初始化项目，由ModelHub XC社区提供模型
Model: mlfoundations-dev/qwen_openthoughts_science_claude Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-7B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: qwen_openthoughts_science_claude
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# qwen_openthoughts_science_claude
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/open-thoughts-science-claude dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 8e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 1
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 16
|
||||
- gradient_accumulation_steps: 32
|
||||
- total_train_batch_size: 512
|
||||
- total_eval_batch_size: 16
|
||||
- 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: 3.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.46.1
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 3.1.0
|
||||
- Tokenizers 0.20.3
|
||||
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": 2.987419245154709,
|
||||
"total_flos": 7.259120111838036e+18,
|
||||
"train_loss": 0.5428441533675561,
|
||||
"train_runtime": 82839.4057,
|
||||
"train_samples_per_second": 1.704,
|
||||
"train_steps_per_second": 0.003
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.46.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
41
configs.yaml
Normal file
41
configs.yaml
Normal file
@@ -0,0 +1,41 @@
|
||||
assistant_tag: gpt
|
||||
bf16: true
|
||||
content_tag: value
|
||||
cutoff_len: 16384
|
||||
dataset: mlfoundations-dev/open-thoughts-science-claude
|
||||
dataset_dir: ONLINE
|
||||
ddp_timeout: 180000000
|
||||
deepspeed: dcft/train/zero3.json
|
||||
do_train: true
|
||||
enable_liger_kernel: true
|
||||
finetuning_type: full
|
||||
formatting: sharegpt
|
||||
global_batch_size: 512
|
||||
gradient_accumulation_steps: 32
|
||||
hub_model_id: mlfoundations-dev/qwen_openthoughts_science_claude
|
||||
learning_rate: 8.0e-05
|
||||
logging_steps: 1
|
||||
lr_scheduler_type: cosine
|
||||
max_samples: 1000000
|
||||
messages: conversations
|
||||
model_name_or_path: Qwen/Qwen2.5-7B-Instruct
|
||||
neat_packing: true
|
||||
num_train_epochs: 3.0
|
||||
output_dir: /data/horse/ws/rehe951g-p_finetuning/checkpoints/qwen_openthoughts_science_claude
|
||||
overwrite_cache: true
|
||||
overwrite_output_dir: true
|
||||
packing: true
|
||||
per_device_eval_batch_size: 1
|
||||
per_device_train_batch_size: 1
|
||||
plot_loss: true
|
||||
preprocessing_num_workers: 16
|
||||
push_to_db: true
|
||||
push_to_hub: true
|
||||
report_to: wandb
|
||||
role_tag: from
|
||||
run_name: qwen_openthoughts_science_claude
|
||||
save_steps: 10
|
||||
stage: sft
|
||||
template: qwen25
|
||||
user_tag: human
|
||||
warmup_ratio: 0.1
|
||||
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": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.46.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c4a46ea2d146f6210bf618aed71932a1a1d11b783ed8c2bf86714b40d2e04ce
|
||||
size 4877660776
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:94d1161c459eba15dae4bea80cb4f27e9109838da981928b6121410e6cc619c6
|
||||
size 4932751008
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5c5f33003e9d4af5f65568cd6cfb11d91d7522d832634422be5cad42731c0ac7
|
||||
size 4330865200
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33fda979d524b8efb82bfca5e05e2dc990ae85f327cf618ad568d9ce14eb1305
|
||||
size 1089994880
|
||||
346
model.safetensors.index.json
Normal file
346
model.safetensors.index.json
Normal file
@@ -0,0 +1,346 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00004.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": "<|endoftext|>",
|
||||
"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
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"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": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"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": 2.987419245154709,
|
||||
"total_flos": 7.259120111838036e+18,
|
||||
"train_loss": 0.5428441533675561,
|
||||
"train_runtime": 82839.4057,
|
||||
"train_samples_per_second": 1.704,
|
||||
"train_steps_per_second": 0.003
|
||||
}
|
||||
274
trainer_log.jsonl
Normal file
274
trainer_log.jsonl
Normal file
@@ -0,0 +1,274 @@
|
||||
{"current_steps": 1, "total_steps": 273, "loss": 0.8514, "lr": 2.8571428571428573e-06, "epoch": 0.01088065283917035, "percentage": 0.37, "elapsed_time": "0:05:19", "remaining_time": "1 day, 0:07:56"}
|
||||
{"current_steps": 2, "total_steps": 273, "loss": 0.8564, "lr": 5.7142857142857145e-06, "epoch": 0.0217613056783407, "percentage": 0.73, "elapsed_time": "0:10:14", "remaining_time": "23:06:37"}
|
||||
{"current_steps": 3, "total_steps": 273, "loss": 0.8354, "lr": 8.571428571428571e-06, "epoch": 0.032641958517511054, "percentage": 1.1, "elapsed_time": "0:15:08", "remaining_time": "22:43:14"}
|
||||
{"current_steps": 4, "total_steps": 273, "loss": 0.771, "lr": 1.1428571428571429e-05, "epoch": 0.0435226113566814, "percentage": 1.47, "elapsed_time": "0:20:03", "remaining_time": "22:28:35"}
|
||||
{"current_steps": 5, "total_steps": 273, "loss": 0.7531, "lr": 1.4285714285714287e-05, "epoch": 0.05440326419585175, "percentage": 1.83, "elapsed_time": "0:24:58", "remaining_time": "22:18:18"}
|
||||
{"current_steps": 6, "total_steps": 273, "loss": 0.7605, "lr": 1.7142857142857142e-05, "epoch": 0.06528391703502211, "percentage": 2.2, "elapsed_time": "0:29:52", "remaining_time": "22:09:24"}
|
||||
{"current_steps": 7, "total_steps": 273, "loss": 0.7288, "lr": 2e-05, "epoch": 0.07616456987419246, "percentage": 2.56, "elapsed_time": "0:34:47", "remaining_time": "22:01:54"}
|
||||
{"current_steps": 8, "total_steps": 273, "loss": 0.7069, "lr": 2.2857142857142858e-05, "epoch": 0.0870452227133628, "percentage": 2.93, "elapsed_time": "0:39:41", "remaining_time": "21:54:44"}
|
||||
{"current_steps": 9, "total_steps": 273, "loss": 0.6744, "lr": 2.5714285714285718e-05, "epoch": 0.09792587555253315, "percentage": 3.3, "elapsed_time": "0:44:36", "remaining_time": "21:48:16"}
|
||||
{"current_steps": 10, "total_steps": 273, "loss": 0.6654, "lr": 2.8571428571428574e-05, "epoch": 0.1088065283917035, "percentage": 3.66, "elapsed_time": "0:49:30", "remaining_time": "21:42:09"}
|
||||
{"current_steps": 11, "total_steps": 273, "loss": 0.6374, "lr": 3.142857142857143e-05, "epoch": 0.11968718123087385, "percentage": 4.03, "elapsed_time": "0:55:29", "remaining_time": "22:01:31"}
|
||||
{"current_steps": 12, "total_steps": 273, "loss": 0.6326, "lr": 3.4285714285714284e-05, "epoch": 0.13056783407004421, "percentage": 4.4, "elapsed_time": "1:00:27", "remaining_time": "21:55:00"}
|
||||
{"current_steps": 13, "total_steps": 273, "loss": 0.6164, "lr": 3.714285714285715e-05, "epoch": 0.14144848690921455, "percentage": 4.76, "elapsed_time": "1:05:24", "remaining_time": "21:48:02"}
|
||||
{"current_steps": 14, "total_steps": 273, "loss": 0.6096, "lr": 4e-05, "epoch": 0.1523291397483849, "percentage": 5.13, "elapsed_time": "1:10:20", "remaining_time": "21:41:18"}
|
||||
{"current_steps": 15, "total_steps": 273, "loss": 0.5988, "lr": 4.2857142857142856e-05, "epoch": 0.16320979258755525, "percentage": 5.49, "elapsed_time": "1:15:15", "remaining_time": "21:34:20"}
|
||||
{"current_steps": 16, "total_steps": 273, "loss": 0.5979, "lr": 4.5714285714285716e-05, "epoch": 0.1740904454267256, "percentage": 5.86, "elapsed_time": "1:20:09", "remaining_time": "21:27:35"}
|
||||
