "lr": 5.840504471210742e-06, "epoch": 1.0, "percentage": 50.16, "elapsed_time": "0:14:44", "remaining_time": "0:14:38"}
|
||||
{"current_steps": 312, "total_steps": 620, "loss": 0.0331, "lr": 5.8127414118779825e-06, "epoch": 1.0032167269802976, "percentage": 50.32, "elapsed_time": "0:14:47", "remaining_time": "0:14:36"}
|
||||
{"current_steps": 313, "total_steps": 620, "loss": 0.0234, "lr": 5.7849525903664636e-06, "epoch": 1.006433453960595, "percentage": 50.48, "elapsed_time": "0:14:50", "remaining_time": "0:14:33"}
|
||||
{"current_steps": 314, "total_steps": 620, "loss": 0.0244, "lr": 5.757138887522884e-06, "epoch": 1.0096501809408926, "percentage": 50.65, "elapsed_time": "0:14:52", "remaining_time": "0:14:30"}
|
||||
{"current_steps": 315, "total_steps": 620, "loss": 0.0334, "lr": 5.729301184982622e-06, "epoch": 1.0128669079211903, "percentage": 50.81, "elapsed_time": "0:14:55", "remaining_time": "0:14:26"}
|
||||
{"current_steps": 316, "total_steps": 620, "loss": 0.0301, "lr": 5.701440365141799e-06, "epoch": 1.0160836349014877, "percentage": 50.97, "elapsed_time": "0:14:57", "remaining_time": "0:14:23"}
|
||||
{"current_steps": 317, "total_steps": 620, "loss": 0.0322, "lr": 5.673557311129306e-06, "epoch": 1.0193003618817853, "percentage": 51.13, "elapsed_time": "0:15:00", "remaining_time": "0:14:20"}
|
||||
{"current_steps": 318, "total_steps": 620, "loss": 0.0304, "lr": 5.645652906778808e-06, "epoch": 1.022517088862083, "percentage": 51.29, "elapsed_time": "0:15:02", "remaining_time": "0:14:17"}
|
||||
{"current_steps": 319, "total_steps": 620, "loss": 0.0219, "lr": 5.617728036600734e-06, "epoch": 1.0257338158423803, "percentage": 51.45, "elapsed_time": "0:15:05", "remaining_time": "0:14:14"}
|
||||
{"current_steps": 320, "total_steps": 620, "loss": 0.0271, "lr": 5.5897835857542315e-06, "epoch": 1.028950542822678, "percentage": 51.61, "elapsed_time": "0:15:07", "remaining_time": "0:14:10"}
|
||||
{"current_steps": 321, "total_steps": 620, "loss": 0.0281, "lr": 5.561820440019117e-06, "epoch": 1.0321672698029756, "percentage": 51.77, "elapsed_time": "0:15:10", "remaining_time": "0:14:07"}
|
||||
{"current_steps": 322, "total_steps": 620, "loss": 0.0181, "lr": 5.533839485767795e-06, "epoch": 1.035383996783273, "percentage": 51.94, "elapsed_time": "0:15:12", "remaining_time": "0:14:04"}
|
||||
{"current_steps": 323, "total_steps": 620, "loss": 0.0261, "lr": 5.505841609937162e-06, "epoch": 1.0386007237635706, "percentage": 52.1, "elapsed_time": "0:15:14", "remaining_time": "0:14:01"}
|
||||
{"current_steps": 324, "total_steps": 620, "loss": 0.0168, "lr": 5.477827700000492e-06, "epoch": 1.041817450743868, "percentage": 52.26, "elapsed_time": "0:15:17", "remaining_time": "0:13:58"}
|
||||
{"current_steps": 325, "total_steps": 620, "loss": 0.0294, "lr": 5.449798643939305e-06, "epoch": 1.0450341777241656, "percentage": 52.42, "elapsed_time": "0:15:19", "remaining_time": "0:13:54"}
|
||||
{"current_steps": 326, "total_steps": 620, "loss": 0.0233, "lr": 5.421755330215223e-06, "epoch": 1.0482509047044632, "percentage": 52.58, "elapsed_time": "0:15:22", "remaining_time": "0:13:51"}
|
||||
{"current_steps": 327, "total_steps": 620, "loss": 0.031, "lr": 5.39369864774181e-06, "epoch": 1.0514676316847607, "percentage": 52.74, "elapsed_time": "0:15:25", "remaining_time": "0:13:49"}
|
||||
{"current_steps": 328, "total_steps": 620, "loss": 0.017, "lr": 5.365629485856381e-06, "epoch": 1.0546843586650583, "percentage": 52.9, "elapsed_time": "0:15:27", "remaining_time": "0:13:46"}
|
||||
{"current_steps": 329, "total_steps": 620, "loss": 0.0372, "lr": 5.337548734291827e-06, "epoch": 1.057901085645356, "percentage": 53.06, "elapsed_time": "0:15:30", "remaining_time": "0:13:43"}
|
||||
{"current_steps": 330, "total_steps": 620, "loss": 0.0213, "lr": 5.30945728314841e-06, "epoch": 1.0611178126256533, "percentage": 53.23, "elapsed_time": "0:15:32", "remaining_time": "0:13:39"}
|
||||
{"current_steps": 331, "total_steps": 620, "loss": 0.0262, "lr": 5.281356022865542e-06, "epoch": 1.064334539605951, "percentage": 53.39, "elapsed_time": "0:15:35", "remaining_time": "0:13:36"}
|
||||
{"current_steps": 332, "total_steps": 620, "loss": 0.0212, "lr": 5.253245844193564e-06, "epoch": 1.0675512665862485, "percentage": 53.55, "elapsed_time": "0:15:38", "remaining_time": "0:13:33"}
|
||||
{"current_steps": 333, "total_steps": 620, "loss": 0.0164, "lr": 5.225127638165514e-06, "epoch": 1.070767993566546, "percentage": 53.71, "elapsed_time": "0:15:40", "remaining_time": "0:13:30"}
|
||||
{"current_steps": 334, "total_steps": 620, "loss": 0.024, "lr": 5.197002296068878e-06, "epoch": 1.0739847205468436, "percentage": 53.87, "elapsed_time": "0:15:43", "remaining_time": "0:13:27"}
|
||||
{"current_steps": 335, "total_steps": 620, "loss": 0.0203, "lr": 5.168870709417342e-06, "epoch": 1.0772014475271412, "percentage": 54.03, "elapsed_time": "0:15:45", "remaining_time": "0:13:24"}
|
||||
{"current_steps": 336, "total_steps": 620, "loss": 0.021, "lr": 5.140733769922525e-06, "epoch": 1.0804181745074386, "percentage": 54.19, "elapsed_time": "0:15:48", "remaining_time": "0:13:21"}
|
||||
{"current_steps": 337, "total_steps": 620, "loss": 0.0372, "lr": 5.112592369465731e-06, "epoch": 1.0836349014877362, "percentage": 54.35, "elapsed_time": "0:15:51", "remaining_time": "0:13:18"}
|
||||
{"current_steps": 338, "total_steps": 620, "loss": 0.02, "lr": 5.084447400069656e-06, "epoch": 1.0868516284680338, "percentage": 54.52, "elapsed_time": "0:15:55", "remaining_time": "0:13:17"}
|
||||
{"current_steps": 339, "total_steps": 620, "loss": 0.0207, "lr": 5.0562997538701295e-06, "epoch": 1.0900683554483312, "percentage": 54.68, "elapsed_time": "0:15:58", "remaining_time": "0:13:14"}
|
||||
{"current_steps": 340, "total_steps": 620, "loss": 0.0234, "lr": 5.0281503230878304e-06, "epoch": 1.0932850824286289, "percentage": 54.84, "elapsed_time": "0:16:00", "remaining_time": "0:13:11"}
|
||||
{"current_steps": 341, "total_steps": 620, "loss": 0.02, "lr": 5e-06, "epoch": 1.0965018094089265, "percentage": 55.0, "elapsed_time": "0:16:03", "remaining_time": "0:13:08"}
|
||||
{"current_steps": 342, "total_steps": 620, "loss": 0.0243, "lr": 4.971849676912172e-06, "epoch": 1.099718536389224, "percentage": 55.16, "elapsed_time": "0:16:06", "remaining_time": "0:13:05"}
|
||||
{"current_steps": 343, "total_steps": 620, "loss": 0.0297, "lr": 4.943700246129871e-06, "epoch": 1.1029352633695215, "percentage": 55.32, "elapsed_time": "0:16:09", "remaining_time": "0:13:02"}
|
||||
{"current_steps": 344, "total_steps": 620, "loss": 0.0204, "lr": 4.915552599930345e-06, "epoch": 1.1061519903498191, "percentage": 55.48, "elapsed_time": "0:16:11", "remaining_time": "0:12:59"}
|
||||
{"current_steps": 345, "total_steps": 620, "loss": 0.0306, "lr": 4.887407630534271e-06, "epoch": 1.1093687173301165, "percentage": 55.65, "elapsed_time": "0:16:14", "remaining_time": "0:12:57"}
|
||||
{"current_steps": 346, "total_steps": 620, "loss": 0.0299, "lr": 4.859266230077474e-06, "epoch": 1.1125854443104142, "percentage": 55.81, "elapsed_time": "0:16:17", "remaining_time": "0:12:54"}
|
||||
{"current_steps": 347, "total_steps": 620, "loss": 0.0231, "lr": 4.83112929058266e-06, "epoch": 1.1158021712907118, "percentage": 55.97, "elapsed_time": "0:16:20", "remaining_time": "0:12:51"}
|
||||
{"current_steps": 348, "total_steps": 620, "loss": 0.0277, "lr": 4.802997703931124e-06, "epoch": 1.1190188982710092, "percentage": 56.13, "elapsed_time": "0:16:23", "remaining_time": "0:12:48"}
|
||||
{"current_steps": 349, "total_steps": 620, "loss": 0.0261, "lr": 4.7748723618344865e-06, "epoch": 1.1222356252513068, "percentage": 56.29, "elapsed_time": "0:16:25", "remaining_time": "0:12:45"}
|
||||
