初始化项目，由ModelHub XC社区提供模型
Model: ahmedheakl/cass-smA100-7b 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
|
||||
66
README.md
Normal file
66
README.md
Normal file
@@ -0,0 +1,66 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: ex42_qwen2.5_7b_92k_15kcw_3ep_cuda_amd_os
|
||||
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. -->
|
||||
|
||||
# ex42_qwen2.5_7b_92k_15kcw_3ep_cuda_amd_os
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on an unknown 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: 2e-05
|
||||
- train_batch_size: 2
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 7
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 112
|
||||
- total_eval_batch_size: 56
|
||||
- optimizer: Use OptimizerNames.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 4.50.0
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 3.4.1
|
||||
- Tokenizers 0.21.0
|
||||
|
||||
## 🔗 Useful Links
|
||||
|
||||
* 🤗 Hugging Face Collection: [CASS on Hugging Face](https://huggingface.co/collections/MBZUAI/cass-6825b5bf7414503cf16f87b2)
|
||||
* 📂 Code & Tools: [GitHub Repository](https://github.com/GustavoStahl/CASS)
|
||||
* Paper: [Arxiv CASS](https://arxiv.org/abs/2505.16968)
|
||||
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
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"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": 131072,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.50.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.50.0"
|
||||
}
|
||||
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:fa02bd5d19303828463d080ae71c1cccce09a88a88dbc201ca5cf31c12c32c60
|
||||
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 sha256:7bbc3197e8327f0ec1d34cd35a13e194453ee524f3c1c2ecde2b5c165d557532
|
||||
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 sha256:5ee6b91176e280477f260d84781d8a09ddb03e7408b8c9bcbbc774b3c3467b75
|
||||
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 sha256:418c021834f96977c7da43be2f50d2f6738bac83891344ad322dfea63444315a
|
||||
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": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
210
tokenizer_config.json
Normal file
210
tokenizer_config.json
Normal file
@@ -0,0 +1,210 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"low_cpu_mem_usage": true,
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
249
trainer_log.jsonl
Normal file
249
trainer_log.jsonl
Normal file
@@ -0,0 +1,249 @@
|
||||
{"current_steps": 10, "total_steps": 2481, "loss": 0.5609, "lr": 8.032128514056225e-07, "epoch": 0.012088244182532487, "percentage": 0.4, "elapsed_time": "0:40:39", "remaining_time": "6 days, 23:25:48"}
|
||||
{"current_steps": 20, "total_steps": 2481, "loss": 0.4953, "lr": 1.606425702811245e-06, "epoch": 0.024176488365064974, "percentage": 0.81, "elapsed_time": "1:21:47", "remaining_time": "6 days, 23:44:18"}
|
||||
{"current_steps": 30, "total_steps": 2481, "loss": 0.3109, "lr": 2.4096385542168676e-06, "epoch": 0.03626473254759746, "percentage": 1.21, "elapsed_time": "2:02:28", "remaining_time": "6 days, 22:46:40"}
|
||||