{"current_steps": 17, "total_steps": 273, "loss": 0.5824, "lr": 4.857142857142857e-05, "epoch": 0.18497109826589594, "percentage": 6.23, "elapsed_time": "1:25:04", "remaining_time": "21:21:02"}
|
||||
{"current_steps": 18, "total_steps": 273, "loss": 0.5851, "lr": 5.1428571428571436e-05, "epoch": 0.1958517511050663, "percentage": 6.59, "elapsed_time": "1:29:58", "remaining_time": "21:14:38"}
|
||||
{"current_steps": 19, "total_steps": 273, "loss": 0.5798, "lr": 5.4285714285714295e-05, "epoch": 0.20673240394423664, "percentage": 6.96, "elapsed_time": "1:34:58", "remaining_time": "21:09:40"}
|
||||
{"current_steps": 20, "total_steps": 273, "loss": 0.5623, "lr": 5.714285714285715e-05, "epoch": 0.217613056783407, "percentage": 7.33, "elapsed_time": "1:39:53", "remaining_time": "21:03:32"}
|
||||
{"current_steps": 21, "total_steps": 273, "loss": 0.5617, "lr": 6.000000000000001e-05, "epoch": 0.22849370962257737, "percentage": 7.69, "elapsed_time": "1:45:46", "remaining_time": "21:09:18"}
|
||||
{"current_steps": 22, "total_steps": 273, "loss": 0.554, "lr": 6.285714285714286e-05, "epoch": 0.2393743624617477, "percentage": 8.06, "elapsed_time": "1:50:41", "remaining_time": "21:02:49"}
|
||||
{"current_steps": 23, "total_steps": 273, "loss": 0.5728, "lr": 6.571428571428571e-05, "epoch": 0.25025501530091804, "percentage": 8.42, "elapsed_time": "1:55:35", "remaining_time": "20:56:27"}
|
||||
{"current_steps": 24, "total_steps": 273, "loss": 0.5663, "lr": 6.857142857142857e-05, "epoch": 0.26113566814008843, "percentage": 8.79, "elapsed_time": "2:00:31", "remaining_time": "20:50:22"}
|
||||
{"current_steps": 25, "total_steps": 273, "loss": 0.5589, "lr": 7.142857142857143e-05, "epoch": 0.27201632097925876, "percentage": 9.16, "elapsed_time": "2:05:26", "remaining_time": "20:44:20"}
|
||||
{"current_steps": 26, "total_steps": 273, "loss": 0.5561, "lr": 7.42857142857143e-05, "epoch": 0.2828969738184291, "percentage": 9.52, "elapsed_time": "2:10:21", "remaining_time": "20:38:20"}
|
||||
{"current_steps": 27, "total_steps": 273, "loss": 0.5371, "lr": 7.714285714285715e-05, "epoch": 0.29377762665759943, "percentage": 9.89, "elapsed_time": "2:15:16", "remaining_time": "20:32:34"}
|
||||
{"current_steps": 28, "total_steps": 273, "loss": 0.5482, "lr": 8e-05, "epoch": 0.3046582794967698, "percentage": 10.26, "elapsed_time": "2:20:11", "remaining_time": "20:26:40"}
|
||||
{"current_steps": 29, "total_steps": 273, "loss": 0.5468, "lr": 7.999671154713278e-05, "epoch": 0.31553893233594016, "percentage": 10.62, "elapsed_time": "2:25:05", "remaining_time": "20:20:48"}
|
||||
{"current_steps": 30, "total_steps": 273, "loss": 0.5484, "lr": 7.99868467292272e-05, "epoch": 0.3264195851751105, "percentage": 10.99, "elapsed_time": "2:30:04", "remaining_time": "20:15:35"}
|
||||
{"current_steps": 31, "total_steps": 273, "loss": 0.5391, "lr": 7.997040716828271e-05, "epoch": 0.3373002380142809, "percentage": 11.36, "elapsed_time": "2:35:56", "remaining_time": "20:17:22"}
|
||||
{"current_steps": 32, "total_steps": 273, "loss": 7.0977, "lr": 7.994739556733538e-05, "epoch": 0.3481808908534512, "percentage": 11.72, "elapsed_time": "2:40:51", "remaining_time": "20:11:29"}
|
||||
{"current_steps": 33, "total_steps": 273, "loss": 8.9951, "lr": 7.991781571001347e-05, "epoch": 0.35906154369262155, "percentage": 12.09, "elapsed_time": "2:45:48", "remaining_time": "20:05:54"}
|
||||
{"current_steps": 34, "total_steps": 273, "loss": 6.6897, "lr": 7.988167245991528e-05, "epoch": 0.3699421965317919, "percentage": 12.45, "elapsed_time": "2:50:43", "remaining_time": "20:00:06"}
|
||||
{"current_steps": 35, "total_steps": 273, "loss": 0.7981, "lr": 7.983897175980957e-05, "epoch": 0.3808228493709623, "percentage": 12.82, "elapsed_time": "2:55:38", "remaining_time": "19:54:20"}
|
||||
{"current_steps": 36, "total_steps": 273, "loss": 0.7036, "lr": 7.97897206306583e-05, "epoch": 0.3917035022101326, "percentage": 13.19, "elapsed_time": "3:00:32", "remaining_time": "19:48:35"}
|
||||
{"current_steps": 37, "total_steps": 273, "loss": 0.6454, "lr": 7.973392717046233e-05, "epoch": 0.40258415504930295, "percentage": 13.55, "elapsed_time": "3:05:27", "remaining_time": "19:42:57"}
|
||||
{"current_steps": 38, "total_steps": 273, "loss": 0.6386, "lr": 7.967160055292984e-05, "epoch": 0.4134648078884733, "percentage": 13.92, "elapsed_time": "3:10:22", "remaining_time": "19:37:17"}
|
||||
{"current_steps": 39, "total_steps": 273, "loss": 0.6128, "lr": 7.960275102596809e-05, "epoch": 0.4243454607276437, "percentage": 14.29, "elapsed_time": "3:15:16", "remaining_time": "19:31:40"}
|
||||
{"current_steps": 40, "total_steps": 273, "loss": 0.5773, "lr": 7.952738990999824e-05, "epoch": 0.435226113566814, "percentage": 14.65, "elapsed_time": "3:20:14", "remaining_time": "19:26:25"}
|
||||
{"current_steps": 41, "total_steps": 273, "loss": 0.569, "lr": 7.94455295960942e-05, "epoch": 0.44610676640598435, "percentage": 15.02, "elapsed_time": "3:26:11", "remaining_time": "19:26:43"}
|
||||
{"current_steps": 42, "total_steps": 273, "loss": 0.5501, "lr": 7.93571835439452e-05, "epoch": 0.45698741924515474, "percentage": 15.38, "elapsed_time": "3:31:06", "remaining_time": "19:21:03"}
|
||||
{"current_steps": 43, "total_steps": 273, "loss": 0.5486, "lr": 7.926236627964262e-05, "epoch": 0.46786807208432507, "percentage": 15.75, "elapsed_time": "3:36:01", "remaining_time": "19:15:28"}
|
||||
{"current_steps": 44, "total_steps": 273, "loss": 0.5452, "lr": 7.916109339329173e-05, "epoch": 0.4787487249234954, "percentage": 16.12, "elapsed_time": "3:40:55", "remaining_time": "19:09:49"}
|
||||
{"current_steps": 45, "total_steps": 273, "loss": 0.5349, "lr": 7.905338153644818e-05, "epoch": 0.48962937776266574, "percentage": 16.48, "elapsed_time": "3:45:50", "remaining_time": "19:04:14"}
|
||||
{"current_steps": 46, "total_steps": 273, "loss": 0.5359, "lr": 7.89392484193802e-05, "epoch": 0.5005100306018361, "percentage": 16.85, "elapsed_time": "3:50:46", "remaining_time": "18:58:47"}
|
||||
{"current_steps": 47, "total_steps": 273, "loss": 0.5192, "lr": 7.881871280815659e-05, "epoch": 0.5113906834410065, "percentage": 17.22, "elapsed_time": "3:55:40", "remaining_time": "18:53:15"}
|
||||
{"current_steps": 48, "total_steps": 273, "loss": 0.523, "lr": 7.869179452156118e-05, "epoch": 0.5222713362801769, "percentage": 17.58, "elapsed_time": "4:00:35", "remaining_time": "18:47:44"}
|
||||
{"current_steps": 49, "total_steps": 273, "loss": 0.5277, "lr": 7.855851442783414e-05, "epoch": 0.5331519891193471, "percentage": 17.95, "elapsed_time": "4:05:29", "remaining_time": "18:42:15"}
|
||||
{"current_steps": 50, "total_steps": 273, "loss": 0.5171, "lr": 7.841889444124078e-05, "epoch": 0.5440326419585175, "percentage": 18.32, "elapsed_time": "4:10:29", "remaining_time": "18:37:11"}
|
||||
{"current_steps": 51, "total_steps": 273, "loss": 0.5228, "lr": 7.827295751846836e-05, "epoch": 0.5549132947976878, "percentage": 18.68, "elapsed_time": "4:16:24", "remaining_time": "18:36:07"}
|
||||
{"current_steps": 52, "total_steps": 273, "loss": 0.5176, "lr": 7.81207276548515e-05, "epoch": 0.5657939476368582, "percentage": 19.05, "elapsed_time": "4:21:24", "remaining_time": "18:30:59"}
|
||||
{"current_steps": 53, "total_steps": 273, "loss": 0.5173, "lr": 7.796222988042676e-05, "epoch": 0.5766746004760286, "percentage": 19.41, "elapsed_time": "4:26:24", "remaining_time": "18:25:50"}
|
||||