{"current_steps": 350, "total_steps": 620, "loss": 0.0213, "lr": 4.746754155806437e-06, "epoch": 1.1254523522316044, "percentage": 56.45, "elapsed_time": "0:16:28", "remaining_time": "0:12:42"}
|
||||
{"current_steps": 351, "total_steps": 620, "loss": 0.0238, "lr": 4.71864397713446e-06, "epoch": 1.1286690792119018, "percentage": 56.61, "elapsed_time": "0:16:30", "remaining_time": "0:12:39"}
|
||||
{"current_steps": 352, "total_steps": 620, "loss": 0.0303, "lr": 4.6905427168515914e-06, "epoch": 1.1318858061921995, "percentage": 56.77, "elapsed_time": "0:16:33", "remaining_time": "0:12:36"}
|
||||
{"current_steps": 353, "total_steps": 620, "loss": 0.0188, "lr": 4.662451265708174e-06, "epoch": 1.135102533172497, "percentage": 56.94, "elapsed_time": "0:16:35", "remaining_time": "0:12:33"}
|
||||
{"current_steps": 354, "total_steps": 620, "loss": 0.0305, "lr": 4.63437051414362e-06, "epoch": 1.1383192601527945, "percentage": 57.1, "elapsed_time": "0:16:38", "remaining_time": "0:12:30"}
|
||||
{"current_steps": 355, "total_steps": 620, "loss": 0.0186, "lr": 4.606301352258192e-06, "epoch": 1.1415359871330921, "percentage": 57.26, "elapsed_time": "0:16:40", "remaining_time": "0:12:27"}
|
||||
{"current_steps": 356, "total_steps": 620, "loss": 0.0193, "lr": 4.5782446697847775e-06, "epoch": 1.1447527141133897, "percentage": 57.42, "elapsed_time": "0:16:43", "remaining_time": "0:12:24"}
|
||||
{"current_steps": 357, "total_steps": 620, "loss": 0.0274, "lr": 4.550201356060695e-06, "epoch": 1.1479694410936871, "percentage": 57.58, "elapsed_time": "0:16:45", "remaining_time": "0:12:21"}
|
||||
{"current_steps": 358, "total_steps": 620, "loss": 0.0256, "lr": 4.52217229999951e-06, "epoch": 1.1511861680739848, "percentage": 57.74, "elapsed_time": "0:16:48", "remaining_time": "0:12:18"}
|
||||
{"current_steps": 359, "total_steps": 620, "loss": 0.0265, "lr": 4.49415839006284e-06, "epoch": 1.1544028950542822, "percentage": 57.9, "elapsed_time": "0:16:51", "remaining_time": "0:12:15"}
|
||||
{"current_steps": 360, "total_steps": 620, "loss": 0.0341, "lr": 4.466160514232206e-06, "epoch": 1.1576196220345798, "percentage": 58.06, "elapsed_time": "0:16:53", "remaining_time": "0:12:12"}
|
||||
{"current_steps": 361, "total_steps": 620, "loss": 0.0163, "lr": 4.438179559980885e-06, "epoch": 1.1608363490148774, "percentage": 58.23, "elapsed_time": "0:16:56", "remaining_time": "0:12:09"}
|
||||
{"current_steps": 362, "total_steps": 620, "loss": 0.0357, "lr": 4.410216414245771e-06, "epoch": 1.1640530759951748, "percentage": 58.39, "elapsed_time": "0:16:58", "remaining_time": "0:12:06"}
|
||||
{"current_steps": 363, "total_steps": 620, "loss": 0.0161, "lr": 4.382271963399268e-06, "epoch": 1.1672698029754724, "percentage": 58.55, "elapsed_time": "0:17:01", "remaining_time": "0:12:03"}
|
||||
{"current_steps": 364, "total_steps": 620, "loss": 0.0206, "lr": 4.354347093221194e-06, "epoch": 1.17048652995577, "percentage": 58.71, "elapsed_time": "0:17:04", "remaining_time": "0:12:00"}
|
||||
{"current_steps": 365, "total_steps": 620, "loss": 0.0207, "lr": 4.326442688870697e-06, "epoch": 1.1737032569360675, "percentage": 58.87, "elapsed_time": "0:17:06", "remaining_time": "0:11:57"}
|
||||
{"current_steps": 366, "total_steps": 620, "loss": 0.0288, "lr": 4.298559634858202e-06, "epoch": 1.176919983916365, "percentage": 59.03, "elapsed_time": "0:17:09", "remaining_time": "0:11:54"}
|
||||
{"current_steps": 367, "total_steps": 620, "loss": 0.0279, "lr": 4.270698815017379e-06, "epoch": 1.1801367108966627, "percentage": 59.19, "elapsed_time": "0:17:12", "remaining_time": "0:11:52"}
|
||||
{"current_steps": 368, "total_steps": 620, "loss": 0.0144, "lr": 4.2428611124771184e-06, "epoch": 1.1833534378769601, "percentage": 59.35, "elapsed_time": "0:17:15", "remaining_time": "0:11:49"}
|
||||
{"current_steps": 369, "total_steps": 620, "loss": 0.023, "lr": 4.2150474096335356e-06, "epoch": 1.1865701648572577, "percentage": 59.52, "elapsed_time": "0:17:18", "remaining_time": "0:11:46"}
|
||||
{"current_steps": 370, "total_steps": 620, "loss": 0.0355, "lr": 4.187258588122019e-06, "epoch": 1.1897868918375554, "percentage": 59.68, "elapsed_time": "0:17:20", "remaining_time": "0:11:43"}
|
||||
{"current_steps": 371, "total_steps": 620, "loss": 0.0165, "lr": 4.15949552878926e-06, "epoch": 1.1930036188178528, "percentage": 59.84, "elapsed_time": "0:17:22", "remaining_time": "0:11:39"}
|
||||
{"current_steps": 372, "total_steps": 620, "loss": 0.0323, "lr": 4.131759111665349e-06, "epoch": 1.1962203457981504, "percentage": 60.0, "elapsed_time": "0:17:25", "remaining_time": "0:11:36"}
|
||||
{"current_steps": 373, "total_steps": 620, "loss": 0.0306, "lr": 4.104050215935875e-06, "epoch": 1.199437072778448, "percentage": 60.16, "elapsed_time": "0:17:27", "remaining_time": "0:11:33"}
|
||||
{"current_steps": 374, "total_steps": 620, "loss": 0.0252, "lr": 4.076369719914055e-06, "epoch": 1.2026537997587454, "percentage": 60.32, "elapsed_time": "0:17:31", "remaining_time": "0:11:31"}
|
||||
{"current_steps": 375, "total_steps": 620, "loss": 0.0168, "lr": 4.048718501012895e-06, "epoch": 1.205870526739043, "percentage": 60.48, "elapsed_time": "0:17:33", "remaining_time": "0:11:28"}
|
||||
{"current_steps": 376, "total_steps": 620, "loss": 0.0297, "lr": 4.021097435717386e-06, "epoch": 1.2090872537193404, "percentage": 60.65, "elapsed_time": "0:17:35", "remaining_time": "0:11:25"}
|
||||
{"current_steps": 377, "total_steps": 620, "loss": 0.0189, "lr": 3.993507399556699e-06, "epoch": 1.212303980699638, "percentage": 60.81, "elapsed_time": "0:17:38", "remaining_time": "0:11:22"}
|
||||
{"current_steps": 378, "total_steps": 620, "loss": 0.0175, "lr": 3.965949267076465e-06, "epoch": 1.2155207076799357, "percentage": 60.97, "elapsed_time": "0:17:41", "remaining_time": "0:11:19"}
|
||||
{"current_steps": 379, "total_steps": 620, "loss": 0.0215, "lr": 3.938423911811021e-06, "epoch": 1.218737434660233, "percentage": 61.13, "elapsed_time": "0:17:43", "remaining_time": "0:11:16"}
|
||||
{"current_steps": 380, "total_steps": 620, "loss": 0.0304, "lr": 3.910932206255742e-06, "epoch": 1.2219541616405307, "percentage": 61.29, "elapsed_time": "0:17:46", "remaining_time": "0:11:13"}
|
||||
{"current_steps": 381, "total_steps": 620, "loss": 0.0269, "lr": 3.883475021839382e-06, "epoch": 1.2251708886208283, "percentage": 61.45, "elapsed_time": "0:17:48", "remaining_time": "0:11:10"}
|
||||
{"current_steps": 382, "total_steps": 620, "loss": 0.0253, "lr": 3.856053228896442e-06, "epoch": 1.2283876156011257, "percentage": 61.61, "elapsed_time": "0:17:51", "remaining_time": "0:11:07"}
|
||||
{"current_steps": 383, "total_steps": 620, "loss": 0.0286, "lr": 3.8286676966395895e-06, "epoch": 1.2316043425814234, "percentage": 61.77, "elapsed_time": "0:17:54", "remaining_time": "0:11:04"}
|
||||
{"current_steps": 384, "total_steps": 620, "loss": 0.0161, "lr": 3.8013192931321095e-06, "epoch": 1.234821069561721, "percentage": 61.94, "elapsed_time": "0:17:56", "remaining_time": "0:11:01"}
|
||||
{"current_steps": 385, "total_steps": 620, "loss": 0.0382, "lr": 3.77400888526038e-06, "epoch": 1.2380377965420184, "percentage": 62.1, "elapsed_time": "0:17:59", "remaining_time": "0:10:58"}
|
||||
{"current_steps": 386, "total_steps": 620, "loss": 0.027, "lr": 3.7467373387063973e-06, "epoch": 1.241254523522316, "percentage": 62.26, "elapsed_time": "0:18:01", "remaining_time": "0:10:55"}
|
||||
{"current_steps": 387, "total_steps": 620, "loss": 0.0283, "lr": 3.719505517920342e-06, "epoch": 1.2444712505026136, "percentage": 62.42, "elapsed_time": "0:18:04", "remaining_time": "0:10:52"}
|
||||
{"current_steps": 388, "total_steps": 620, "loss": 0.024, "lr": 3.692314286093167e-06, "epoch": 1.247687977482911, "percentage": 62.58, "elapsed_time": "0:18:07", "remaining_time": "0:10:50"}
|
||||