{"current_steps": 40, "total_steps": 2481, "loss": 0.1601, "lr": 3.21285140562249e-06, "epoch": 0.04835297673012995, "percentage": 1.61, "elapsed_time": "2:43:05", "remaining_time": "6 days, 21:52:23"}
|
||||
{"current_steps": 50, "total_steps": 2481, "loss": 0.1074, "lr": 4.016064257028113e-06, "epoch": 0.060441220912662436, "percentage": 2.02, "elapsed_time": "3:23:55", "remaining_time": "6 days, 21:14:35"}
|
||||
{"current_steps": 60, "total_steps": 2481, "loss": 0.0879, "lr": 4.819277108433735e-06, "epoch": 0.07252946509519492, "percentage": 2.42, "elapsed_time": "4:04:50", "remaining_time": "6 days, 20:39:13"}
|
||||
{"current_steps": 70, "total_steps": 2481, "loss": 0.0784, "lr": 5.622489959839358e-06, "epoch": 0.08461770927772741, "percentage": 2.82, "elapsed_time": "4:45:24", "remaining_time": "6 days, 19:50:09"}
|
||||
{"current_steps": 80, "total_steps": 2481, "loss": 0.067, "lr": 6.42570281124498e-06, "epoch": 0.0967059534602599, "percentage": 3.22, "elapsed_time": "5:25:39", "remaining_time": "6 days, 18:53:48"}
|
||||
{"current_steps": 90, "total_steps": 2481, "loss": 0.0607, "lr": 7.228915662650603e-06, "epoch": 0.10879419764279238, "percentage": 3.63, "elapsed_time": "6:06:37", "remaining_time": "6 days, 18:19:58"}
|
||||
{"current_steps": 100, "total_steps": 2481, "loss": 0.0562, "lr": 8.032128514056226e-06, "epoch": 0.12088244182532487, "percentage": 4.03, "elapsed_time": "6:47:26", "remaining_time": "6 days, 17:41:09"}
|
||||
{"current_steps": 110, "total_steps": 2481, "loss": 0.0531, "lr": 8.835341365461849e-06, "epoch": 0.13297068600785736, "percentage": 4.43, "elapsed_time": "7:28:15", "remaining_time": "6 days, 17:02:04"}
|
||||
{"current_steps": 120, "total_steps": 2481, "loss": 0.0497, "lr": 9.63855421686747e-06, "epoch": 0.14505893019038985, "percentage": 4.84, "elapsed_time": "8:08:54", "remaining_time": "6 days, 16:19:15"}
|
||||
{"current_steps": 130, "total_steps": 2481, "loss": 0.0471, "lr": 1.0441767068273094e-05, "epoch": 0.15714717437292233, "percentage": 5.24, "elapsed_time": "8:49:42", "remaining_time": "6 days, 15:39:35"}
|
||||
{"current_steps": 140, "total_steps": 2481, "loss": 0.0453, "lr": 1.1244979919678715e-05, "epoch": 0.16923541855545482, "percentage": 5.64, "elapsed_time": "9:30:33", "remaining_time": "6 days, 15:00:25"}
|
||||
{"current_steps": 150, "total_steps": 2481, "loss": 0.0425, "lr": 1.204819277108434e-05, "epoch": 0.1813236627379873, "percentage": 6.05, "elapsed_time": "10:11:36", "remaining_time": "6 days, 14:24:22"}
|
||||
{"current_steps": 160, "total_steps": 2481, "loss": 0.0421, "lr": 1.285140562248996e-05, "epoch": 0.1934119069205198, "percentage": 6.45, "elapsed_time": "10:52:40", "remaining_time": "6 days, 13:47:51"}
|
||||
{"current_steps": 170, "total_steps": 2481, "loss": 0.0389, "lr": 1.3654618473895585e-05, "epoch": 0.20550015110305228, "percentage": 6.85, "elapsed_time": "11:33:11", "remaining_time": "6 days, 13:03:18"}
|
||||
{"current_steps": 180, "total_steps": 2481, "loss": 0.0369, "lr": 1.4457831325301207e-05, "epoch": 0.21758839528558477, "percentage": 7.26, "elapsed_time": "12:13:39", "remaining_time": "6 days, 12:18:36"}
|
||||