{"current_steps": 54, "total_steps": 273, "loss": 0.5112, "lr": 7.779749025581717e-05, "epoch": 0.5875552533151989, "percentage": 19.78, "elapsed_time": "4:31:18", "remaining_time": "18:20:19"}
|
||||
{"current_steps": 55, "total_steps": 273, "loss": 0.5207, "lr": 7.762653586794731e-05, "epoch": 0.5984359061543693, "percentage": 20.15, "elapsed_time": "4:36:13", "remaining_time": "18:14:51"}
|
||||
{"current_steps": 56, "total_steps": 273, "loss": 0.5023, "lr": 7.74493948255895e-05, "epoch": 0.6093165589935396, "percentage": 20.51, "elapsed_time": "4:41:09", "remaining_time": "18:09:28"}
|
||||
{"current_steps": 57, "total_steps": 273, "loss": 0.493, "lr": 7.726609625474218e-05, "epoch": 0.6201972118327099, "percentage": 20.88, "elapsed_time": "4:46:04", "remaining_time": "18:04:03"}
|
||||
{"current_steps": 58, "total_steps": 273, "loss": 0.5002, "lr": 7.707667029384088e-05, "epoch": 0.6310778646718803, "percentage": 21.25, "elapsed_time": "4:51:00", "remaining_time": "17:58:44"}
|
||||
{"current_steps": 59, "total_steps": 273, "loss": 0.5014, "lr": 7.688114808880283e-05, "epoch": 0.6419585175110507, "percentage": 21.61, "elapsed_time": "4:55:55", "remaining_time": "17:53:22"}
|
||||
{"current_steps": 60, "total_steps": 273, "loss": 0.4932, "lr": 7.667956178790582e-05, "epoch": 0.652839170350221, "percentage": 21.98, "elapsed_time": "5:00:50", "remaining_time": "17:47:59"}
|
||||
{"current_steps": 61, "total_steps": 273, "loss": 0.5052, "lr": 7.647194453650228e-05, "epoch": 0.6637198231893914, "percentage": 22.34, "elapsed_time": "5:06:44", "remaining_time": "17:46:01"}
|
||||
{"current_steps": 62, "total_steps": 273, "loss": 0.48, "lr": 7.625833047156953e-05, "epoch": 0.6746004760285618, "percentage": 22.71, "elapsed_time": "5:11:38", "remaining_time": "17:40:35"}
|
||||
{"current_steps": 63, "total_steps": 273, "loss": 0.496, "lr": 7.603875471609677e-05, "epoch": 0.685481128867732, "percentage": 23.08, "elapsed_time": "5:16:33", "remaining_time": "17:35:12"}
|
||||
{"current_steps": 64, "total_steps": 273, "loss": 0.4961, "lr": 7.581325337331013e-05, "epoch": 0.6963617817069024, "percentage": 23.44, "elapsed_time": "5:21:28", "remaining_time": "17:29:48"}
|
||||
{"current_steps": 65, "total_steps": 273, "loss": 0.4835, "lr": 7.558186352073648e-05, "epoch": 0.7072424345460727, "percentage": 23.81, "elapsed_time": "5:26:26", "remaining_time": "17:24:37"}
|
||||
{"current_steps": 66, "total_steps": 273, "loss": 0.4935, "lr": 7.534462320410702e-05, "epoch": 0.7181230873852431, "percentage": 24.18, "elapsed_time": "5:31:20", "remaining_time": "17:19:13"}
|
||||
{"current_steps": 67, "total_steps": 273, "loss": 0.4906, "lr": 7.510157143110172e-05, "epoch": 0.7290037402244135, "percentage": 24.54, "elapsed_time": "5:36:15", "remaining_time": "17:13:50"}
|
||||
{"current_steps": 68, "total_steps": 273, "loss": 0.4924, "lr": 7.485274816493558e-05, "epoch": 0.7398843930635838, "percentage": 24.91, "elapsed_time": "5:41:09", "remaining_time": "17:08:28"}
|
||||
{"current_steps": 69, "total_steps": 273, "loss": 0.4947, "lr": 7.459819431778775e-05, "epoch": 0.7507650459027542, "percentage": 25.27, "elapsed_time": "5:46:03", "remaining_time": "17:03:08"}
|
||||
{"current_steps": 70, "total_steps": 273, "loss": 0.4817, "lr": 7.433795174407465e-05, "epoch": 0.7616456987419246, "percentage": 25.64, "elapsed_time": "5:50:57", "remaining_time": "16:57:47"}
|
||||
{"current_steps": 71, "total_steps": 273, "loss": 0.4918, "lr": 7.407206323356818e-05, "epoch": 0.7725263515810948, "percentage": 26.01, "elapsed_time": "5:56:49", "remaining_time": "16:55:12"}
|
||||
{"current_steps": 72, "total_steps": 273, "loss": 0.4887, "lr": 7.380057250436006e-05, "epoch": 0.7834070044202652, "percentage": 26.37, "elapsed_time": "6:01:44", "remaining_time": "16:49:52"}
|
||||
{"current_steps": 73, "total_steps": 273, "loss": 0.4816, "lr": 7.352352419567362e-05, "epoch": 0.7942876572594356, "percentage": 26.74, "elapsed_time": "6:06:39", "remaining_time": "16:44:32"}
|
||||
{"current_steps": 74, "total_steps": 273, "loss": 0.485, "lr": 7.324096386052416e-05, "epoch": 0.8051683100986059, "percentage": 27.11, "elapsed_time": "6:11:34", "remaining_time": "16:39:12"}
|
||||
{"current_steps": 75, "total_steps": 273, "loss": 0.4744, "lr": 7.295293795822887e-05, "epoch": 0.8160489629377763, "percentage": 27.47, "elapsed_time": "6:16:28", "remaining_time": "16:33:54"}
|
||||
{"current_steps": 76, "total_steps": 273, "loss": 0.4722, "lr": 7.265949384676795e-05, "epoch": 0.8269296157769466, "percentage": 27.84, "elapsed_time": "6:21:23", "remaining_time": "16:28:35"}
|
||||
{"current_steps": 77, "total_steps": 273, "loss": 0.4807, "lr": 7.236067977499791e-05, "epoch": 0.837810268616117, "percentage": 28.21, "elapsed_time": "6:26:17", "remaining_time": "16:23:17"}
|
||||
{"current_steps": 78, "total_steps": 273, "loss": 0.4797, "lr": 7.205654487471826e-05, "epoch": 0.8486909214552874, "percentage": 28.57, "elapsed_time": "6:31:18", "remaining_time": "16:18:17"}
|
||||
{"current_steps": 79, "total_steps": 273, "loss": 0.475, "lr": 7.174713915259331e-05, "epoch": 0.8595715742944576, "percentage": 28.94, "elapsed_time": "6:36:13", "remaining_time": "16:13:01"}
|
||||
{"current_steps": 80, "total_steps": 273, "loss": 0.4677, "lr": 7.143251348192971e-05, "epoch": 0.870452227133628, "percentage": 29.3, "elapsed_time": "6:41:08", "remaining_time": "16:07:44"}
|
||||
{"current_steps": 81, "total_steps": 273, "loss": 0.4793, "lr": 7.111271959431189e-05, "epoch": 0.8813328799727984, "percentage": 29.67, "elapsed_time": "6:47:10", "remaining_time": "16:05:10"}
|
||||
{"current_steps": 82, "total_steps": 273, "loss": 0.4695, "lr": 7.078781007109625e-05, "epoch": 0.8922135328119687, "percentage": 30.04, "elapsed_time": "6:52:06", "remaining_time": "15:59:54"}
|
||||
{"current_steps": 83, "total_steps": 273, "loss": 0.4794, "lr": 7.045783833476538e-05, "epoch": 0.9030941856511391, "percentage": 30.4, "elapsed_time": "6:57:01", "remaining_time": "15:54:37"}
|
||||
{"current_steps": 84, "total_steps": 273, "loss": 0.4758, "lr": 7.012285864014445e-05, "epoch": 0.9139748384903095, "percentage": 30.77, "elapsed_time": "7:01:57", "remaining_time": "15:49:24"}
|
||||
{"current_steps": 85, "total_steps": 273, "loss": 0.4716, "lr": 6.978292606548029e-05, "epoch": 0.9248554913294798, "percentage": 31.14, "elapsed_time": "7:06:52", "remaining_time": "15:44:08"}
|
||||
{"current_steps": 86, "total_steps": 273, "loss": 0.4703, "lr": 6.943809650338541e-05, "epoch": 0.9357361441686501, "percentage": 31.5, "elapsed_time": "7:11:47", "remaining_time": "15:38:52"}
|
||||
{"current_steps": 87, "total_steps": 273, "loss": 0.4665, "lr": 6.908842665164789e-05, "epoch": 0.9466167970078204, "percentage": 31.87, "elapsed_time": "7:16:41", "remaining_time": "15:33:37"}
|
||||
{"current_steps": 88, "total_steps": 273, "loss": 0.4718, "lr": 6.873397400390911e-05, "epoch": 0.9574974498469908, "percentage": 32.23, "elapsed_time": "7:21:36", "remaining_time": "15:28:23"}
|
||||
{"current_steps": 89, "total_steps": 273, "loss": 0.4726, "lr": 6.837479684021032e-05, "epoch": 0.9683781026861612, "percentage": 32.6, "elapsed_time": "7:26:31", "remaining_time": "15:23:08"}
|
||||
{"current_steps": 90, "total_steps": 273, "loss": 0.4699, "lr": 6.80109542174102e-05, "epoch": 0.9792587555253315, "percentage": 32.97, "elapsed_time": "7:31:26", "remaining_time": "15:17:54"}
|
||||
{"current_steps": 91, "total_steps": 273, "loss": 0.4788, "lr": 6.76425059594746e-05, "epoch": 0.9901394083645019, "percentage": 33.33, "elapsed_time": "7:37:17", "remaining_time": "15:14:35"}