{"current_steps": 389, "total_steps": 620, "loss": 0.0226, "lr": 3.6651645051292415e-06, "epoch": 1.2509047044632087, "percentage": 62.74, "elapsed_time": "0:18:10", "remaining_time": "0:10:47"}
|
||||
{"current_steps": 390, "total_steps": 620, "loss": 0.0197, "lr": 3.6380570356190346e-06, "epoch": 1.2541214314435063, "percentage": 62.9, "elapsed_time": "0:18:14", "remaining_time": "0:10:45"}
|
||||
{"current_steps": 391, "total_steps": 620, "loss": 0.0188, "lr": 3.610992736811827e-06, "epoch": 1.2573381584238037, "percentage": 63.06, "elapsed_time": "0:18:17", "remaining_time": "0:10:42"}
|
||||
{"current_steps": 392, "total_steps": 620, "loss": 0.0193, "lr": 3.58397246658848e-06, "epoch": 1.2605548854041013, "percentage": 63.23, "elapsed_time": "0:18:19", "remaining_time": "0:10:39"}
|
||||
{"current_steps": 393, "total_steps": 620, "loss": 0.025, "lr": 3.556997081434248e-06, "epoch": 1.263771612384399, "percentage": 63.39, "elapsed_time": "0:18:21", "remaining_time": "0:10:36"}
|
||||
{"current_steps": 394, "total_steps": 620, "loss": 0.0237, "lr": 3.5300674364116173e-06, "epoch": 1.2669883393646963, "percentage": 63.55, "elapsed_time": "0:18:24", "remaining_time": "0:10:33"}
|
||||
{"current_steps": 395, "total_steps": 620, "loss": 0.0231, "lr": 3.5031843851332105e-06, "epoch": 1.270205066344994, "percentage": 63.71, "elapsed_time": "0:18:28", "remaining_time": "0:10:31"}
|
||||
{"current_steps": 396, "total_steps": 620, "loss": 0.0246, "lr": 3.476348779734732e-06, "epoch": 1.2734217933252916, "percentage": 63.87, "elapsed_time": "0:18:30", "remaining_time": "0:10:28"}
|
||||
{"current_steps": 397, "total_steps": 620, "loss": 0.0262, "lr": 3.449561470847947e-06, "epoch": 1.276638520305589, "percentage": 64.03, "elapsed_time": "0:18:33", "remaining_time": "0:10:25"}
|
||||
{"current_steps": 398, "total_steps": 620, "loss": 0.0294, "lr": 3.4228233075737225e-06, "epoch": 1.2798552472858866, "percentage": 64.19, "elapsed_time": "0:18:35", "remaining_time": "0:10:22"}
|
||||
{"current_steps": 399, "total_steps": 620, "loss": 0.0279, "lr": 3.3961351374551234e-06, "epoch": 1.2830719742661842, "percentage": 64.35, "elapsed_time": "0:18:38", "remaining_time": "0:10:19"}
|
||||
{"current_steps": 400, "total_steps": 620, "loss": 0.0104, "lr": 3.3694978064505258e-06, "epoch": 1.2862887012464816, "percentage": 64.52, "elapsed_time": "0:18:40", "remaining_time": "0:10:16"}
|
||||
{"current_steps": 401, "total_steps": 620, "loss": 0.023, "lr": 3.3429121589068213e-06, "epoch": 1.2895054282267793, "percentage": 64.68, "elapsed_time": "0:18:42", "remaining_time": "0:10:13"}
|
||||
{"current_steps": 402, "total_steps": 620, "loss": 0.0238, "lr": 3.316379037532644e-06, "epoch": 1.292722155207077, "percentage": 64.84, "elapsed_time": "0:18:45", "remaining_time": "0:10:10"}
|
||||
{"current_steps": 403, "total_steps": 620, "loss": 0.0233, "lr": 3.289899283371657e-06, "epoch": 1.2959388821873743, "percentage": 65.0, "elapsed_time": "0:18:48", "remaining_time": "0:10:07"}
|
||||
{"current_steps": 404, "total_steps": 620, "loss": 0.0247, "lr": 3.2634737357758994e-06, "epoch": 1.299155609167672, "percentage": 65.16, "elapsed_time": "0:18:50", "remaining_time": "0:10:04"}
|
||||
{"current_steps": 405, "total_steps": 620, "loss": 0.0209, "lr": 3.2371032323791757e-06, "epoch": 1.3023723361479695, "percentage": 65.32, "elapsed_time": "0:18:52", "remaining_time": "0:10:01"}
|
||||
{"current_steps": 406, "total_steps": 620, "loss": 0.0188, "lr": 3.2107886090705035e-06, "epoch": 1.305589063128267, "percentage": 65.48, "elapsed_time": "0:18:56", "remaining_time": "0:09:58"}
|
||||
{"current_steps": 407, "total_steps": 620, "loss": 0.0328, "lr": 3.1845306999676274e-06, "epoch": 1.3088057901085646, "percentage": 65.65, "elapsed_time": "0:18:58", "remaining_time": "0:09:55"}
|
||||
{"current_steps": 408, "total_steps": 620, "loss": 0.0263, "lr": 3.158330337390565e-06, "epoch": 1.3120225170888622, "percentage": 65.81, "elapsed_time": "0:19:01", "remaining_time": "0:09:53"}
|
||||
{"current_steps": 409, "total_steps": 620, "loss": 0.0316, "lr": 3.132188351835232e-06, "epoch": 1.3152392440691596, "percentage": 65.97, "elapsed_time": "0:19:03", "remaining_time": "0:09:50"}
|
||||
{"current_steps": 410, "total_steps": 620, "loss": 0.0229, "lr": 3.10610557194712e-06, "epoch": 1.3184559710494572, "percentage": 66.13, "elapsed_time": "0:19:06", "remaining_time": "0:09:47"}
|
||||
{"current_steps": 411, "total_steps": 620, "loss": 0.0276, "lr": 3.080082824495024e-06, "epoch": 1.3216726980297548, "percentage": 66.29, "elapsed_time": "0:19:09", "remaining_time": "0:09:44"}
|
||||
{"current_steps": 412, "total_steps": 620, "loss": 0.0228, "lr": 3.0541209343448373e-06, "epoch": 1.3248894250100522, "percentage": 66.45, "elapsed_time": "0:19:12", "remaining_time": "0:09:41"}
|
||||
{"current_steps": 413, "total_steps": 620, "loss": 0.0211, "lr": 3.0282207244334084e-06, "epoch": 1.3281061519903499, "percentage": 66.61, "elapsed_time": "0:19:15", "remaining_time": "0:09:38"}
|
||||
{"current_steps": 414, "total_steps": 620, "loss": 0.0269, "lr": 3.0023830157424504e-06, "epoch": 1.3313228789706475, "percentage": 66.77, "elapsed_time": "0:19:17", "remaining_time": "0:09:36"}
|
||||
{"current_steps": 415, "total_steps": 620, "loss": 0.0226, "lr": 2.97660862727252e-06, "epoch": 1.334539605950945, "percentage": 66.94, "elapsed_time": "0:19:20", "remaining_time": "0:09:33"}
|
||||
{"current_steps": 416, "total_steps": 620, "loss": 0.0226, "lr": 2.950898376017064e-06, "epoch": 1.3377563329312425, "percentage": 67.1, "elapsed_time": "0:19:24", "remaining_time": "0:09:30"}
|
||||
{"current_steps": 417, "total_steps": 620, "loss": 0.0177, "lr": 2.9252530769365053e-06, "epoch": 1.3409730599115401, "percentage": 67.26, "elapsed_time": "0:19:26", "remaining_time": "0:09:28"}
|
||||
{"current_steps": 418, "total_steps": 620, "loss": 0.0208, "lr": 2.8996735429324256e-06, "epoch": 1.3441897868918375, "percentage": 67.42, "elapsed_time": "0:19:29", "remaining_time": "0:09:25"}
|
||||
{"current_steps": 419, "total_steps": 620, "loss": 0.0204, "lr": 2.874160584821798e-06, "epoch": 1.3474065138721352, "percentage": 67.58, "elapsed_time": "0:19:32", "remaining_time": "0:09:22"}
|
||||
{"current_steps": 420, "total_steps": 620, "loss": 0.0179, "lr": 2.848715011311271e-06, "epoch": 1.3506232408524326, "percentage": 67.74, "elapsed_time": "0:19:34", "remaining_time": "0:09:19"}
|
||||
{"current_steps": 421, "total_steps": 620, "loss": 0.0176, "lr": 2.823337628971551e-06, "epoch": 1.3538399678327302, "percentage": 67.9, "elapsed_time": "0:19:37", "remaining_time": "0:09:16"}
|
||||
{"current_steps": 422, "total_steps": 620, "loss": 0.0264, "lr": 2.7980292422118282e-06, "epoch": 1.3570566948130278, "percentage": 68.06, "elapsed_time": "0:19:39", "remaining_time": "0:09:13"}
|
||||
{"current_steps": 423, "total_steps": 620, "loss": 0.021, "lr": 2.7727906532542783e-06, "epoch": 1.3602734217933252, "percentage": 68.23, "elapsed_time": "0:19:41", "remaining_time": "0:09:10"}
|
||||
{"current_steps": 424, "total_steps": 620, "loss": 0.0209, "lr": 2.7476226621086354e-06, "epoch": 1.3634901487736228, "percentage": 68.39, "elapsed_time": "0:19:44", "remaining_time": "0:09:07"}
|
||||
{"current_steps": 425, "total_steps": 620, "loss": 0.0209, "lr": 2.72252606654683e-06, "epoch": 1.3667068757539202, "percentage": 68.55, "elapsed_time": "0:19:46", "remaining_time": "0:09:04"}
|
||||
{"current_steps": 426, "total_steps": 620, "loss": 0.0299, "lr": 2.697501662077707e-06, "epoch": 1.3699236027342179, "percentage": 68.71, "elapsed_time": "0:19:49", "remaining_time": "0:09:01"}
|
||||
{"current_steps": 427, "total_steps": 620, "loss": 0.0346, "lr": 2.6725502419218084e-06, "epoch": 1.3731403297145155, "percentage": 68.87, "elapsed_time": "0:19:51", "remaining_time": "0:08:58"}
|
||||