{"current_steps": 190, "total_steps": 2481, "loss": 0.0359, "lr": 1.526104417670683e-05, "epoch": 0.22967663946811726, "percentage": 7.66, "elapsed_time": "12:54:06", "remaining_time": "6 days, 11:34:01"}
|
||||
{"current_steps": 200, "total_steps": 2481, "loss": 0.0344, "lr": 1.606425702811245e-05, "epoch": 0.24176488365064974, "percentage": 8.06, "elapsed_time": "13:35:01", "remaining_time": "6 days, 10:55:20"}
|
||||
{"current_steps": 210, "total_steps": 2481, "loss": 0.0333, "lr": 1.6867469879518076e-05, "epoch": 0.25385312783318226, "percentage": 8.46, "elapsed_time": "14:16:22", "remaining_time": "6 days, 10:21:07"}
|
||||
{"current_steps": 220, "total_steps": 2481, "loss": 0.0346, "lr": 1.7670682730923698e-05, "epoch": 0.2659413720157147, "percentage": 8.87, "elapsed_time": "14:57:30", "remaining_time": "6 days, 9:43:54"}
|
||||
{"current_steps": 230, "total_steps": 2481, "loss": 0.0337, "lr": 1.847389558232932e-05, "epoch": 0.27802961619824723, "percentage": 9.27, "elapsed_time": "15:38:27", "remaining_time": "6 days, 9:04:38"}
|
||||
{"current_steps": 240, "total_steps": 2481, "loss": 0.0328, "lr": 1.927710843373494e-05, "epoch": 0.2901178603807797, "percentage": 9.67, "elapsed_time": "16:19:31", "remaining_time": "6 days, 8:26:21"}
|
||||
{"current_steps": 250, "total_steps": 2481, "loss": 0.0301, "lr": 1.9999990094388352e-05, "epoch": 0.3022061045633122, "percentage": 10.08, "elapsed_time": "17:00:15", "remaining_time": "6 days, 7:44:51"}
|
||||
{"current_steps": 260, "total_steps": 2481, "loss": 0.0266, "lr": 1.9998801444735345e-05, "epoch": 0.31429434874584466, "percentage": 10.48, "elapsed_time": "17:41:27", "remaining_time": "6 days, 7:07:18"}
|
||||
{"current_steps": 270, "total_steps": 2481, "loss": 0.0306, "lr": 1.9995631942576458e-05, "epoch": 0.3263825929283772, "percentage": 10.88, "elapsed_time": "18:22:08", "remaining_time": "6 days, 6:25:22"}
|
||||
{"current_steps": 280, "total_steps": 2481, "loss": 0.0267, "lr": 1.999048221581858e-05, "epoch": 0.33847083711090964, "percentage": 11.29, "elapsed_time": "19:03:14", "remaining_time": "6 days, 5:46:38"}
|
||||
{"current_steps": 290, "total_steps": 2481, "loss": 0.0284, "lr": 1.99833532846689e-05, "epoch": 0.35055908129344215, "percentage": 11.69, "elapsed_time": "19:44:07", "remaining_time": "6 days, 5:06:12"}
|
||||
{"current_steps": 300, "total_steps": 2481, "loss": 0.0253, "lr": 1.9974246561432806e-05, "epoch": 0.3626473254759746, "percentage": 12.09, "elapsed_time": "20:24:54", "remaining_time": "6 days, 4:25:04"}
|
||||
{"current_steps": 310, "total_steps": 2481, "loss": 0.0281, "lr": 1.9963163850234086e-05, "epoch": 0.37473556965850713, "percentage": 12.49, "elapsed_time": "21:06:14", "remaining_time": "6 days, 3:47:48"}
|
||||
{"current_steps": 320, "total_steps": 2481, "loss": 0.0266, "lr": 1.9950107346657517e-05, "epoch": 0.3868238138410396, "percentage": 12.9, "elapsed_time": "21:46:51", "remaining_time": "6 days, 3:05:23"}
|
||||
{"current_steps": 330, "total_steps": 2481, "loss": 0.0271, "lr": 1.9935079637313906e-05, "epoch": 0.3989120580235721, "percentage": 13.3, "elapsed_time": "22:28:09", "remaining_time": "6 days, 2:27:31"}