|
||||
{"current_steps": 92, "total_steps": 273, "loss": 0.456, "lr": 6.726951264763998e-05, "epoch": 1.009520571234274, "percentage": 33.7, "elapsed_time": "7:42:26", "remaining_time": "15:09:48"}
|
||||
{"current_steps": 93, "total_steps": 273, "loss": 0.4545, "lr": 6.689203561045268e-05, "epoch": 1.0204012240734444, "percentage": 34.07, "elapsed_time": "7:47:21", "remaining_time": "15:04:33"}
|
||||
{"current_steps": 94, "total_steps": 273, "loss": 0.4589, "lr": 6.651013691368492e-05, "epoch": 1.0312818769126149, "percentage": 34.43, "elapsed_time": "7:52:15", "remaining_time": "14:59:18"}
|
||||
{"current_steps": 95, "total_steps": 273, "loss": 0.4594, "lr": 6.612387935012995e-05, "epoch": 1.0421625297517851, "percentage": 34.8, "elapsed_time": "7:57:10", "remaining_time": "14:54:03"}
|
||||
{"current_steps": 96, "total_steps": 273, "loss": 0.4514, "lr": 6.573332642927737e-05, "epoch": 1.0530431825909554, "percentage": 35.16, "elapsed_time": "8:02:04", "remaining_time": "14:48:49"}
|
||||
{"current_steps": 97, "total_steps": 273, "loss": 0.4416, "lr": 6.53385423668708e-05, "epoch": 1.063923835430126, "percentage": 35.53, "elapsed_time": "8:07:01", "remaining_time": "14:43:40"}
|
||||
{"current_steps": 98, "total_steps": 273, "loss": 0.4497, "lr": 6.493959207434934e-05, "epoch": 1.0748044882692962, "percentage": 35.9, "elapsed_time": "8:11:57", "remaining_time": "14:38:28"}
|
||||
{"current_steps": 99, "total_steps": 273, "loss": 0.457, "lr": 6.453654114817467e-05, "epoch": 1.0856851411084665, "percentage": 36.26, "elapsed_time": "8:16:51", "remaining_time": "14:33:16"}
|
||||
{"current_steps": 100, "total_steps": 273, "loss": 0.4481, "lr": 6.412945585904545e-05, "epoch": 1.0965657939476368, "percentage": 36.63, "elapsed_time": "8:21:46", "remaining_time": "14:28:04"}
|
||||
{"current_steps": 101, "total_steps": 273, "loss": 0.4514, "lr": 6.371840314100104e-05, "epoch": 1.1074464467868073, "percentage": 37.0, "elapsed_time": "8:27:38", "remaining_time": "14:24:29"}
|
||||
{"current_steps": 102, "total_steps": 273, "loss": 0.4583, "lr": 6.330345058041585e-05, "epoch": 1.1183270996259775, "percentage": 37.36, "elapsed_time": "8:32:32", "remaining_time": "14:19:15"}
|
||||
{"current_steps": 103, "total_steps": 273, "loss": 0.4374, "lr": 6.288466640488679e-05, "epoch": 1.1292077524651478, "percentage": 37.73, "elapsed_time": "8:37:26", "remaining_time": "14:14:02"}
|
||||
{"current_steps": 104, "total_steps": 273, "loss": 0.4428, "lr": 6.2462119472015e-05, "epoch": 1.1400884053043183, "percentage": 38.1, "elapsed_time": "8:42:21", "remaining_time": "14:08:49"}
|
||||
{"current_steps": 105, "total_steps": 273, "loss": 0.4471, "lr": 6.20358792580841e-05, "epoch": 1.1509690581434886, "percentage": 38.46, "elapsed_time": "8:47:15", "remaining_time": "14:03:37"}
|
||||
{"current_steps": 106, "total_steps": 273, "loss": 0.4453, "lr": 6.160601584663681e-05, "epoch": 1.1618497109826589, "percentage": 38.83, "elapsed_time": "8:52:10", "remaining_time": "13:58:24"}
|
||||
{"current_steps": 107, "total_steps": 273, "loss": 0.4491, "lr": 6.11725999169515e-05, "epoch": 1.1727303638218294, "percentage": 39.19, "elapsed_time": "8:57:04", "remaining_time": "13:53:13"}
|
||||
{"current_steps": 108, "total_steps": 273, "loss": 0.4443, "lr": 6.0735702732421015e-05, "epoch": 1.1836110166609997, "percentage": 39.56, "elapsed_time": "9:01:58", "remaining_time": "13:48:01"}
|
||||
{"current_steps": 109, "total_steps": 273, "loss": 0.4402, "lr": 6.029539612883529e-05, "epoch": 1.19449166950017, "percentage": 39.93, "elapsed_time": "9:06:53", "remaining_time": "13:42:51"}
|
||||
{"current_steps": 110, "total_steps": 273, "loss": 0.435, "lr": 5.9851752502570015e-05, "epoch": 1.2053723223393404, "percentage": 40.29, "elapsed_time": "9:11:57", "remaining_time": "13:37:53"}
|
||||
{"current_steps": 111, "total_steps": 273, "loss": 0.4462, "lr": 5.940484479868288e-05, "epoch": 1.2162529751785107, "percentage": 40.66, "elapsed_time": "9:17:48", "remaining_time": "13:34:06"}
|
||||
{"current_steps": 112, "total_steps": 273, "loss": 0.4421, "lr": 5.895474649891995e-05, "epoch": 1.227133628017681, "percentage": 41.03, "elapsed_time": "9:22:43", "remaining_time": "13:28:54"}
|
||||
{"current_steps": 113, "total_steps": 273, "loss": 0.446, "lr": 5.8501531609633424e-05, "epoch": 1.2380142808568515, "percentage": 41.39, "elapsed_time": "9:27:37", "remaining_time": "13:23:43"}
|
||||
{"current_steps": 114, "total_steps": 273, "loss": 0.4448, "lr": 5.8045274649613386e-05, "epoch": 1.2488949336960218, "percentage": 41.76, "elapsed_time": "9:32:37", "remaining_time": "13:18:39"}
|
||||
{"current_steps": 115, "total_steps": 273, "loss": 0.4374, "lr": 5.7586050637835295e-05, "epoch": 1.259775586535192, "percentage": 42.12, "elapsed_time": "9:37:32", "remaining_time": "13:13:29"}
|
||||
{"current_steps": 116, "total_steps": 273, "loss": 0.4458, "lr": 5.7123935081125034e-05, "epoch": 1.2706562393743623, "percentage": 42.49, "elapsed_time": "9:42:26", "remaining_time": "13:08:18"}
|
||||
{"current_steps": 117, "total_steps": 273, "loss": 0.4376, "lr": 5.6659003961743965e-05, "epoch": 1.2815368922135328, "percentage": 42.86, "elapsed_time": "9:47:21", "remaining_time": "13:03:08"}
|
||||
{"current_steps": 118, "total_steps": 273, "loss": 0.4515, "lr": 5.619133372489575e-05, "epoch": 1.2924175450527031, "percentage": 43.22, "elapsed_time": "9:52:15", "remaining_time": "12:57:58"}
|
||||
{"current_steps": 119, "total_steps": 273, "loss": 0.4443, "lr": 5.572100126615695e-05, "epoch": 1.3032981978918734, "percentage": 43.59, "elapsed_time": "9:57:10", "remaining_time": "12:52:48"}
|
||||
{"current_steps": 120, "total_steps": 273, "loss": 0.441, "lr": 5.524808391883367e-05, "epoch": 1.314178850731044, "percentage": 43.96, "elapsed_time": "10:02:04", "remaining_time": "12:47:38"}
|
||||
{"current_steps": 121, "total_steps": 273, "loss": 0.4354, "lr": 5.477265944124626e-05, "epoch": 1.3250595035702142, "percentage": 44.32, "elapsed_time": "10:08:02", "remaining_time": "12:43:49"}
|
||||
{"current_steps": 122, "total_steps": 273, "loss": 0.4407, "lr": 5.429480600394405e-05, "epoch": 1.3359401564093845, "percentage": 44.69, "elapsed_time": "10:12:57", "remaining_time": "12:38:39"}
|
||||
{"current_steps": 123, "total_steps": 273, "loss": 0.4359, "lr": 5.381460217685231e-05, "epoch": 1.346820809248555, "percentage": 45.05, "elapsed_time": "10:17:53", "remaining_time": "12:33:31"}
|
||||
{"current_steps": 124, "total_steps": 273, "loss": 0.4347, "lr": 5.333212691635368e-05, "epoch": 1.3577014620877252, "percentage": 45.42, "elapsed_time": "10:22:47", "remaining_time": "12:28:21"}
|
||||
{"current_steps": 125, "total_steps": 273, "loss": 0.4337, "lr": 5.2847459552305834e-05, "epoch": 1.3685821149268955, "percentage": 45.79, "elapsed_time": "10:27:42", "remaining_time": "12:23:12"}
|
||||
{"current_steps": 126, "total_steps": 273, "loss": 0.4384, "lr": 5.23606797749979e-05, "epoch": 1.379462767766066, "percentage": 46.15, "elapsed_time": "10:32:37", "remaining_time": "12:18:03"}
|
||||
{"current_steps": 127, "total_steps": 273, "loss": 0.4444, "lr": 5.1871867622047624e-05, "epoch": 1.3903434206052363, "percentage": 46.52, "elapsed_time": "10:37:31", "remaining_time": "12:12:54"}
|
||||
{"current_steps": 128, "total_steps": 273, "loss": 0.4371, "lr": 5.13811034652413e-05, "epoch": 1.4012240734444066, "percentage": 46.89, "elapsed_time": "10:42:26", "remaining_time": "12:07:46"}