{"current_steps": 428, "total_steps": 620, "loss": 0.0418, "lr": 2.6476725969862227e-06, "epoch": 1.376357056694813, "percentage": 69.03, "elapsed_time": "0:19:54", "remaining_time": "0:08:55"}
|
||||
{"current_steps": 429, "total_steps": 620, "loss": 0.0179, "lr": 2.622869515839524e-06, "epoch": 1.3795737836751105, "percentage": 69.19, "elapsed_time": "0:19:56", "remaining_time": "0:08:52"}
|
||||
{"current_steps": 430, "total_steps": 620, "loss": 0.0242, "lr": 2.5981417846867753e-06, "epoch": 1.3827905106554081, "percentage": 69.35, "elapsed_time": "0:19:58", "remaining_time": "0:08:49"}
|
||||
{"current_steps": 431, "total_steps": 620, "loss": 0.0137, "lr": 2.573490187344596e-06, "epoch": 1.3860072376357055, "percentage": 69.52, "elapsed_time": "0:20:01", "remaining_time": "0:08:46"}
|
||||
{"current_steps": 432, "total_steps": 620, "loss": 0.0287, "lr": 2.548915505216333e-06, "epoch": 1.3892239646160032, "percentage": 69.68, "elapsed_time": "0:20:03", "remaining_time": "0:08:43"}
|
||||
{"current_steps": 433, "total_steps": 620, "loss": 0.0251, "lr": 2.524418517267283e-06, "epoch": 1.3924406915963008, "percentage": 69.84, "elapsed_time": "0:20:06", "remaining_time": "0:08:41"}
|
||||
{"current_steps": 434, "total_steps": 620, "loss": 0.0297, "lr": 2.5000000000000015e-06, "epoch": 1.3956574185765982, "percentage": 70.0, "elapsed_time": "0:20:09", "remaining_time": "0:08:38"}
|
||||
{"current_steps": 435, "total_steps": 620, "loss": 0.0236, "lr": 2.4756607274296844e-06, "epoch": 1.3988741455568958, "percentage": 70.16, "elapsed_time": "0:20:11", "remaining_time": "0:08:35"}
|
||||
{"current_steps": 436, "total_steps": 620, "loss": 0.0205, "lr": 2.4514014710596467e-06, "epoch": 1.4020908725371934, "percentage": 70.32, "elapsed_time": "0:20:14", "remaining_time": "0:08:32"}
|
||||
{"current_steps": 437, "total_steps": 620, "loss": 0.0367, "lr": 2.4272229998568576e-06, "epoch": 1.4053075995174908, "percentage": 70.48, "elapsed_time": "0:20:16", "remaining_time": "0:08:29"}
|
||||
{"current_steps": 438, "total_steps": 620, "loss": 0.0271, "lr": 2.4031260802275623e-06, "epoch": 1.4085243264977885, "percentage": 70.65, "elapsed_time": "0:20:19", "remaining_time": "0:08:26"}
|
||||
{"current_steps": 439, "total_steps": 620, "loss": 0.0188, "lr": 2.3791114759930013e-06, "epoch": 1.411741053478086, "percentage": 70.81, "elapsed_time": "0:20:21", "remaining_time": "0:08:23"}
|
||||
{"current_steps": 440, "total_steps": 620, "loss": 0.0264, "lr": 2.3551799483651894e-06, "epoch": 1.4149577804583835, "percentage": 70.97, "elapsed_time": "0:20:23", "remaining_time": "0:08:20"}
|
||||
{"current_steps": 441, "total_steps": 620, "loss": 0.0184, "lr": 2.331332255922784e-06, "epoch": 1.4181745074386811, "percentage": 71.13, "elapsed_time": "0:20:26", "remaining_time": "0:08:17"}
|
||||
{"current_steps": 442, "total_steps": 620, "loss": 0.0184, "lr": 2.307569154587056e-06, "epoch": 1.4213912344189787, "percentage": 71.29, "elapsed_time": "0:20:29", "remaining_time": "0:08:14"}
|
||||
{"current_steps": 443, "total_steps": 620, "loss": 0.0206, "lr": 2.283891397597908e-06, "epoch": 1.4246079613992761, "percentage": 71.45, "elapsed_time": "0:20:31", "remaining_time": "0:08:12"}
|
||||
{"current_steps": 444, "total_steps": 620, "loss": 0.031, "lr": 2.2602997354900075e-06, "epoch": 1.4278246883795738, "percentage": 71.61, "elapsed_time": "0:20:34", "remaining_time": "0:08:09"}
|
||||
{"current_steps": 445, "total_steps": 620, "loss": 0.0171, "lr": 2.236794916069007e-06, "epoch": 1.4310414153598714, "percentage": 71.77, "elapsed_time": "0:20:37", "remaining_time": "0:08:06"}
|
||||
{"current_steps": 446, "total_steps": 620, "loss": 0.0191, "lr": 2.2133776843878185e-06, "epoch": 1.4342581423401688, "percentage": 71.94, "elapsed_time": "0:20:40", "remaining_time": "0:08:03"}
|
||||
{"current_steps": 447, "total_steps": 620, "loss": 0.0225, "lr": 2.190048782723015e-06, "epoch": 1.4374748693204664, "percentage": 72.1, "elapsed_time": "0:20:42", "remaining_time": "0:08:00"}
|
||||
{"current_steps": 448, "total_steps": 620, "loss": 0.0256, "lr": 2.166808950551296e-06, "epoch": 1.440691596300764, "percentage": 72.26, "elapsed_time": "0:20:45", "remaining_time": "0:07:58"}
|
||||
{"current_steps": 449, "total_steps": 620, "loss": 0.0236, "lr": 2.1436589245260375e-06, "epoch": 1.4439083232810614, "percentage": 72.42, "elapsed_time": "0:20:47", "remaining_time": "0:07:55"}
|
||||
{"current_steps": 450, "total_steps": 620, "loss": 0.0241, "lr": 2.120599438453968e-06, "epoch": 1.447125050261359, "percentage": 72.58, "elapsed_time": "0:20:49", "remaining_time": "0:07:52"}
|
||||
{"current_steps": 451, "total_steps": 620, "loss": 0.0282, "lr": 2.0976312232718763e-06, "epoch": 1.4503417772416567, "percentage": 72.74, "elapsed_time": "0:20:53", "remaining_time": "0:07:49"}
|
||||
{"current_steps": 452, "total_steps": 620, "loss": 0.0278, "lr": 2.074755007023461e-06, "epoch": 1.453558504221954, "percentage": 72.9, "elapsed_time": "0:20:56", "remaining_time": "0:07:46"}
|
||||
{"current_steps": 453, "total_steps": 620, "loss": 0.0176, "lr": 2.0519715148362585e-06, "epoch": 1.4567752312022517, "percentage": 73.06, "elapsed_time": "0:20:58", "remaining_time": "0:07:43"}
|
||||
{"current_steps": 454, "total_steps": 620, "loss": 0.0224, "lr": 2.0292814688986375e-06, "epoch": 1.4599919581825493, "percentage": 73.23, "elapsed_time": "0:21:01", "remaining_time": "0:07:41"}
|
||||
{"current_steps": 455, "total_steps": 620, "loss": 0.0312, "lr": 2.0066855884369246e-06, "epoch": 1.4632086851628467, "percentage": 73.39, "elapsed_time": "0:21:03", "remaining_time": "0:07:38"}
|
||||
{"current_steps": 456, "total_steps": 620, "loss": 0.0256, "lr": 1.9841845896926022e-06, "epoch": 1.4664254121431444, "percentage": 73.55, "elapsed_time": "0:21:06", "remaining_time": "0:07:35"}
|
||||
{"current_steps": 457, "total_steps": 620, "loss": 0.0224, "lr": 1.961779185899597e-06, "epoch": 1.469642139123442, "percentage": 73.71, "elapsed_time": "0:21:09", "remaining_time": "0:07:32"}
|
||||
{"current_steps": 458, "total_steps": 620, "loss": 0.0197, "lr": 1.9394700872616856e-06, "epoch": 1.4728588661037394, "percentage": 73.87, "elapsed_time": "0:21:11", "remaining_time": "0:07:29"}
|
||||
{"current_steps": 459, "total_steps": 620, "loss": 0.0164, "lr": 1.9172580009299735e-06, "epoch": 1.476075593084037, "percentage": 74.03, "elapsed_time": "0:21:14", "remaining_time": "0:07:27"}
|
||||
{"current_steps": 460, "total_steps": 620, "loss": 0.0344, "lr": 1.8951436309804766e-06, "epoch": 1.4792923200643346, "percentage": 74.19, "elapsed_time": "0:21:17", "remaining_time": "0:07:24"}
|
||||
{"current_steps": 461, "total_steps": 620, "loss": 0.0195, "lr": 1.8731276783918162e-06, "epoch": 1.482509047044632, "percentage": 74.35, "elapsed_time": "0:21:19", "remaining_time": "0:07:21"}
|
||||
{"current_steps": 462, "total_steps": 620, "loss": 0.0306, "lr": 1.8512108410229878e-06, "epoch": 1.4857257740249297, "percentage": 74.52, "elapsed_time": "0:21:22", "remaining_time": "0:07:18"}
|
||||
{"current_steps": 463, "total_steps": 620, "loss": 0.0217, "lr": 1.8293938135912475e-06, "epoch": 1.4889425010052273, "percentage": 74.68, "elapsed_time": "0:21:25", "remaining_time": "0:07:15"}
|
||||
{"current_steps": 464, "total_steps": 620, "loss": 0.0298, "lr": 1.8076772876500831e-06, "epoch": 1.4921592279855247, "percentage": 74.84, "elapsed_time": "0:21:27", "remaining_time": "0:07:12"}
|
||||
{"current_steps": 465, "total_steps": 620, "loss": 0.0316, "lr": 1.7860619515673034e-06, "epoch": 1.4953759549658223, "percentage": 75.0, "elapsed_time": "0:21:29", "remaining_time": "0:07:09"}
|
||||
{"current_steps": 466, "total_steps": 620, "loss": 0.0182, "lr": 1.7645484905032129e-06, "epoch": 1.49859268194612, "percentage": 75.16, "elapsed_time": "0:21:33", "remaining_time": "0:07:07"}