|
||||
{"current_steps": 340, "total_steps": 2481, "loss": 0.025, "lr": 1.9918083699327642e-05, "epoch": 0.41100030220610456, "percentage": 13.7, "elapsed_time": "23:08:41", "remaining_time": "6 days, 1:44:41"}
|
||||
{"current_steps": 350, "total_steps": 2481, "loss": 0.0281, "lr": 1.9899122899746922e-05, "epoch": 0.4230885463886371, "percentage": 14.11, "elapsed_time": "23:49:41", "remaining_time": "6 days, 1:04:48"}
|
||||
{"current_steps": 360, "total_steps": 2481, "loss": 0.0252, "lr": 1.98782009948767e-05, "epoch": 0.43517679057116954, "percentage": 14.51, "elapsed_time": "1 day, 0:30:37", "remaining_time": "6 days, 0:24:25"}
|
||||
{"current_steps": 370, "total_steps": 2481, "loss": 0.0243, "lr": 1.985532212953452e-05, "epoch": 0.44726503475370205, "percentage": 14.91, "elapsed_time": "1 day, 1:11:39", "remaining_time": "5 days, 23:44:37"}
|
||||
{"current_steps": 380, "total_steps": 2481, "loss": 0.0225, "lr": 1.98304908362294e-05, "epoch": 0.4593532789362345, "percentage": 15.32, "elapsed_time": "1 day, 1:52:30", "remaining_time": "5 days, 23:03:46"}
|
||||
{"current_steps": 390, "total_steps": 2481, "loss": 0.0239, "lr": 1.980371203426391e-05, "epoch": 0.471441523118767, "percentage": 15.72, "elapsed_time": "1 day, 2:33:47", "remaining_time": "5 days, 22:25:12"}
|
||||
{"current_steps": 400, "total_steps": 2481, "loss": 0.0223, "lr": 1.9774991028759593e-05, "epoch": 0.4835297673012995, "percentage": 16.12, "elapsed_time": "1 day, 3:14:36", "remaining_time": "5 days, 21:44:04"}
|
||||
{"current_steps": 410, "total_steps": 2481, "loss": 0.023, "lr": 1.9744333509605982e-05, "epoch": 0.495618011483832, "percentage": 16.53, "elapsed_time": "1 day, 3:57:07", "remaining_time": "5 days, 21:11:30"}
|
||||
{"current_steps": 420, "total_steps": 2481, "loss": 0.0233, "lr": 1.9711745550333392e-05, "epoch": 0.5077062556663645, "percentage": 16.93, "elapsed_time": "1 day, 4:38:16", "remaining_time": "5 days, 20:31:47"}
|
||||
{"current_steps": 430, "total_steps": 2481, "loss": 0.0216, "lr": 1.9677233606909683e-05, "epoch": 0.5197944998488969, "percentage": 17.33, "elapsed_time": "1 day, 5:19:18", "remaining_time": "5 days, 19:51:28"}
|
||||
{"current_steps": 440, "total_steps": 2481, "loss": 0.0231, "lr": 1.9640804516461288e-05, "epoch": 0.5318827440314294, "percentage": 17.73, "elapsed_time": "1 day, 5:59:43", "remaining_time": "5 days, 19:08:16"}
|
||||
{"current_steps": 450, "total_steps": 2481, "loss": 0.0206, "lr": 1.9602465495918697e-05, "epoch": 0.543970988213962, "percentage": 18.14, "elapsed_time": "1 day, 6:40:20", "remaining_time": "5 days, 18:26:06"}
|
||||
{"current_steps": 460, "total_steps": 2481, "loss": 0.0216, "lr": 1.9562224140586747e-05, "epoch": 0.5560592323964945, "percentage": 18.54, "elapsed_time": "1 day, 7:21:12", "remaining_time": "5 days, 17:45:01"}
|
||||
{"current_steps": 470, "total_steps": 2481, "loss": 0.0208, "lr": 1.9520088422639903e-05, "epoch": 0.5681474765790269, "percentage": 18.94, "elapsed_time": "1 day, 8:01:25", "remaining_time": "5 days, 17:01:15"}
|
||||