|
||||
{"current_steps": 129, "total_steps": 273, "loss": 0.4342, "lr": 5.088846799731885e-05, "epoch": 1.412104726283577, "percentage": 47.25, "elapsed_time": "10:47:21", "remaining_time": "12:02:37"}
|
||||
{"current_steps": 130, "total_steps": 273, "loss": 0.4296, "lr": 5.039404221870612e-05, "epoch": 1.4229853791227474, "percentage": 47.62, "elapsed_time": "10:52:15", "remaining_time": "11:57:29"}
|
||||
{"current_steps": 131, "total_steps": 273, "loss": 0.4415, "lr": 4.989790742419658e-05, "epoch": 1.4338660319619176, "percentage": 47.99, "elapsed_time": "10:58:09", "remaining_time": "11:53:25"}
|
||||
{"current_steps": 132, "total_steps": 273, "loss": 0.4338, "lr": 4.940014518958461e-05, "epoch": 1.4447466848010881, "percentage": 48.35, "elapsed_time": "11:03:04", "remaining_time": "11:48:16"}
|
||||
{"current_steps": 133, "total_steps": 273, "loss": 0.4397, "lr": 4.890083735825258e-05, "epoch": 1.4556273376402584, "percentage": 48.72, "elapsed_time": "11:07:58", "remaining_time": "11:43:07"}
|
||||
{"current_steps": 134, "total_steps": 273, "loss": 0.4271, "lr": 4.8400066027713974e-05, "epoch": 1.4665079904794287, "percentage": 49.08, "elapsed_time": "11:12:52", "remaining_time": "11:37:59"}
|
||||
{"current_steps": 135, "total_steps": 273, "loss": 0.4229, "lr": 4.789791353611469e-05, "epoch": 1.4773886433185992, "percentage": 49.45, "elapsed_time": "11:17:47", "remaining_time": "11:32:50"}
|
||||
{"current_steps": 136, "total_steps": 273, "loss": 0.4383, "lr": 4.7394462448694756e-05, "epoch": 1.4882692961577695, "percentage": 49.82, "elapsed_time": "11:22:42", "remaining_time": "11:27:43"}
|
||||
{"current_steps": 137, "total_steps": 273, "loss": 0.4307, "lr": 4.688979554421276e-05, "epoch": 1.4991499489969398, "percentage": 50.18, "elapsed_time": "11:27:36", "remaining_time": "11:22:35"}
|
||||
{"current_steps": 138, "total_steps": 273, "loss": 0.4413, "lr": 4.6383995801335176e-05, "epoch": 1.5100306018361103, "percentage": 50.55, "elapsed_time": "11:32:30", "remaining_time": "11:17:27"}
|
||||
{"current_steps": 139, "total_steps": 273, "loss": 0.4343, "lr": 4.5877146384992725e-05, "epoch": 1.5209112546752805, "percentage": 50.92, "elapsed_time": "11:37:24", "remaining_time": "11:12:19"}
|
||||
{"current_steps": 140, "total_steps": 273, "loss": 0.4304, "lr": 4.5369330632706223e-05, "epoch": 1.5317919075144508, "percentage": 51.28, "elapsed_time": "11:42:19", "remaining_time": "11:07:12"}
|
||||
{"current_steps": 141, "total_steps": 273, "loss": 0.433, "lr": 4.486063204088402e-05, "epoch": 1.5426725603536213, "percentage": 51.65, "elapsed_time": "11:48:10", "remaining_time": "11:02:57"}
|
||||
{"current_steps": 142, "total_steps": 273, "loss": 0.4298, "lr": 4.435113425109324e-05, "epoch": 1.5535532131927916, "percentage": 52.01, "elapsed_time": "11:53:05", "remaining_time": "10:57:50"}
|
||||
{"current_steps": 143, "total_steps": 273, "loss": 0.4348, "lr": 4.3840921036307274e-05, "epoch": 1.5644338660319619, "percentage": 52.38, "elapsed_time": "11:57:59", "remaining_time": "10:52:43"}
|
||||
{"current_steps": 144, "total_steps": 273, "loss": 0.4384, "lr": 4.333007628713158e-05, "epoch": 1.5753145188711324, "percentage": 52.75, "elapsed_time": "12:02:54", "remaining_time": "10:47:36"}
|
||||
{"current_steps": 145, "total_steps": 273, "loss": 0.4362, "lr": 4.281868399801016e-05, "epoch": 1.5861951717103027, "percentage": 53.11, "elapsed_time": "12:07:49", "remaining_time": "10:42:29"}
|
||||
{"current_steps": 146, "total_steps": 273, "loss": 0.4321, "lr": 4.230682825341498e-05, "epoch": 1.597075824549473, "percentage": 53.48, "elapsed_time": "12:12:43", "remaining_time": "10:37:22"}
|
||||
{"current_steps": 147, "total_steps": 273, "loss": 0.4343, "lr": 4.17945932140206e-05, "epoch": 1.6079564773886434, "percentage": 53.85, "elapsed_time": "12:17:38", "remaining_time": "10:32:15"}
|
||||
{"current_steps": 148, "total_steps": 273, "loss": 0.4319, "lr": 4.128206310286622e-05, "epoch": 1.6188371302278135, "percentage": 54.21, "elapsed_time": "12:22:33", "remaining_time": "10:27:09"}
|
||||
{"current_steps": 149, "total_steps": 273, "loss": 0.4349, "lr": 4.0769322191507485e-05, "epoch": 1.629717783066984, "percentage": 54.58, "elapsed_time": "12:27:28", "remaining_time": "10:22:03"}
|
||||
{"current_steps": 150, "total_steps": 273, "loss": 0.4286, "lr": 4.025645478616045e-05, "epoch": 1.6405984359061545, "percentage": 54.95, "elapsed_time": "12:32:23", "remaining_time": "10:16:57"}
|
||||
{"current_steps": 151, "total_steps": 273, "loss": 0.4326, "lr": 3.974354521383956e-05, "epoch": 1.6514790887453246, "percentage": 55.31, "elapsed_time": "12:38:18", "remaining_time": "10:12:40"}
|
||||
{"current_steps": 152, "total_steps": 273, "loss": 0.4325, "lr": 3.923067780849252e-05, "epoch": 1.662359741584495, "percentage": 55.68, "elapsed_time": "12:43:13", "remaining_time": "10:07:33"}
|
||||
{"current_steps": 153, "total_steps": 273, "loss": 0.4269, "lr": 3.87179368971338e-05, "epoch": 1.6732403944236656, "percentage": 56.04, "elapsed_time": "12:48:07", "remaining_time": "10:02:26"}
|
||||
{"current_steps": 154, "total_steps": 273, "loss": 0.4352, "lr": 3.820540678597942e-05, "epoch": 1.6841210472628356, "percentage": 56.41, "elapsed_time": "12:53:01", "remaining_time": "9:57:20"}
|
||||
{"current_steps": 155, "total_steps": 273, "loss": 0.4331, "lr": 3.769317174658503e-05, "epoch": 1.6950017001020061, "percentage": 56.78, "elapsed_time": "12:57:55", "remaining_time": "9:52:13"}
|
||||
{"current_steps": 156, "total_steps": 273, "loss": 0.4385, "lr": 3.718131600198984e-05, "epoch": 1.7058823529411766, "percentage": 57.14, "elapsed_time": "13:02:49", "remaining_time": "9:47:07"}
|
||||
{"current_steps": 157, "total_steps": 273, "loss": 0.4313, "lr": 3.666992371286843e-05, "epoch": 1.7167630057803467, "percentage": 57.51, "elapsed_time": "13:07:51", "remaining_time": "9:42:06"}
|
||||
{"current_steps": 158, "total_steps": 273, "loss": 0.442, "lr": 3.615907896369273e-05, "epoch": 1.7276436586195172, "percentage": 57.88, "elapsed_time": "13:12:47", "remaining_time": "9:37:01"}
|
||||
{"current_steps": 159, "total_steps": 273, "loss": 0.4376, "lr": 3.564886574890677e-05, "epoch": 1.7385243114586875, "percentage": 58.24, "elapsed_time": "13:17:41", "remaining_time": "9:31:55"}
|
||||
{"current_steps": 160, "total_steps": 273, "loss": 0.438, "lr": 3.5139367959115986e-05, "epoch": 1.7494049642978577, "percentage": 58.61, "elapsed_time": "13:22:36", "remaining_time": "9:26:50"}
|
||||
{"current_steps": 161, "total_steps": 273, "loss": 0.4301, "lr": 3.4630669367293797e-05, "epoch": 1.7602856171370282, "percentage": 58.97, "elapsed_time": "13:28:32", "remaining_time": "9:22:28"}
|
||||
{"current_steps": 162, "total_steps": 273, "loss": 0.4365, "lr": 3.412285361500729e-05, "epoch": 1.7711662699761985, "percentage": 59.34, "elapsed_time": "13:33:28", "remaining_time": "9:17:22"}
|
||||
{"current_steps": 163, "total_steps": 273, "loss": 0.4261, "lr": 3.3616004198664845e-05, "epoch": 1.7820469228153688, "percentage": 59.71, "elapsed_time": "13:38:22", "remaining_time": "9:12:16"}
|
||||
{"current_steps": 164, "total_steps": 273, "loss": 0.4358, "lr": 3.311020445578725e-05, "epoch": 1.7929275756545393, "percentage": 60.07, "elapsed_time": "13:43:17", "remaining_time": "9:07:11"}
|
||||