|
||||
{"current_steps": 467, "total_steps": 620, "loss": 0.025, "lr": 1.74313758638889e-06, "epoch": 1.5018094089264173, "percentage": 75.32, "elapsed_time": "0:21:35", "remaining_time": "0:07:04"}
|
||||
{"current_steps": 468, "total_steps": 620, "loss": 0.0256, "lr": 1.7218299179045789e-06, "epoch": 1.505026135906715, "percentage": 75.48, "elapsed_time": "0:21:38", "remaining_time": "0:07:01"}
|
||||
{"current_steps": 469, "total_steps": 620, "loss": 0.0144, "lr": 1.7006261604581725e-06, "epoch": 1.5082428628870126, "percentage": 75.65, "elapsed_time": "0:21:41", "remaining_time": "0:06:58"}
|
||||
{"current_steps": 470, "total_steps": 620, "loss": 0.0256, "lr": 1.6795269861638041e-06, "epoch": 1.51145958986731, "percentage": 75.81, "elapsed_time": "0:21:43", "remaining_time": "0:06:56"}
|
||||
{"current_steps": 471, "total_steps": 620, "loss": 0.0283, "lr": 1.6585330638205454e-06, "epoch": 1.5146763168476074, "percentage": 75.97, "elapsed_time": "0:21:46", "remaining_time": "0:06:53"}
|
||||
{"current_steps": 472, "total_steps": 620, "loss": 0.0223, "lr": 1.6376450588911985e-06, "epoch": 1.5178930438279052, "percentage": 76.13, "elapsed_time": "0:21:48", "remaining_time": "0:06:50"}
|
||||
{"current_steps": 473, "total_steps": 620, "loss": 0.0142, "lr": 1.6168636334812126e-06, "epoch": 1.5211097708082026, "percentage": 76.29, "elapsed_time": "0:21:51", "remaining_time": "0:06:47"}
|
||||
{"current_steps": 474, "total_steps": 620, "loss": 0.0258, "lr": 1.5961894463176942e-06, "epoch": 1.5243264977885, "percentage": 76.45, "elapsed_time": "0:21:54", "remaining_time": "0:06:44"}
|
||||
{"current_steps": 475, "total_steps": 620, "loss": 0.027, "lr": 1.5756231527285181e-06, "epoch": 1.527543224768798, "percentage": 76.61, "elapsed_time": "0:21:57", "remaining_time": "0:06:42"}
|
||||
{"current_steps": 476, "total_steps": 620, "loss": 0.0273, "lr": 1.555165404621567e-06, "epoch": 1.5307599517490953, "percentage": 76.77, "elapsed_time": "0:22:00", "remaining_time": "0:06:39"}
|
||||
{"current_steps": 477, "total_steps": 620, "loss": 0.0282, "lr": 1.5348168504640631e-06, "epoch": 1.5339766787293927, "percentage": 76.94, "elapsed_time": "0:22:02", "remaining_time": "0:06:36"}
|
||||
{"current_steps": 478, "total_steps": 620, "loss": 0.0273, "lr": 1.5145781352620054e-06, "epoch": 1.5371934057096905, "percentage": 77.1, "elapsed_time": "0:22:05", "remaining_time": "0:06:33"}
|
||||
{"current_steps": 479, "total_steps": 620, "loss": 0.0164, "lr": 1.4944499005397372e-06, "epoch": 1.540410132689988, "percentage": 77.26, "elapsed_time": "0:22:07", "remaining_time": "0:06:30"}
|
||||
{"current_steps": 480, "total_steps": 620, "loss": 0.0283, "lr": 1.4744327843196043e-06, "epoch": 1.5436268596702853, "percentage": 77.42, "elapsed_time": "0:22:10", "remaining_time": "0:06:27"}
|
||||
{"current_steps": 481, "total_steps": 620, "loss": 0.0278, "lr": 1.4545274211017264e-06, "epoch": 1.5468435866505832, "percentage": 77.58, "elapsed_time": "0:22:12", "remaining_time": "0:06:25"}
|
||||
{"current_steps": 482, "total_steps": 620, "loss": 0.0273, "lr": 1.434734441843899e-06, "epoch": 1.5500603136308806, "percentage": 77.74, "elapsed_time": "0:22:15", "remaining_time": "0:06:22"}
|
||||
{"current_steps": 483, "total_steps": 620, "loss": 0.0238, "lr": 1.4150544739415755e-06, "epoch": 1.553277040611178, "percentage": 77.9, "elapsed_time": "0:22:17", "remaining_time": "0:06:19"}
|
||||
{"current_steps": 484, "total_steps": 620, "loss": 0.0296, "lr": 1.3954881412079945e-06, "epoch": 1.5564937675914756, "percentage": 78.06, "elapsed_time": "0:22:19", "remaining_time": "0:06:16"}
|
||||
{"current_steps": 485, "total_steps": 620, "loss": 0.0258, "lr": 1.3760360638544012e-06, "epoch": 1.5597104945717732, "percentage": 78.23, "elapsed_time": "0:22:22", "remaining_time": "0:06:13"}
|
||||
{"current_steps": 486, "total_steps": 620, "loss": 0.0256, "lr": 1.3566988584703817e-06, "epoch": 1.5629272215520706, "percentage": 78.39, "elapsed_time": "0:22:24", "remaining_time": "0:06:10"}
|
||||
{"current_steps": 487, "total_steps": 620, "loss": 0.0221, "lr": 1.3374771380043306e-06, "epoch": 1.5661439485323683, "percentage": 78.55, "elapsed_time": "0:22:27", "remaining_time": "0:06:07"}
|
||||
{"current_steps": 488, "total_steps": 620, "loss": 0.0293, "lr": 1.3183715117440143e-06, "epoch": 1.569360675512666, "percentage": 78.71, "elapsed_time": "0:22:29", "remaining_time": "0:06:05"}
|
||||
{"current_steps": 489, "total_steps": 620, "loss": 0.0152, "lr": 1.2993825852972559e-06, "epoch": 1.5725774024929633, "percentage": 78.87, "elapsed_time": "0:22:32", "remaining_time": "0:06:02"}
|
||||
{"current_steps": 490, "total_steps": 620, "loss": 0.0297, "lr": 1.280510960572745e-06, "epoch": 1.575794129473261, "percentage": 79.03, "elapsed_time": "0:22:35", "remaining_time": "0:05:59"}
|
||||
{"current_steps": 491, "total_steps": 620, "loss": 0.023, "lr": 1.2617572357609565e-06, "epoch": 1.5790108564535585, "percentage": 79.19, "elapsed_time": "0:22:37", "remaining_time": "0:05:56"}
|
||||
{"current_steps": 492, "total_steps": 620, "loss": 0.0276, "lr": 1.2431220053151832e-06, "epoch": 1.582227583433856, "percentage": 79.35, "elapsed_time": "0:22:40", "remaining_time": "0:05:53"}
|
||||
{"current_steps": 493, "total_steps": 620, "loss": 0.0197, "lr": 1.2246058599327021e-06, "epoch": 1.5854443104141536, "percentage": 79.52, "elapsed_time": "0:22:42", "remaining_time": "0:05:51"}
|
||||
{"current_steps": 494, "total_steps": 620, "loss": 0.0266, "lr": 1.2062093865360458e-06, "epoch": 1.5886610373944512, "percentage": 79.68, "elapsed_time": "0:22:45", "remaining_time": "0:05:48"}
|
||||
{"current_steps": 495, "total_steps": 620, "loss": 0.0146, "lr": 1.1879331682543972e-06, "epoch": 1.5918777643747486, "percentage": 79.84, "elapsed_time": "0:22:47", "remaining_time": "0:05:45"}
|
||||
{"current_steps": 496, "total_steps": 620, "loss": 0.0266, "lr": 1.1697777844051105e-06, "epoch": 1.5950944913550462, "percentage": 80.0, "elapsed_time": "0:22:50", "remaining_time": "0:05:42"}
|
||||
{"current_steps": 497, "total_steps": 620, "loss": 0.0278, "lr": 1.1517438104753386e-06, "epoch": 1.5983112183353438, "percentage": 80.16, "elapsed_time": "0:22:52", "remaining_time": "0:05:39"}
|
||||
{"current_steps": 498, "total_steps": 620, "loss": 0.0264, "lr": 1.1338318181038037e-06, "epoch": 1.6015279453156412, "percentage": 80.32, "elapsed_time": "0:22:55", "remaining_time": "0:05:36"}
|
||||
{"current_steps": 499, "total_steps": 620, "loss": 0.0297, "lr": 1.1160423750626693e-06, "epoch": 1.6047446722959389, "percentage": 80.48, "elapsed_time": "0:22:57", "remaining_time": "0:05:34"}
|
||||
{"current_steps": 500, "total_steps": 620, "loss": 0.0181, "lr": 1.0983760452395415e-06, "epoch": 1.6079613992762365, "percentage": 80.65, "elapsed_time": "0:23:00", "remaining_time": "0:05:31"}
|
||||
{"current_steps": 501, "total_steps": 620, "loss": 0.0203, "lr": 1.0808333886196038e-06, "epoch": 1.611178126256534, "percentage": 80.81, "elapsed_time": "0:29:58", "remaining_time": "0:07:07"}
|
||||
{"current_steps": 502, "total_steps": 620, "loss": 0.0243, "lr": 1.063414961267859e-06, "epoch": 1.6143948532368315, "percentage": 80.97, "elapsed_time": "0:30:01", "remaining_time": "0:07:03"}
|
||||
{"current_steps": 503, "total_steps": 620, "loss": 0.0201, "lr": 1.046121315311508e-06, "epoch": 1.6176115802171291, "percentage": 81.13, "elapsed_time": "0:30:03", "remaining_time": "0:06:59"}
|
||||
{"current_steps": 504, "total_steps": 620, "loss": 0.0269, "lr": 1.02895299892244e-06, "epoch": 1.6208283071974265, "percentage": 81.29, "elapsed_time": "0:30:05", "remaining_time": "0:06:55"}
|
||||
{"current_steps": 505, "total_steps": 620, "loss": 0.0253, "lr": 1.01191055629987e-06, "epoch": 1.6240450341777242, "percentage": 81.45, "elapsed_time": "0:30:08", "remaining_time": "0:06:51"}