{"current_steps": 480, "total_steps": 2481, "loss": 0.0219, "lr": 1.94760666895429e-05, "epoch": 0.5802357207615594, "percentage": 19.35, "elapsed_time": "1 day, 8:41:49", "remaining_time": "5 days, 16:18:22"}
|
||||
{"current_steps": 490, "total_steps": 2481, "loss": 0.0215, "lr": 1.9430167662397043e-05, "epoch": 0.5923239649440919, "percentage": 19.75, "elapsed_time": "1 day, 9:22:37", "remaining_time": "5 days, 15:37:13"}
|
||||
{"current_steps": 500, "total_steps": 2481, "loss": 0.0211, "lr": 1.9382400434212476e-05, "epoch": 0.6044122091266244, "percentage": 20.15, "elapsed_time": "1 day, 10:03:18", "remaining_time": "5 days, 14:55:33"}
|
||||
{"current_steps": 510, "total_steps": 2481, "loss": 0.0203, "lr": 1.933277446810677e-05, "epoch": 0.6165004533091568, "percentage": 20.56, "elapsed_time": "1 day, 10:44:01", "remaining_time": "5 days, 14:14:07"}
|
||||
{"current_steps": 520, "total_steps": 2481, "loss": 0.02, "lr": 1.928129959543019e-05, "epoch": 0.6285886974916893, "percentage": 20.96, "elapsed_time": "1 day, 11:24:23", "remaining_time": "5 days, 13:31:22"}
|
||||
{"current_steps": 530, "total_steps": 2481, "loss": 0.0201, "lr": 1.9227986013818046e-05, "epoch": 0.6406769416742218, "percentage": 21.36, "elapsed_time": "1 day, 12:04:40", "remaining_time": "5 days, 12:48:27"}
|
||||
{"current_steps": 540, "total_steps": 2481, "loss": 0.0202, "lr": 1.9172844285170404e-05, "epoch": 0.6527651858567544, "percentage": 21.77, "elapsed_time": "1 day, 12:44:45", "remaining_time": "5 days, 12:04:53"}
|
||||
{"current_steps": 550, "total_steps": 2481, "loss": 0.0194, "lr": 1.911588533355971e-05, "epoch": 0.6648534300392868, "percentage": 22.17, "elapsed_time": "1 day, 13:25:20", "remaining_time": "5 days, 11:23:11"}
|
||||
{"current_steps": 560, "total_steps": 2481, "loss": 0.0182, "lr": 1.9057120443066637e-05, "epoch": 0.6769416742218193, "percentage": 22.57, "elapsed_time": "1 day, 14:05:53", "remaining_time": "5 days, 10:41:24"}
|
||||
{"current_steps": 570, "total_steps": 2481, "loss": 0.0207, "lr": 1.8996561255544575e-05, "epoch": 0.6890299184043518, "percentage": 22.97, "elapsed_time": "1 day, 14:46:14", "remaining_time": "5 days, 9:59:02"}
|
||||
{"current_steps": 580, "total_steps": 2481, "loss": 0.0198, "lr": 1.8934219768313308e-05, "epoch": 0.7011181625868843, "percentage": 23.38, "elapsed_time": "1 day, 15:26:51", "remaining_time": "5 days, 9:17:33"}
|
||||
{"current_steps": 590, "total_steps": 2481, "loss": 0.0191, "lr": 1.887010833178222e-05, "epoch": 0.7132064067694167, "percentage": 23.78, "elapsed_time": "1 day, 16:07:17", "remaining_time": "5 days, 8:35:33"}
|
||||
{"current_steps": 600, "total_steps": 2481, "loss": 0.0202, "lr": 1.8804239647003574e-05, "epoch": 0.7252946509519492, "percentage": 24.18, "elapsed_time": "1 day, 16:47:26", "remaining_time": "5 days, 7:52:45"}
|
||||
{"current_steps": 610, "total_steps": 2481, "loss": 0.0208, "lr": 1.8736626763156317e-05, "epoch": 0.7373828951344817, "percentage": 24.59, "elapsed_time": "1 day, 17:29:01", "remaining_time": "5 days, 7:14:22"}
|
||||
{"current_steps": 620, "total_steps": 2481, "loss": 0.0189, "lr": 1.866728307496092e-05, "epoch": 0.7494711393170143, "percentage": 24.99, "elapsed_time": "1 day, 18:09:32", "remaining_time": "5 days, 6:32:43"}