{"current_steps": 165, "total_steps": 273, "loss": 0.4317, "lr": 3.260553755130525e-05, "epoch": 1.8038082284937096, "percentage": 60.44, "elapsed_time": "13:48:11", "remaining_time": "9:02:05"}
|
||||
{"current_steps": 166, "total_steps": 273, "loss": 0.4201, "lr": 3.210208646388532e-05, "epoch": 1.8146888813328799, "percentage": 60.81, "elapsed_time": "13:53:06", "remaining_time": "8:57:00"}
|
||||
{"current_steps": 167, "total_steps": 273, "loss": 0.4296, "lr": 3.1599933972286026e-05, "epoch": 1.8255695341720504, "percentage": 61.17, "elapsed_time": "13:58:01", "remaining_time": "8:51:54"}
|
||||
{"current_steps": 168, "total_steps": 273, "loss": 0.4252, "lr": 3.109916264174743e-05, "epoch": 1.8364501870112206, "percentage": 61.54, "elapsed_time": "14:02:55", "remaining_time": "8:46:49"}
|
||||
{"current_steps": 169, "total_steps": 273, "loss": 0.4201, "lr": 3.0599854810415393e-05, "epoch": 1.847330839850391, "percentage": 61.9, "elapsed_time": "14:07:50", "remaining_time": "8:41:44"}
|
||||
{"current_steps": 170, "total_steps": 273, "loss": 0.4343, "lr": 3.0102092575803435e-05, "epoch": 1.8582114926895614, "percentage": 62.27, "elapsed_time": "14:12:53", "remaining_time": "8:36:45"}
|
||||
{"current_steps": 171, "total_steps": 273, "loss": 0.4388, "lr": 2.9605957781293893e-05, "epoch": 1.8690921455287317, "percentage": 62.64, "elapsed_time": "14:18:48", "remaining_time": "8:32:16"}
|
||||
{"current_steps": 172, "total_steps": 273, "loss": 0.4361, "lr": 2.911153200268116e-05, "epoch": 1.879972798367902, "percentage": 63.0, "elapsed_time": "14:23:42", "remaining_time": "8:27:10"}
|
||||
{"current_steps": 173, "total_steps": 273, "loss": 0.4303, "lr": 2.8618896534758707e-05, "epoch": 1.8908534512070725, "percentage": 63.37, "elapsed_time": "14:28:37", "remaining_time": "8:22:05"}
|
||||
{"current_steps": 174, "total_steps": 273, "loss": 0.4332, "lr": 2.8128132377952376e-05, "epoch": 1.9017341040462428, "percentage": 63.74, "elapsed_time": "14:33:34", "remaining_time": "8:17:02"}
|
||||
{"current_steps": 175, "total_steps": 273, "loss": 0.4228, "lr": 2.7639320225002108e-05, "epoch": 1.912614756885413, "percentage": 64.1, "elapsed_time": "14:38:29", "remaining_time": "8:11:57"}
|
||||
{"current_steps": 176, "total_steps": 273, "loss": 0.4282, "lr": 2.715254044769418e-05, "epoch": 1.9234954097245835, "percentage": 64.47, "elapsed_time": "14:43:24", "remaining_time": "8:06:52"}
|
||||
{"current_steps": 177, "total_steps": 273, "loss": 0.4284, "lr": 2.666787308364634e-05, "epoch": 1.9343760625637538, "percentage": 64.84, "elapsed_time": "14:48:18", "remaining_time": "8:01:47"}
|
||||
{"current_steps": 178, "total_steps": 273, "loss": 0.4265, "lr": 2.6185397823147703e-05, "epoch": 1.945256715402924, "percentage": 65.2, "elapsed_time": "14:53:12", "remaining_time": "7:56:42"}
|
||||
{"current_steps": 179, "total_steps": 273, "loss": 0.4255, "lr": 2.5705193996055977e-05, "epoch": 1.9561373682420946, "percentage": 65.57, "elapsed_time": "14:58:07", "remaining_time": "7:51:38"}
|
||||
{"current_steps": 180, "total_steps": 273, "loss": 0.4267, "lr": 2.5227340558753755e-05, "epoch": 1.967018021081265, "percentage": 65.93, "elapsed_time": "15:03:01", "remaining_time": "7:46:33"}
|
||||
{"current_steps": 181, "total_steps": 273, "loss": 0.4322, "lr": 2.4751916081166336e-05, "epoch": 1.9778986739204352, "percentage": 66.3, "elapsed_time": "15:09:01", "remaining_time": "7:42:02"}
|
||||
{"current_steps": 182, "total_steps": 273, "loss": 0.4237, "lr": 2.427899873384306e-05, "epoch": 1.9887793267596057, "percentage": 66.67, "elapsed_time": "15:13:56", "remaining_time": "7:36:58"}
|
||||
{"current_steps": 183, "total_steps": 273, "loss": 0.4132, "lr": 2.3808666275104248e-05, "epoch": 2.0081604896293777, "percentage": 67.03, "elapsed_time": "15:19:04", "remaining_time": "7:32:00"}
|
||||
{"current_steps": 184, "total_steps": 273, "loss": 0.4088, "lr": 2.334099603825605e-05, "epoch": 2.019041142468548, "percentage": 67.4, "elapsed_time": "15:23:59", "remaining_time": "7:26:55"}
|
||||
{"current_steps": 185, "total_steps": 273, "loss": 0.4049, "lr": 2.2876064918874993e-05, "epoch": 2.0299217953077187, "percentage": 67.77, "elapsed_time": "15:28:53", "remaining_time": "7:21:51"}
|
||||
{"current_steps": 186, "total_steps": 273, "loss": 0.3949, "lr": 2.241394936216472e-05, "epoch": 2.0408024481468887, "percentage": 68.13, "elapsed_time": "15:33:47", "remaining_time": "7:16:46"}
|
||||
{"current_steps": 187, "total_steps": 273, "loss": 0.4004, "lr": 2.1954725350386614e-05, "epoch": 2.051683100986059, "percentage": 68.5, "elapsed_time": "15:38:43", "remaining_time": "7:11:42"}
|
||||
{"current_steps": 188, "total_steps": 273, "loss": 0.4047, "lr": 2.14984683903666e-05, "epoch": 2.0625637538252297, "percentage": 68.86, "elapsed_time": "15:43:38", "remaining_time": "7:06:38"}
|
||||
{"current_steps": 189, "total_steps": 273, "loss": 0.4029, "lr": 2.1045253501080058e-05, "epoch": 2.0734444066643998, "percentage": 69.23, "elapsed_time": "15:48:32", "remaining_time": "7:01:34"}
|
||||
{"current_steps": 190, "total_steps": 273, "loss": 0.4033, "lr": 2.0595155201317115e-05, "epoch": 2.0843250595035703, "percentage": 69.6, "elapsed_time": "15:53:27", "remaining_time": "6:56:30"}
|
||||
{"current_steps": 191, "total_steps": 273, "loss": 0.4035, "lr": 2.0148247497430012e-05, "epoch": 2.095205712342741, "percentage": 69.96, "elapsed_time": "15:59:30", "remaining_time": "6:51:56"}
|
||||
{"current_steps": 192, "total_steps": 273, "loss": 0.4003, "lr": 1.970460387116472e-05, "epoch": 2.106086365181911, "percentage": 70.33, "elapsed_time": "16:04:26", "remaining_time": "6:46:52"}
|
||||
{"current_steps": 193, "total_steps": 273, "loss": 0.4, "lr": 1.9264297267579e-05, "epoch": 2.1169670180210813, "percentage": 70.7, "elapsed_time": "16:09:21", "remaining_time": "6:41:48"}
|
||||
{"current_steps": 194, "total_steps": 273, "loss": 0.4032, "lr": 1.8827400083048503e-05, "epoch": 2.127847670860252, "percentage": 71.06, "elapsed_time": "16:14:16", "remaining_time": "6:36:44"}
|
||||
{"current_steps": 195, "total_steps": 273, "loss": 0.4084, "lr": 1.8393984153363203e-05, "epoch": 2.138728323699422, "percentage": 71.43, "elapsed_time": "16:19:11", "remaining_time": "6:31:40"}
|
||||
{"current_steps": 196, "total_steps": 273, "loss": 0.4021, "lr": 1.7964120741915905e-05, "epoch": 2.1496089765385924, "percentage": 71.79, "elapsed_time": "16:24:06", "remaining_time": "6:26:36"}
|
||||
{"current_steps": 197, "total_steps": 273, "loss": 0.4063, "lr": 1.753788052798501e-05, "epoch": 2.1604896293777625, "percentage": 72.16, "elapsed_time": "16:29:01", "remaining_time": "6:21:33"}
|
||||
{"current_steps": 198, "total_steps": 273, "loss": 0.4093, "lr": 1.7115333595113225e-05, "epoch": 2.171370282216933, "percentage": 72.53, "elapsed_time": "16:33:57", "remaining_time": "6:16:29"}
|
||||
{"current_steps": 199, "total_steps": 273, "loss": 0.3998, "lr": 1.669654941958416e-05, "epoch": 2.1822509350561035, "percentage": 72.89, "elapsed_time": "16:38:52", "remaining_time": "6:11:26"}
|
||||
{"current_steps": 200, "total_steps": 273, "loss": 0.404, "lr": 1.628159685899897e-05, "epoch": 2.1931315878952735, "percentage": 73.26, "elapsed_time": "16:43:46", "remaining_time": "6:06:22"}
|
||||
{"current_steps": 201, "total_steps": 273, "loss": 0.4029, "lr": 1.5870544140954543e-05, "epoch": 2.204012240734444, "percentage": 73.63, "elapsed_time": "16:49:53", "remaining_time": "6:01:45"}
|
||||