|
||||
{"current_steps": 506, "total_steps": 620, "loss": 0.0202, "lr": 9.949945276530782e-07, "epoch": 1.6272617611580218, "percentage": 81.61, "elapsed_time": "0:30:10", "remaining_time": "0:06:47"}
|
||||
{"current_steps": 507, "total_steps": 620, "loss": 0.0184, "lr": 9.782054491842879e-07, "epoch": 1.6304784881383192, "percentage": 81.77, "elapsed_time": "0:30:13", "remaining_time": "0:06:44"}
|
||||
{"current_steps": 508, "total_steps": 620, "loss": 0.0144, "lr": 9.615438530716753e-07, "epoch": 1.6336952151186168, "percentage": 81.94, "elapsed_time": "0:30:15", "remaining_time": "0:06:40"}
|
||||
{"current_steps": 509, "total_steps": 620, "loss": 0.0206, "lr": 9.450102674524952e-07, "epoch": 1.6369119420989144, "percentage": 82.1, "elapsed_time": "0:30:19", "remaining_time": "0:06:36"}
|
||||
{"current_steps": 510, "total_steps": 620, "loss": 0.0267, "lr": 9.286052164063369e-07, "epoch": 1.6401286690792118, "percentage": 82.26, "elapsed_time": "0:30:21", "remaining_time": "0:06:32"}
|
||||
{"current_steps": 511, "total_steps": 620, "loss": 0.0334, "lr": 9.123292199385247e-07, "epoch": 1.6433453960595095, "percentage": 82.42, "elapsed_time": "0:30:24", "remaining_time": "0:06:29"}
|
||||
{"current_steps": 512, "total_steps": 620, "loss": 0.023, "lr": 8.961827939636198e-07, "epoch": 1.646562123039807, "percentage": 82.58, "elapsed_time": "0:30:26", "remaining_time": "0:06:25"}
|
||||
{"current_steps": 513, "total_steps": 620, "loss": 0.0214, "lr": 8.801664502890722e-07, "epoch": 1.6497788500201045, "percentage": 82.74, "elapsed_time": "0:30:29", "remaining_time": "0:06:21"}
|
||||
{"current_steps": 514, "total_steps": 620, "loss": 0.0215, "lr": 8.64280696599008e-07, "epoch": 1.6529955770004021, "percentage": 82.9, "elapsed_time": "0:30:31", "remaining_time": "0:06:17"}
|
||||
{"current_steps": 515, "total_steps": 620, "loss": 0.0186, "lr": 8.485260364381187e-07, "epoch": 1.6562123039806997, "percentage": 83.06, "elapsed_time": "0:30:34", "remaining_time": "0:06:13"}
|
||||
{"current_steps": 516, "total_steps": 620, "loss": 0.0257, "lr": 8.329029691957124e-07, "epoch": 1.6594290309609971, "percentage": 83.23, "elapsed_time": "0:30:37", "remaining_time": "0:06:10"}
|
||||
{"current_steps": 517, "total_steps": 620, "loss": 0.0389, "lr": 8.17411990089883e-07, "epoch": 1.6626457579412948, "percentage": 83.39, "elapsed_time": "0:30:40", "remaining_time": "0:06:06"}
|
||||
{"current_steps": 518, "total_steps": 620, "loss": 0.0281, "lr": 8.02053590151805e-07, "epoch": 1.6658624849215924, "percentage": 83.55, "elapsed_time": "0:30:43", "remaining_time": "0:06:03"}
|
||||
{"current_steps": 519, "total_steps": 620, "loss": 0.0212, "lr": 7.868282562101819e-07, "epoch": 1.6690792119018898, "percentage": 83.71, "elapsed_time": "0:30:46", "remaining_time": "0:05:59"}
|
||||
{"current_steps": 520, "total_steps": 620, "loss": 0.0265, "lr": 7.717364708758024e-07, "epoch": 1.6722959388821874, "percentage": 83.87, "elapsed_time": "0:30:48", "remaining_time": "0:05:55"}
|
||||
{"current_steps": 521, "total_steps": 620, "loss": 0.0197, "lr": 7.567787125262449e-07, "epoch": 1.675512665862485, "percentage": 84.03, "elapsed_time": "0:30:51", "remaining_time": "0:05:51"}
|
||||
{"current_steps": 522, "total_steps": 620, "loss": 0.03, "lr": 7.41955455290726e-07, "epoch": 1.6787293928427824, "percentage": 84.19, "elapsed_time": "0:30:53", "remaining_time": "0:05:48"}
|
||||
{"current_steps": 523, "total_steps": 620, "loss": 0.0253, "lr": 7.27267169035053e-07, "epoch": 1.68194611982308, "percentage": 84.35, "elapsed_time": "0:30:56", "remaining_time": "0:05:44"}
|
||||
{"current_steps": 524, "total_steps": 620, "loss": 0.0209, "lr": 7.127143193467445e-07, "epoch": 1.6851628468033777, "percentage": 84.52, "elapsed_time": "0:30:58", "remaining_time": "0:05:40"}
|
||||
{"current_steps": 525, "total_steps": 620, "loss": 0.0263, "lr": 6.982973675202676e-07, "epoch": 1.688379573783675, "percentage": 84.68, "elapsed_time": "0:31:01", "remaining_time": "0:05:36"}
|
||||
{"current_steps": 526, "total_steps": 620, "loss": 0.0268, "lr": 6.840167705424106e-07, "epoch": 1.6915963007639725, "percentage": 84.84, "elapsed_time": "0:31:03", "remaining_time": "0:05:33"}
|
||||
{"current_steps": 527, "total_steps": 620, "loss": 0.0158, "lr": 6.698729810778065e-07, "epoch": 1.6948130277442703, "percentage": 85.0, "elapsed_time": "0:31:05", "remaining_time": "0:05:29"}
|
||||
{"current_steps": 528, "total_steps": 620, "loss": 0.0312, "lr": 6.558664474545817e-07, "epoch": 1.6980297547245677, "percentage": 85.16, "elapsed_time": "0:31:08", "remaining_time": "0:05:25"}
|
||||
{"current_steps": 529, "total_steps": 620, "loss": 0.0188, "lr": 6.419976136501377e-07, "epoch": 1.7012464817048651, "percentage": 85.32, "elapsed_time": "0:31:10", "remaining_time": "0:05:21"}
|
||||
{"current_steps": 530, "total_steps": 620, "loss": 0.0164, "lr": 6.282669192770896e-07, "epoch": 1.704463208685163, "percentage": 85.48, "elapsed_time": "0:31:13", "remaining_time": "0:05:18"}
|
||||
{"current_steps": 531, "total_steps": 620, "loss": 0.0251, "lr": 6.146747995693225e-07, "epoch": 1.7076799356654604, "percentage": 85.65, "elapsed_time": "0:31:15", "remaining_time": "0:05:14"}
|
||||
{"current_steps": 532, "total_steps": 620, "loss": 0.0271, "lr": 6.012216853682001e-07, "epoch": 1.7108966626457578, "percentage": 85.81, "elapsed_time": "0:31:18", "remaining_time": "0:05:10"}
|
||||
{"current_steps": 533, "total_steps": 620, "loss": 0.0297, "lr": 5.879080031089047e-07, "epoch": 1.7141133896260556, "percentage": 85.97, "elapsed_time": "0:31:21", "remaining_time": "0:05:07"}
|
||||
{"current_steps": 534, "total_steps": 620, "loss": 0.0184, "lr": 5.747341748069229e-07, "epoch": 1.717330116606353, "percentage": 86.13, "elapsed_time": "0:31:23", "remaining_time": "0:05:03"}
|
||||
{"current_steps": 535, "total_steps": 620, "loss": 0.0237, "lr": 5.617006180446688e-07, "epoch": 1.7205468435866504, "percentage": 86.29, "elapsed_time": "0:31:26", "remaining_time": "0:04:59"}
|
||||
{"current_steps": 536, "total_steps": 620, "loss": 0.0219, "lr": 5.488077459582425e-07, "epoch": 1.7237635705669483, "percentage": 86.45, "elapsed_time": "0:31:28", "remaining_time": "0:04:56"}
|
||||
{"current_steps": 537, "total_steps": 620, "loss": 0.0228, "lr": 5.360559672243421e-07, "epoch": 1.7269802975472457, "percentage": 86.61, "elapsed_time": "0:31:31", "remaining_time": "0:04:52"}
|
||||
{"current_steps": 538, "total_steps": 620, "loss": 0.0227, "lr": 5.234456860473042e-07, "epoch": 1.730197024527543, "percentage": 86.77, "elapsed_time": "0:31:34", "remaining_time": "0:04:48"}
|
||||
{"current_steps": 539, "total_steps": 620, "loss": 0.0156, "lr": 5.109773021462921e-07, "epoch": 1.7334137515078407, "percentage": 86.94, "elapsed_time": "0:31:37", "remaining_time": "0:04:45"}
|
||||
{"current_steps": 540, "total_steps": 620, "loss": 0.0308, "lr": 4.986512107426283e-07, "epoch": 1.7366304784881383, "percentage": 87.1, "elapsed_time": "0:31:39", "remaining_time": "0:04:41"}
|
||||
{"current_steps": 541, "total_steps": 620, "loss": 0.0119, "lr": 4.864678025472635e-07, "epoch": 1.7398472054684357, "percentage": 87.26, "elapsed_time": "0:31:42", "remaining_time": "0:04:37"}
|
||||
{"current_steps": 542, "total_steps": 620, "loss": 0.0267, "lr": 4.7442746374839363e-07, "epoch": 1.7430639324487334, "percentage": 87.42, "elapsed_time": "0:31:45", "remaining_time": "0:04:34"}
|
||||
{"current_steps": 543, "total_steps": 620, "loss": 0.0185, "lr": 4.625305759992205e-07, "epoch": 1.746280659429031, "percentage": 87.58, "elapsed_time": "0:31:47", "remaining_time": "0:04:30"}
|
||||
{"current_steps": 544, "total_steps": 620, "loss": 0.0244, "lr": 4.50777516405847e-07, "epoch": 1.7494973864093284, "percentage": 87.74, "elapsed_time": "0:31:50", "remaining_time": "0:04:26"}