|
||||
{"current_steps": 630, "total_steps": 2481, "loss": 0.0182, "lr": 1.859622232002576e-05, "epoch": 0.7615593834995467, "percentage": 25.39, "elapsed_time": "1 day, 18:50:11", "remaining_time": "5 days, 5:51:27"}
|
||||
{"current_steps": 640, "total_steps": 2481, "loss": 0.0181, "lr": 1.852345857612559e-05, "epoch": 0.7736476276820792, "percentage": 25.8, "elapsed_time": "1 day, 19:31:09", "remaining_time": "5 days, 5:11:10"}
|
||||
{"current_steps": 650, "total_steps": 2481, "loss": 0.0189, "lr": 1.844900625841259e-05, "epoch": 0.7857358718646117, "percentage": 26.2, "elapsed_time": "1 day, 20:12:24", "remaining_time": "5 days, 4:31:38"}
|
||||
{"current_steps": 660, "total_steps": 2481, "loss": 0.0174, "lr": 1.8372880116560597e-05, "epoch": 0.7978241160471442, "percentage": 26.6, "elapsed_time": "1 day, 20:52:54", "remaining_time": "5 days, 3:49:58"}
|
||||
{"current_steps": 670, "total_steps": 2481, "loss": 0.0195, "lr": 1.8295095231843075e-05, "epoch": 0.8099123602296766, "percentage": 27.01, "elapsed_time": "1 day, 21:33:54", "remaining_time": "5 days, 3:09:42"}
|
||||
{"current_steps": 680, "total_steps": 2481, "loss": 0.0346, "lr": 1.821566701414536e-05, "epoch": 0.8220006044122091, "percentage": 27.41, "elapsed_time": "1 day, 22:14:18", "remaining_time": "5 days, 2:27:50"}
|
||||
{"current_steps": 690, "total_steps": 2481, "loss": 0.0245, "lr": 1.813461119891184e-05, "epoch": 0.8340888485947416, "percentage": 27.81, "elapsed_time": "1 day, 22:54:55", "remaining_time": "5 days, 1:46:34"}
|
||||
{"current_steps": 700, "total_steps": 2481, "loss": 0.0209, "lr": 1.8051943844028613e-05, "epoch": 0.8461770927772742, "percentage": 28.21, "elapsed_time": "1 day, 23:35:29", "remaining_time": "5 days, 1:05:12"}
|
||||
{"current_steps": 710, "total_steps": 2481, "loss": 0.0203, "lr": 1.7967681326642283e-05, "epoch": 0.8582653369598066, "percentage": 28.62, "elapsed_time": "2 days, 0:16:37", "remaining_time": "5 days, 0:25:15"}
|
||||
{"current_steps": 720, "total_steps": 2481, "loss": 0.0181, "lr": 1.7881840339915482e-05, "epoch": 0.8703535811423391, "percentage": 29.02, "elapsed_time": "2 days, 0:57:36", "remaining_time": "4 days, 23:44:55"}
|
||||
{"current_steps": 730, "total_steps": 2481, "loss": 0.0171, "lr": 1.779443788971983e-05, "epoch": 0.8824418253248716, "percentage": 29.42, "elapsed_time": "2 days, 1:38:28", "remaining_time": "4 days, 23:04:15"}
|
||||
{"current_steps": 740, "total_steps": 2481, "loss": 0.0192, "lr": 1.7705491291266896e-05, "epoch": 0.8945300695074041, "percentage": 29.83, "elapsed_time": "2 days, 2:19:23", "remaining_time": "4 days, 22:23:43"}
|
||||
{"current_steps": 750, "total_steps": 2481, "loss": 0.0176, "lr": 1.7615018165677916e-05, "epoch": 0.9066183136899365, "percentage": 30.23, "elapsed_time": "2 days, 3:00:02", "remaining_time": "4 days, 21:42:34"}
|
||||
{"current_steps": 760, "total_steps": 2481, "loss": 0.0191, "lr": 1.7523036436492873e-05, "epoch": 0.918706557872469, "percentage": 30.63, "elapsed_time": "2 days, 3:41:22", "remaining_time": "4 days, 21:02:59"}
|
||||