{"current_steps": 202, "total_steps": 273, "loss": 0.4034, "lr": 1.5463458851825345e-05, "epoch": 2.2148928935736145, "percentage": 73.99, "elapsed_time": "16:54:48", "remaining_time": "5:56:41"}
|
||||
{"current_steps": 203, "total_steps": 273, "loss": 0.4047, "lr": 1.5060407925650662e-05, "epoch": 2.2257735464127846, "percentage": 74.36, "elapsed_time": "16:59:43", "remaining_time": "5:51:37"}
|
||||
{"current_steps": 204, "total_steps": 273, "loss": 0.4028, "lr": 1.466145763312922e-05, "epoch": 2.236654199251955, "percentage": 74.73, "elapsed_time": "17:04:38", "remaining_time": "5:46:34"}
|
||||
{"current_steps": 205, "total_steps": 273, "loss": 0.4057, "lr": 1.426667357072265e-05, "epoch": 2.2475348520911256, "percentage": 75.09, "elapsed_time": "17:09:33", "remaining_time": "5:41:30"}
|
||||
{"current_steps": 206, "total_steps": 273, "loss": 0.401, "lr": 1.3876120649870051e-05, "epoch": 2.2584155049302956, "percentage": 75.46, "elapsed_time": "17:14:28", "remaining_time": "5:36:27"}
|
||||
{"current_steps": 207, "total_steps": 273, "loss": 0.406, "lr": 1.3489863086315085e-05, "epoch": 2.269296157769466, "percentage": 75.82, "elapsed_time": "17:19:22", "remaining_time": "5:31:23"}
|
||||
{"current_steps": 208, "total_steps": 273, "loss": 0.4105, "lr": 1.3107964389547326e-05, "epoch": 2.2801768106086366, "percentage": 76.19, "elapsed_time": "17:24:17", "remaining_time": "5:26:20"}
|
||||
{"current_steps": 209, "total_steps": 273, "loss": 0.3986, "lr": 1.2730487352360026e-05, "epoch": 2.2910574634478067, "percentage": 76.56, "elapsed_time": "17:29:12", "remaining_time": "5:21:17"}
|
||||
{"current_steps": 210, "total_steps": 273, "loss": 0.4026, "lr": 1.2357494040525416e-05, "epoch": 2.301938116286977, "percentage": 76.92, "elapsed_time": "17:34:07", "remaining_time": "5:16:14"}
|
||||
{"current_steps": 211, "total_steps": 273, "loss": 0.4019, "lr": 1.1989045782589815e-05, "epoch": 2.3128187691261477, "percentage": 77.29, "elapsed_time": "17:40:02", "remaining_time": "5:11:28"}
|
||||
{"current_steps": 212, "total_steps": 273, "loss": 0.404, "lr": 1.1625203159789686e-05, "epoch": 2.3236994219653178, "percentage": 77.66, "elapsed_time": "17:44:57", "remaining_time": "5:06:25"}
|
||||
{"current_steps": 213, "total_steps": 273, "loss": 0.3968, "lr": 1.1266025996090902e-05, "epoch": 2.3345800748044883, "percentage": 78.02, "elapsed_time": "17:49:52", "remaining_time": "5:01:22"}
|
||||
{"current_steps": 214, "total_steps": 273, "loss": 0.3997, "lr": 1.0911573348352107e-05, "epoch": 2.3454607276436588, "percentage": 78.39, "elapsed_time": "17:54:47", "remaining_time": "4:56:19"}
|
||||
{"current_steps": 215, "total_steps": 273, "loss": 0.4019, "lr": 1.0561903496614603e-05, "epoch": 2.356341380482829, "percentage": 78.75, "elapsed_time": "17:59:42", "remaining_time": "4:51:16"}
|
||||
{"current_steps": 216, "total_steps": 273, "loss": 0.3961, "lr": 1.0217073934519726e-05, "epoch": 2.3672220333219993, "percentage": 79.12, "elapsed_time": "18:04:36", "remaining_time": "4:46:13"}
|
||||
{"current_steps": 217, "total_steps": 273, "loss": 0.4107, "lr": 9.877141359855567e-06, "epoch": 2.37810268616117, "percentage": 79.49, "elapsed_time": "18:09:31", "remaining_time": "4:41:10"}
|
||||
{"current_steps": 218, "total_steps": 273, "loss": 0.4041, "lr": 9.542161665234623e-06, "epoch": 2.38898333900034, "percentage": 79.85, "elapsed_time": "18:14:25", "remaining_time": "4:36:07"}
|
||||
{"current_steps": 219, "total_steps": 273, "loss": 0.4057, "lr": 9.212189928903758e-06, "epoch": 2.3998639918395104, "percentage": 80.22, "elapsed_time": "18:19:20", "remaining_time": "4:31:04"}
|
||||
{"current_steps": 220, "total_steps": 273, "loss": 0.4035, "lr": 8.887280405688106e-06, "epoch": 2.410744644678681, "percentage": 80.59, "elapsed_time": "18:24:15", "remaining_time": "4:26:01"}
|
||||
{"current_steps": 221, "total_steps": 273, "loss": 0.3979, "lr": 8.567486518070306e-06, "epoch": 2.421625297517851, "percentage": 80.95, "elapsed_time": "18:30:14", "remaining_time": "4:21:13"}
|
||||
{"current_steps": 222, "total_steps": 273, "loss": 0.4007, "lr": 8.252860847406712e-06, "epoch": 2.4325059503570214, "percentage": 81.32, "elapsed_time": "18:35:09", "remaining_time": "4:16:11"}
|
||||
{"current_steps": 223, "total_steps": 273, "loss": 0.4038, "lr": 7.943455125281741e-06, "epoch": 2.443386603196192, "percentage": 81.68, "elapsed_time": "18:40:04", "remaining_time": "4:11:08"}
|
||||
{"current_steps": 224, "total_steps": 273, "loss": 0.3987, "lr": 7.639320225002106e-06, "epoch": 2.454267256035362, "percentage": 82.05, "elapsed_time": "18:44:59", "remaining_time": "4:06:05"}
|
||||
{"current_steps": 225, "total_steps": 273, "loss": 0.4051, "lr": 7.340506153232052e-06, "epoch": 2.4651479088745325, "percentage": 82.42, "elapsed_time": "18:49:53", "remaining_time": "4:01:02"}
|
||||
{"current_steps": 226, "total_steps": 273, "loss": 0.4038, "lr": 7.047062041771133e-06, "epoch": 2.476028561713703, "percentage": 82.78, "elapsed_time": "18:54:48", "remaining_time": "3:55:59"}
|
||||
{"current_steps": 227, "total_steps": 273, "loss": 0.4035, "lr": 6.759036139475843e-06, "epoch": 2.486909214552873, "percentage": 83.15, "elapsed_time": "18:59:43", "remaining_time": "3:50:57"}
|
||||
{"current_steps": 228, "total_steps": 273, "loss": 0.3945, "lr": 6.476475804326377e-06, "epoch": 2.4977898673920436, "percentage": 83.52, "elapsed_time": "19:04:37", "remaining_time": "3:45:54"}
|
||||
{"current_steps": 229, "total_steps": 273, "loss": 0.3953, "lr": 6.199427495639963e-06, "epoch": 2.508670520231214, "percentage": 83.88, "elapsed_time": "19:09:32", "remaining_time": "3:40:52"}
|
||||
{"current_steps": 230, "total_steps": 273, "loss": 0.3951, "lr": 5.927936766431836e-06, "epoch": 2.519551173070384, "percentage": 84.25, "elapsed_time": "19:14:26", "remaining_time": "3:35:49"}
|
||||
{"current_steps": 231, "total_steps": 273, "loss": 0.4007, "lr": 5.662048255925357e-06, "epoch": 2.5304318259095546, "percentage": 84.62, "elapsed_time": "19:20:31", "remaining_time": "3:31:00"}
|
||||
{"current_steps": 232, "total_steps": 273, "loss": 0.3956, "lr": 5.40180568221226e-06, "epoch": 2.5413124787487247, "percentage": 84.98, "elapsed_time": "19:25:31", "remaining_time": "3:25:58"}
|
||||
{"current_steps": 233, "total_steps": 273, "loss": 0.401, "lr": 5.147251835064424e-06, "epoch": 2.552193131587895, "percentage": 85.35, "elapsed_time": "19:30:28", "remaining_time": "3:20:56"}
|
||||
{"current_steps": 234, "total_steps": 273, "loss": 0.4018, "lr": 4.898428568898288e-06, "epoch": 2.5630737844270657, "percentage": 85.71, "elapsed_time": "19:35:23", "remaining_time": "3:15:53"}
|
||||
{"current_steps": 235, "total_steps": 273, "loss": 0.4033, "lr": 4.65537679589299e-06, "epoch": 2.573954437266236, "percentage": 86.08, "elapsed_time": "19:40:21", "remaining_time": "3:10:51"}
|
||||
{"current_steps": 236, "total_steps": 273, "loss": 0.3957, "lr": 4.418136479263533e-06, "epoch": 2.5848350901054062, "percentage": 86.45, "elapsed_time": "19:45:16", "remaining_time": "3:05:49"}
|
||||
{"current_steps": 237, "total_steps": 273, "loss": 0.3978, "lr": 4.186746626689879e-06, "epoch": 2.5957157429445767, "percentage": 86.81, "elapsed_time": "19:50:11", "remaining_time": "3:00:47"}
|
||||
{"current_steps": 238, "total_steps": 273, "loss": 0.4004, "lr": 3.961245283903239e-06, "epoch": 2.606596395783747, "percentage": 87.18, "elapsed_time": "19:55:06", "remaining_time": "2:55:45"}
|
||||