|
||||
{"current_steps": 545, "total_steps": 620, "loss": 0.024, "lr": 4.3916865751533313e-07, "epoch": 1.752714113389626, "percentage": 87.9, "elapsed_time": "0:31:52", "remaining_time": "0:04:23"}
|
||||
{"current_steps": 546, "total_steps": 620, "loss": 0.0281, "lr": 4.2770436730388166e-07, "epoch": 1.7559308403699236, "percentage": 88.06, "elapsed_time": "0:31:55", "remaining_time": "0:04:19"}
|
||||
{"current_steps": 547, "total_steps": 620, "loss": 0.0345, "lr": 4.163850091651717e-07, "epoch": 1.759147567350221, "percentage": 88.23, "elapsed_time": "0:31:57", "remaining_time": "0:04:15"}
|
||||
{"current_steps": 548, "total_steps": 620, "loss": 0.0203, "lr": 4.05210941898847e-07, "epoch": 1.7623642943305187, "percentage": 88.39, "elapsed_time": "0:32:00", "remaining_time": "0:04:12"}
|
||||
{"current_steps": 549, "total_steps": 620, "loss": 0.0249, "lr": 3.941825196991378e-07, "epoch": 1.7655810213108163, "percentage": 88.55, "elapsed_time": "0:32:02", "remaining_time": "0:04:08"}
|
||||
{"current_steps": 550, "total_steps": 620, "loss": 0.0218, "lr": 3.8330009214363197e-07, "epoch": 1.7687977482911137, "percentage": 88.71, "elapsed_time": "0:32:05", "remaining_time": "0:04:05"}
|
||||
{"current_steps": 551, "total_steps": 620, "loss": 0.0251, "lr": 3.725640041822026e-07, "epoch": 1.7720144752714113, "percentage": 88.87, "elapsed_time": "0:32:07", "remaining_time": "0:04:01"}
|
||||
{"current_steps": 552, "total_steps": 620, "loss": 0.0255, "lr": 3.619745961260623e-07, "epoch": 1.775231202251709, "percentage": 89.03, "elapsed_time": "0:32:10", "remaining_time": "0:03:57"}
|
||||
{"current_steps": 553, "total_steps": 620, "loss": 0.0233, "lr": 3.5153220363698225e-07, "epoch": 1.7784479292320063, "percentage": 89.19, "elapsed_time": "0:32:12", "remaining_time": "0:03:54"}
|
||||
{"current_steps": 554, "total_steps": 620, "loss": 0.0211, "lr": 3.4123715771665786e-07, "epoch": 1.781664656212304, "percentage": 89.35, "elapsed_time": "0:32:16", "remaining_time": "0:03:50"}
|
||||
{"current_steps": 555, "total_steps": 620, "loss": 0.0158, "lr": 3.310897846962041e-07, "epoch": 1.7848813831926016, "percentage": 89.52, "elapsed_time": "0:32:18", "remaining_time": "0:03:47"}
|
||||
{"current_steps": 556, "total_steps": 620, "loss": 0.0129, "lr": 3.2109040622582186e-07, "epoch": 1.788098110172899, "percentage": 89.68, "elapsed_time": "0:32:21", "remaining_time": "0:03:43"}
|
||||
{"current_steps": 557, "total_steps": 620, "loss": 0.0241, "lr": 3.112393392645985e-07, "epoch": 1.7913148371531966, "percentage": 89.84, "elapsed_time": "0:32:24", "remaining_time": "0:03:39"}
|
||||
{"current_steps": 558, "total_steps": 620, "loss": 0.026, "lr": 3.015368960704584e-07, "epoch": 1.7945315641334942, "percentage": 90.0, "elapsed_time": "0:32:26", "remaining_time": "0:03:36"}
|
||||
{"current_steps": 559, "total_steps": 620, "loss": 0.0229, "lr": 2.919833841902714e-07, "epoch": 1.7977482911137916, "percentage": 90.16, "elapsed_time": "0:32:29", "remaining_time": "0:03:32"}
|
||||
{"current_steps": 560, "total_steps": 620, "loss": 0.025, "lr": 2.8257910645009935e-07, "epoch": 1.8009650180940893, "percentage": 90.32, "elapsed_time": "0:32:31", "remaining_time": "0:03:29"}
|
||||
{"current_steps": 561, "total_steps": 620, "loss": 0.0248, "lr": 2.733243609455971e-07, "epoch": 1.8041817450743869, "percentage": 90.48, "elapsed_time": "0:32:33", "remaining_time": "0:03:25"}
|
||||
{"current_steps": 562, "total_steps": 620, "loss": 0.0118, "lr": 2.6421944103256657e-07, "epoch": 1.8073984720546843, "percentage": 90.65, "elapsed_time": "0:32:36", "remaining_time": "0:03:21"}
|
||||
{"current_steps": 563, "total_steps": 620, "loss": 0.0272, "lr": 2.5526463531765467e-07, "epoch": 1.810615199034982, "percentage": 90.81, "elapsed_time": "0:32:39", "remaining_time": "0:03:18"}
|
||||
{"current_steps": 564, "total_steps": 620, "loss": 0.0181, "lr": 2.4646022764920843e-07, "epoch": 1.8138319260152795, "percentage": 90.97, "elapsed_time": "0:32:42", "remaining_time": "0:03:14"}
|
||||
{"current_steps": 565, "total_steps": 620, "loss": 0.0223, "lr": 2.3780649710827552e-07, "epoch": 1.817048652995577, "percentage": 91.13, "elapsed_time": "0:32:44", "remaining_time": "0:03:11"}
|
||||
{"current_steps": 566, "total_steps": 620, "loss": 0.0209, "lr": 2.2930371799975593e-07, "epoch": 1.8202653799758746, "percentage": 91.29, "elapsed_time": "0:32:47", "remaining_time": "0:03:07"}
|
||||
{"current_steps": 567, "total_steps": 620, "loss": 0.0197, "lr": 2.20952159843712e-07, "epoch": 1.8234821069561722, "percentage": 91.45, "elapsed_time": "0:32:49", "remaining_time": "0:03:04"}
|
||||
{"current_steps": 568, "total_steps": 620, "loss": 0.0149, "lr": 2.1275208736682262e-07, "epoch": 1.8266988339364696, "percentage": 91.61, "elapsed_time": "0:32:52", "remaining_time": "0:03:00"}
|
||||
{"current_steps": 569, "total_steps": 620, "loss": 0.0132, "lr": 2.0470376049398944e-07, "epoch": 1.8299155609167672, "percentage": 91.77, "elapsed_time": "0:32:54", "remaining_time": "0:02:56"}
|
||||
{"current_steps": 570, "total_steps": 620, "loss": 0.0201, "lr": 1.9680743434010385e-07, "epoch": 1.8331322878970648, "percentage": 91.94, "elapsed_time": "0:32:57", "remaining_time": "0:02:53"}
|
||||
{"current_steps": 571, "total_steps": 620, "loss": 0.0172, "lr": 1.8906335920195418e-07, "epoch": 1.8363490148773622, "percentage": 92.1, "elapsed_time": "0:32:59", "remaining_time": "0:02:49"}
|
||||
{"current_steps": 572, "total_steps": 620, "loss": 0.023, "lr": 1.814717805502958e-07, "epoch": 1.8395657418576599, "percentage": 92.26, "elapsed_time": "0:33:02", "remaining_time": "0:02:46"}
|
||||
{"current_steps": 573, "total_steps": 620, "loss": 0.0231, "lr": 1.7403293902206851e-07, "epoch": 1.8427824688379575, "percentage": 92.42, "elapsed_time": "0:33:06", "remaining_time": "0:02:42"}
|
||||
{"current_steps": 574, "total_steps": 620, "loss": 0.0323, "lr": 1.667470704127694e-07, "epoch": 1.845999195818255, "percentage": 92.58, "elapsed_time": "0:33:09", "remaining_time": "0:02:39"}
|
||||
{"current_steps": 575, "total_steps": 620, "loss": 0.0237, "lr": 1.5961440566897913e-07, "epoch": 1.8492159227985525, "percentage": 92.74, "elapsed_time": "0:33:11", "remaining_time": "0:02:35"}
|
||||
{"current_steps": 576, "total_steps": 620, "loss": 0.0232, "lr": 1.5263517088103862e-07, "epoch": 1.8524326497788501, "percentage": 92.9, "elapsed_time": "0:33:14", "remaining_time": "0:02:32"}
|
||||
{"current_steps": 577, "total_steps": 620, "loss": 0.0154, "lr": 1.4580958727588746e-07, "epoch": 1.8556493767591475, "percentage": 93.06, "elapsed_time": "0:33:17", "remaining_time": "0:02:28"}
|
||||
{"current_steps": 578, "total_steps": 620, "loss": 0.0255, "lr": 1.3913787121004717e-07, "epoch": 1.8588661037394452, "percentage": 93.23, "elapsed_time": "0:33:20", "remaining_time": "0:02:25"}
|
||||
{"current_steps": 579, "total_steps": 620, "loss": 0.0293, "lr": 1.3262023416276414e-07, "epoch": 1.8620828307197428, "percentage": 93.39, "elapsed_time": "0:33:22", "remaining_time": "0:02:21"}
|
||||
{"current_steps": 580, "total_steps": 620, "loss": 0.0244, "lr": 1.2625688272930925e-07, "epoch": 1.8652995577000402, "percentage": 93.55, "elapsed_time": "0:33:25", "remaining_time": "0:02:18"}
|
||||
{"current_steps": 581, "total_steps": 620, "loss": 0.0227, "lr": 1.2004801861442373e-07, "epoch": 1.8685162846803376, "percentage": 93.71, "elapsed_time": "0:33:27", "remaining_time": "0:02:14"}
|
||||
{"current_steps": 582, "total_steps": 620, "loss": 0.0242, "lr": 1.1399383862592928e-07, "epoch": 1.8717330116606354, "percentage": 93.87, "elapsed_time": "0:33:30", "remaining_time": "0:02:11"}
|
||||
{"current_steps": 583, "total_steps": 620, "loss": 0.0277, "lr": 1.0809453466849029e-07, "epoch": 1.8749497386409328, "percentage": 94.03, "elapsed_time": "0:33:32", "remaining_time": "0:02:07"}