{"current_steps": 770, "total_steps": 2481, "loss": 0.0199, "lr": 1.7429564326119707e-05, "epoch": 0.9307948020550015, "percentage": 31.04, "elapsed_time": "2 days, 4:22:00", "remaining_time": "4 days, 20:21:48"}
|
||||
{"current_steps": 780, "total_steps": 2481, "loss": 0.0177, "lr": 1.733462035222426e-05, "epoch": 0.942883046237534, "percentage": 31.44, "elapsed_time": "2 days, 5:02:45", "remaining_time": "4 days, 19:40:51"}
|
||||
{"current_steps": 790, "total_steps": 2481, "loss": 0.0184, "lr": 1.7238223324061795e-05, "epoch": 0.9549712904200665, "percentage": 31.84, "elapsed_time": "2 days, 5:43:50", "remaining_time": "4 days, 19:00:38"}
|
||||
{"current_steps": 800, "total_steps": 2481, "loss": 0.0179, "lr": 1.7140392338750676e-05, "epoch": 0.967059534602599, "percentage": 32.25, "elapsed_time": "2 days, 6:24:12", "remaining_time": "4 days, 18:18:56"}
|
||||
{"current_steps": 810, "total_steps": 2481, "loss": 0.0175, "lr": 1.7041146777489097e-05, "epoch": 0.9791477787851315, "percentage": 32.65, "elapsed_time": "2 days, 7:05:47", "remaining_time": "4 days, 17:39:44"}
|
||||
{"current_steps": 820, "total_steps": 2481, "loss": 0.0182, "lr": 1.6940506301715458e-05, "epoch": 0.991236022967664, "percentage": 33.05, "elapsed_time": "2 days, 7:46:33", "remaining_time": "4 days, 16:58:49"}
|
||||
{"current_steps": 830, "total_steps": 2481, "loss": 0.0168, "lr": 1.683849084921328e-05, "epoch": 1.0024176488365064, "percentage": 33.45, "elapsed_time": "2 days, 8:24:12", "remaining_time": "4 days, 16:11:43"}
|
||||
{"current_steps": 840, "total_steps": 2481, "loss": 0.015, "lr": 1.6735120630161325e-05, "epoch": 1.014505893019039, "percentage": 33.86, "elapsed_time": "2 days, 9:04:59", "remaining_time": "4 days, 15:30:57"}
|
||||
{"current_steps": 850, "total_steps": 2481, "loss": 0.0147, "lr": 1.663041612312982e-05, "epoch": 1.0265941372015714, "percentage": 34.26, "elapsed_time": "2 days, 9:45:46", "remaining_time": "4 days, 14:50:13"}
|
||||
{"current_steps": 860, "total_steps": 2481, "loss": 0.0154, "lr": 1.6524398071023426e-05, "epoch": 1.038682381384104, "percentage": 34.66, "elapsed_time": "2 days, 10:26:49", "remaining_time": "4 days, 14:09:56"}
|
||||
{"current_steps": 870, "total_steps": 2481, "loss": 0.0146, "lr": 1.64170874769719e-05, "epoch": 1.0507706255666365, "percentage": 35.07, "elapsed_time": "2 days, 11:08:00", "remaining_time": "4 days, 13:29:56"}
|
||||
{"current_steps": 880, "total_steps": 2481, "loss": 0.0154, "lr": 1.630850560016919e-05, "epoch": 1.062858869749169, "percentage": 35.47, "elapsed_time": "2 days, 11:48:37", "remaining_time": "4 days, 12:48:51"}
|
||||
{"current_steps": 890, "total_steps": 2481, "loss": 0.0145, "lr": 1.619867395166179e-05, "epoch": 1.0749471139317015, "percentage": 35.87, "elapsed_time": "2 days, 12:29:41", "remaining_time": "4 days, 12:08:35"}
|
||||
{"current_steps": 900, "total_steps": 2481, "loss": 0.0158, "lr": 1.608761429008721e-05, "epoch": 1.087035358114234, "percentage": 36.28, "elapsed_time": "2 days, 13:10:44", "remaining_time": "4 days, 11:28:16"}
|
||||