{"current_steps": 239, "total_steps": 273, "loss": 0.4062, "lr": 3.7416695284304737e-06, "epoch": 2.6174770486229173, "percentage": 87.55, "elapsed_time": "20:00:00", "remaining_time": "2:50:42"}
|
||||
{"current_steps": 240, "total_steps": 273, "loss": 0.3974, "lr": 3.5280554634977217e-06, "epoch": 2.628357701462088, "percentage": 87.91, "elapsed_time": "20:04:55", "remaining_time": "2:45:40"}
|
||||
{"current_steps": 241, "total_steps": 273, "loss": 0.4021, "lr": 3.320438212094197e-06, "epoch": 2.6392383543012583, "percentage": 88.28, "elapsed_time": "20:10:53", "remaining_time": "2:40:46"}
|
||||
{"current_steps": 242, "total_steps": 273, "loss": 0.4046, "lr": 3.1188519111971804e-06, "epoch": 2.6501190071404284, "percentage": 88.64, "elapsed_time": "20:15:52", "remaining_time": "2:35:45"}
|
||||
{"current_steps": 243, "total_steps": 273, "loss": 0.3986, "lr": 2.9233297061591346e-06, "epoch": 2.660999659979599, "percentage": 89.01, "elapsed_time": "20:20:49", "remaining_time": "2:30:43"}
|
||||
{"current_steps": 244, "total_steps": 273, "loss": 0.4143, "lr": 2.733903745257838e-06, "epoch": 2.671880312818769, "percentage": 89.38, "elapsed_time": "20:25:43", "remaining_time": "2:25:40"}
|
||||
{"current_steps": 245, "total_steps": 273, "loss": 0.3982, "lr": 2.550605174410512e-06, "epoch": 2.6827609656579394, "percentage": 89.74, "elapsed_time": "20:30:38", "remaining_time": "2:20:38"}
|
||||
{"current_steps": 246, "total_steps": 273, "loss": 0.3975, "lr": 2.373464132052701e-06, "epoch": 2.69364161849711, "percentage": 90.11, "elapsed_time": "20:35:33", "remaining_time": "2:15:36"}
|
||||
{"current_steps": 247, "total_steps": 273, "loss": 0.3958, "lr": 2.202509744182835e-06, "epoch": 2.7045222713362804, "percentage": 90.48, "elapsed_time": "20:40:27", "remaining_time": "2:10:34"}
|
||||
{"current_steps": 248, "total_steps": 273, "loss": 0.4094, "lr": 2.0377701195732545e-06, "epoch": 2.7154029241754505, "percentage": 90.84, "elapsed_time": "20:45:22", "remaining_time": "2:05:32"}
|
||||
{"current_steps": 249, "total_steps": 273, "loss": 0.4071, "lr": 1.879272345148513e-06, "epoch": 2.726283577014621, "percentage": 91.21, "elapsed_time": "20:50:17", "remaining_time": "2:00:30"}
|
||||
{"current_steps": 250, "total_steps": 273, "loss": 0.3997, "lr": 1.727042481531651e-06, "epoch": 2.737164229853791, "percentage": 91.58, "elapsed_time": "21:00:05", "remaining_time": "1:55:55"}
|
||||
{"current_steps": 251, "total_steps": 273, "loss": 0.4032, "lr": 1.5811055587592283e-06, "epoch": 2.7480448826929615, "percentage": 91.94, "elapsed_time": "21:06:10", "remaining_time": "1:50:58"}
|
||||
{"current_steps": 252, "total_steps": 273, "loss": 0.4011, "lr": 1.4414855721658705e-06, "epoch": 2.758925535532132, "percentage": 92.31, "elapsed_time": "21:11:05", "remaining_time": "1:45:55"}
|
||||
{"current_steps": 253, "total_steps": 273, "loss": 0.3938, "lr": 1.3082054784388221e-06, "epoch": 2.7698061883713025, "percentage": 92.67, "elapsed_time": "21:17:30", "remaining_time": "1:40:59"}
|
||||
{"current_steps": 254, "total_steps": 273, "loss": 0.4036, "lr": 1.1812871918434143e-06, "epoch": 2.7806868412104726, "percentage": 93.04, "elapsed_time": "21:22:26", "remaining_time": "1:35:55"}
|
||||
{"current_steps": 255, "total_steps": 273, "loss": 0.3975, "lr": 1.0607515806198142e-06, "epoch": 2.791567494049643, "percentage": 93.41, "elapsed_time": "21:27:21", "remaining_time": "1:30:52"}
|
||||
{"current_steps": 256, "total_steps": 273, "loss": 0.397, "lr": 9.466184635518361e-07, "epoch": 2.802448146888813, "percentage": 93.77, "elapsed_time": "21:32:16", "remaining_time": "1:25:48"}
|
||||
{"current_steps": 257, "total_steps": 273, "loss": 0.4011, "lr": 8.389066067082852e-07, "epoch": 2.8133287997279837, "percentage": 94.14, "elapsed_time": "21:37:11", "remaining_time": "1:20:45"}
|
||||
{"current_steps": 258, "total_steps": 273, "loss": 0.4, "lr": 7.376337203573824e-07, "epoch": 2.824209452567154, "percentage": 94.51, "elapsed_time": "21:42:06", "remaining_time": "1:15:42"}
|
||||
{"current_steps": 259, "total_steps": 273, "loss": 0.4021, "lr": 6.428164560548134e-07, "epoch": 2.8350901054063242, "percentage": 94.87, "elapsed_time": "21:47:01", "remaining_time": "1:10:38"}
|
||||
{"current_steps": 260, "total_steps": 273, "loss": 0.4001, "lr": 5.544704039058025e-07, "epoch": 2.8459707582454947, "percentage": 95.24, "elapsed_time": "21:51:56", "remaining_time": "1:05:35"}
|
||||
{"current_steps": 261, "total_steps": 273, "loss": 0.4025, "lr": 4.7261009000177274e-07, "epoch": 2.8568514110846652, "percentage": 95.6, "elapsed_time": "21:58:01", "remaining_time": "1:00:35"}
|
||||
{"current_steps": 262, "total_steps": 273, "loss": 0.4091, "lr": 3.972489740319274e-07, "epoch": 2.8677320639238353, "percentage": 95.97, "elapsed_time": "22:02:56", "remaining_time": "0:55:32"}
|
||||
{"current_steps": 263, "total_steps": 273, "loss": 0.4055, "lr": 3.283994470701579e-07, "epoch": 2.878612716763006, "percentage": 96.34, "elapsed_time": "22:07:51", "remaining_time": "0:50:29"}
|
||||
{"current_steps": 264, "total_steps": 273, "loss": 0.408, "lr": 2.66072829537678e-07, "epoch": 2.8894933696021763, "percentage": 96.7, "elapsed_time": "22:13:36", "remaining_time": "0:45:27"}
|
||||
{"current_steps": 265, "total_steps": 273, "loss": 0.402, "lr": 2.102793693417038e-07, "epoch": 2.9003740224413463, "percentage": 97.07, "elapsed_time": "22:18:31", "remaining_time": "0:40:24"}
|
||||
{"current_steps": 266, "total_steps": 273, "loss": 0.3985, "lr": 1.6102824019043728e-07, "epoch": 2.911254675280517, "percentage": 97.44, "elapsed_time": "22:23:28", "remaining_time": "0:35:21"}
|
||||
{"current_steps": 267, "total_steps": 273, "loss": 0.4025, "lr": 1.1832754008472614e-07, "epoch": 2.9221353281196873, "percentage": 97.8, "elapsed_time": "22:28:23", "remaining_time": "0:30:18"}
|
||||
{"current_steps": 268, "total_steps": 273, "loss": 0.3962, "lr": 8.21842899865466e-08, "epoch": 2.9330159809588574, "percentage": 98.17, "elapsed_time": "22:33:18", "remaining_time": "0:25:14"}
|
||||
{"current_steps": 269, "total_steps": 273, "loss": 0.3982, "lr": 5.260443266462467e-08, "epoch": 2.943896633798028, "percentage": 98.53, "elapsed_time": "22:38:13", "remaining_time": "0:20:11"}
|
||||
{"current_steps": 270, "total_steps": 273, "loss": 0.3988, "lr": 2.9592831717293326e-08, "epoch": 2.9547772866371984, "percentage": 98.9, "elapsed_time": "22:43:08", "remaining_time": "0:15:08"}
|
||||
{"current_steps": 271, "total_steps": 273, "loss": 0.4009, "lr": 1.3153270772807702e-08, "epoch": 2.9656579394763685, "percentage": 99.27, "elapsed_time": "22:49:08", "remaining_time": "0:10:06"}
|
||||
{"current_steps": 272, "total_steps": 273, "loss": 0.4001, "lr": 3.2884528672294523e-09, "epoch": 2.976538592315539, "percentage": 99.63, "elapsed_time": "22:54:02", "remaining_time": "0:05:03"}
|
||||
{"current_steps": 273, "total_steps": 273, "loss": 0.4048, "lr": 0.0, "epoch": 2.987419245154709, "percentage": 100.0, "elapsed_time": "22:58:57", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 273, "total_steps": 273, "epoch": 2.987419245154709, "percentage": 100.0, "elapsed_time": "23:00:31", "remaining_time": "0:00:00"}
|
||||
1953
trainer_state.json
Normal file
1953
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 sha256:024e44e8f58081460e46ed90f950bf3675b7224673f19f7df6844c3dace2a452
|
||||
size 7352
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 29 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