|
||||
{"current_steps": 584, "total_steps": 620, "loss": 0.0218, "lr": 1.0235029373752758e-07, "epoch": 1.8781664656212302, "percentage": 94.19, "elapsed_time": "0:33:34", "remaining_time": "0:02:04"}
|
||||
{"current_steps": 585, "total_steps": 620, "loss": 0.0232, "lr": 9.676129791329481e-08, "epoch": 1.881383192601528, "percentage": 94.35, "elapsed_time": "0:33:37", "remaining_time": "0:02:00"}
|
||||
{"current_steps": 586, "total_steps": 620, "loss": 0.0255, "lr": 9.132772435510362e-08, "epoch": 1.8845999195818255, "percentage": 94.52, "elapsed_time": "0:33:39", "remaining_time": "0:01:57"}
|
||||
{"current_steps": 587, "total_steps": 620, "loss": 0.0368, "lr": 8.604974529571042e-08, "epoch": 1.887816646562123, "percentage": 94.68, "elapsed_time": "0:33:42", "remaining_time": "0:01:53"}
|
||||
{"current_steps": 588, "total_steps": 620, "loss": 0.0234, "lr": 8.092752803585513e-08, "epoch": 1.8910333735424207, "percentage": 94.84, "elapsed_time": "0:33:44", "remaining_time": "0:01:50"}
|
||||
{"current_steps": 589, "total_steps": 620, "loss": 0.0222, "lr": 7.59612349389599e-08, "epoch": 1.8942501005227181, "percentage": 95.0, "elapsed_time": "0:33:47", "remaining_time": "0:01:46"}
|
||||
{"current_steps": 590, "total_steps": 620, "loss": 0.0347, "lr": 7.115102342598101e-08, "epoch": 1.8974668275030155, "percentage": 95.16, "elapsed_time": "0:33:50", "remaining_time": "0:01:43"}
|
||||
{"current_steps": 591, "total_steps": 620, "loss": 0.022, "lr": 6.649704597042061e-08, "epoch": 1.9006835544833134, "percentage": 95.32, "elapsed_time": "0:33:52", "remaining_time": "0:01:39"}
|
||||
{"current_steps": 592, "total_steps": 620, "loss": 0.0195, "lr": 6.199945009349173e-08, "epoch": 1.9039002814636108, "percentage": 95.48, "elapsed_time": "0:33:55", "remaining_time": "0:01:36"}
|
||||
{"current_steps": 593, "total_steps": 620, "loss": 0.0307, "lr": 5.7658378359443104e-08, "epoch": 1.9071170084439082, "percentage": 95.65, "elapsed_time": "0:33:57", "remaining_time": "0:01:32"}
|
||||
{"current_steps": 594, "total_steps": 620, "loss": 0.0206, "lr": 5.3473968371040575e-08, "epoch": 1.910333735424206, "percentage": 95.81, "elapsed_time": "0:34:00", "remaining_time": "0:01:29"}
|
||||
{"current_steps": 595, "total_steps": 620, "loss": 0.0231, "lr": 4.944635276520393e-08, "epoch": 1.9135504624045034, "percentage": 95.97, "elapsed_time": "0:34:02", "remaining_time": "0:01:25"}
|
||||
{"current_steps": 596, "total_steps": 620, "loss": 0.0219, "lr": 4.55756592088058e-08, "epoch": 1.9167671893848008, "percentage": 96.13, "elapsed_time": "0:34:05", "remaining_time": "0:01:22"}
|
||||
{"current_steps": 597, "total_steps": 620, "loss": 0.0243, "lr": 4.186201039462046e-08, "epoch": 1.9199839163650985, "percentage": 96.29, "elapsed_time": "0:34:07", "remaining_time": "0:01:18"}
|
||||
{"current_steps": 598, "total_steps": 620, "loss": 0.0269, "lr": 3.8305524037438035e-08, "epoch": 1.923200643345396, "percentage": 96.45, "elapsed_time": "0:34:09", "remaining_time": "0:01:15"}
|
||||
{"current_steps": 599, "total_steps": 620, "loss": 0.0172, "lr": 3.4906312870331973e-08, "epoch": 1.9264173703256935, "percentage": 96.61, "elapsed_time": "0:34:13", "remaining_time": "0:01:11"}
|
||||
{"current_steps": 600, "total_steps": 620, "loss": 0.0302, "lr": 3.166448464108629e-08, "epoch": 1.9296340973059911, "percentage": 96.77, "elapsed_time": "0:34:15", "remaining_time": "0:01:08"}
|
||||
{"current_steps": 601, "total_steps": 620, "loss": 0.0182, "lr": 2.8580142108778354e-08, "epoch": 1.9328508242862887, "percentage": 96.94, "elapsed_time": "0:34:18", "remaining_time": "0:01:05"}
|
||||
{"current_steps": 602, "total_steps": 620, "loss": 0.0299, "lr": 2.5653383040524228e-08, "epoch": 1.9360675512665861, "percentage": 97.1, "elapsed_time": "0:34:21", "remaining_time": "0:01:01"}
|
||||
{"current_steps": 603, "total_steps": 620, "loss": 0.0278, "lr": 2.2884300208378395e-08, "epoch": 1.9392842782468838, "percentage": 97.26, "elapsed_time": "0:34:23", "remaining_time": "0:00:58"}
|
||||
{"current_steps": 604, "total_steps": 620, "loss": 0.0207, "lr": 2.0272981386393332e-08, "epoch": 1.9425010052271814, "percentage": 97.42, "elapsed_time": "0:34:26", "remaining_time": "0:00:54"}
|
||||
{"current_steps": 605, "total_steps": 620, "loss": 0.0177, "lr": 1.781950934783505e-08, "epoch": 1.9457177322074788, "percentage": 97.58, "elapsed_time": "0:34:30", "remaining_time": "0:00:51"}
|
||||
{"current_steps": 606, "total_steps": 620, "loss": 0.0255, "lr": 1.552396186256411e-08, "epoch": 1.9489344591877764, "percentage": 97.74, "elapsed_time": "0:34:32", "remaining_time": "0:00:47"}
|
||||
{"current_steps": 607, "total_steps": 620, "loss": 0.0278, "lr": 1.3386411694565894e-08, "epoch": 1.952151186168074, "percentage": 97.9, "elapsed_time": "0:34:35", "remaining_time": "0:00:44"}
|
||||
{"current_steps": 608, "total_steps": 620, "loss": 0.0192, "lr": 1.1406926599646373e-08, "epoch": 1.9553679131483714, "percentage": 98.06, "elapsed_time": "0:34:37", "remaining_time": "0:00:41"}
|
||||
{"current_steps": 609, "total_steps": 620, "loss": 0.0265, "lr": 9.585569323284915e-09, "epoch": 1.958584640128669, "percentage": 98.23, "elapsed_time": "0:34:40", "remaining_time": "0:00:37"}
|
||||
{"current_steps": 610, "total_steps": 620, "loss": 0.0357, "lr": 7.922397598642551e-09, "epoch": 1.9618013671089667, "percentage": 98.39, "elapsed_time": "0:34:42", "remaining_time": "0:00:34"}
|
||||
{"current_steps": 611, "total_steps": 620, "loss": 0.0232, "lr": 6.417464144736208e-09, "epoch": 1.965018094089264, "percentage": 98.55, "elapsed_time": "0:34:45", "remaining_time": "0:00:30"}
|
||||
{"current_steps": 612, "total_steps": 620, "loss": 0.0205, "lr": 5.0708166647628345e-09, "epoch": 1.9682348210695617, "percentage": 98.71, "elapsed_time": "0:34:48", "remaining_time": "0:00:27"}
|
||||
{"current_steps": 613, "total_steps": 620, "loss": 0.0193, "lr": 3.88249784459227e-09, "epoch": 1.9714515480498593, "percentage": 98.87, "elapsed_time": "0:34:50", "remaining_time": "0:00:23"}
|
||||
{"current_steps": 614, "total_steps": 620, "loss": 0.0177, "lr": 2.8525453514099966e-09, "epoch": 1.9746682750301567, "percentage": 99.03, "elapsed_time": "0:34:52", "remaining_time": "0:00:20"}
|
||||
{"current_steps": 615, "total_steps": 620, "loss": 0.0385, "lr": 1.980991832524759e-09, "epoch": 1.9778850020104544, "percentage": 99.19, "elapsed_time": "0:34:55", "remaining_time": "0:00:17"}
|
||||
{"current_steps": 616, "total_steps": 620, "loss": 0.0219, "lr": 1.2678649143349485e-09, "epoch": 1.981101728990752, "percentage": 99.35, "elapsed_time": "0:34:57", "remaining_time": "0:00:13"}
|
||||
{"current_steps": 617, "total_steps": 620, "loss": 0.0211, "lr": 7.131872014509711e-10, "epoch": 1.9843184559710494, "percentage": 99.52, "elapsed_time": "0:35:00", "remaining_time": "0:00:10"}
|
||||
{"current_steps": 618, "total_steps": 620, "loss": 0.0169, "lr": 3.1697627597970794e-10, "epoch": 1.987535182951347, "percentage": 99.68, "elapsed_time": "0:35:03", "remaining_time": "0:00:06"}
|
||||
{"current_steps": 619, "total_steps": 620, "loss": 0.0259, "lr": 7.924469696718451e-11, "epoch": 1.9907519099316446, "percentage": 99.84, "elapsed_time": "0:35:05", "remaining_time": "0:00:03"}
|
||||
{"current_steps": 620, "total_steps": 620, "loss": 0.0252, "lr": 0.0, "epoch": 1.993968636911942, "percentage": 100.0, "elapsed_time": "0:35:07", "remaining_time": "0:00:00"}
|
||||
4382
trainer_state.json
Normal file
4382
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb7d91dcf655532f6f2c298dae7e1fe9be35a59328187ef31be219a20580a2c6
|
||||
size 5944
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 44 KiB |
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user