{"current_steps": 910, "total_steps": 2481, "loss": 0.0146, "lr": 1.597534861736339e-05, "epoch": 1.0991236022967663, "percentage": 36.68, "elapsed_time": "2 days, 13:51:29", "remaining_time": "4 days, 10:47:25"}
|
||||
{"current_steps": 920, "total_steps": 2481, "loss": 0.0157, "lr": 1.5861899174329937e-05, "epoch": 1.1112118464792988, "percentage": 37.08, "elapsed_time": "2 days, 14:32:07", "remaining_time": "4 days, 10:06:23"}
|
||||
{"current_steps": 930, "total_steps": 2481, "loss": 0.0152, "lr": 1.5747288436341994e-05, "epoch": 1.1233000906618313, "percentage": 37.48, "elapsed_time": "2 days, 15:12:53", "remaining_time": "4 days, 9:25:33"}
|
||||
{"current_steps": 940, "total_steps": 2481, "loss": 0.0144, "lr": 1.563153910881769e-05, "epoch": 1.1353883348443639, "percentage": 37.89, "elapsed_time": "2 days, 15:53:34", "remaining_time": "4 days, 8:44:37"}
|
||||
{"current_steps": 950, "total_steps": 2481, "loss": 0.014, "lr": 1.5514674122739978e-05, "epoch": 1.1474765790268964, "percentage": 38.29, "elapsed_time": "2 days, 16:34:11", "remaining_time": "4 days, 8:03:33"}
|
||||
{"current_steps": 960, "total_steps": 2481, "loss": 0.0157, "lr": 1.53967166301138e-05, "epoch": 1.1595648232094289, "percentage": 38.69, "elapsed_time": "2 days, 17:15:00", "remaining_time": "4 days, 7:22:49"}
|
||||
{"current_steps": 970, "total_steps": 2481, "loss": 0.0131, "lr": 1.5277689999379484e-05, "epoch": 1.1716530673919614, "percentage": 39.1, "elapsed_time": "2 days, 17:55:52", "remaining_time": "4 days, 6:42:12"}
|
||||
{"current_steps": 980, "total_steps": 2481, "loss": 0.015, "lr": 1.5157617810783229e-05, "epoch": 1.1837413115744937, "percentage": 39.5, "elapsed_time": "2 days, 18:36:14", "remaining_time": "4 days, 6:00:46"}
|
||||
{"current_steps": 990, "total_steps": 2481, "loss": 0.0133, "lr": 1.5036523851705647e-05, "epoch": 1.1958295557570262, "percentage": 39.9, "elapsed_time": "2 days, 19:16:56", "remaining_time": "4 days, 5:19:53"}
|
||||
{"current_steps": 1000, "total_steps": 2481, "loss": 0.0126, "lr": 1.491443211194928e-05, "epoch": 1.2079177999395587, "percentage": 40.31, "elapsed_time": "2 days, 19:57:50", "remaining_time": "4 days, 4:39:17"}
|
||||
{"current_steps": 1010, "total_steps": 2481, "loss": 0.0144, "lr": 1.4791366778985992e-05, "epoch": 1.2200060441220912, "percentage": 40.71, "elapsed_time": "2 days, 20:40:10", "remaining_time": "4 days, 4:00:46"}
|
||||
{"current_steps": 1020, "total_steps": 2481, "loss": 0.0158, "lr": 1.4667352233165222e-05, "epoch": 1.2320942883046238, "percentage": 41.11, "elapsed_time": "2 days, 21:21:17", "remaining_time": "4 days, 3:20:25"}
|
||||
{"current_steps": 1030, "total_steps": 2481, "loss": 0.0138, "lr": 1.4542413042884013e-05, "epoch": 1.2441825324871563, "percentage": 41.52, "elapsed_time": "2 days, 22:02:15", "remaining_time": "4 days, 2:39:52"}
|
||||
{"current_steps": 1040, "total_steps": 2481, "loss": 0.0135, "lr": 1.44165739597198e-05, "epoch": 1.2562707766696888, "percentage": 41.92, "elapsed_time": "2 days, 22:43:19", "remaining_time": "4 days, 1:59:26"}
|
||||
{"current_steps": 1050, "total_steps": 2481, "loss": 0.0153, "lr": 1.4289859913526876e-05, "epoch": 1.2683590208522213, "percentage": 42.32, "elapsed_time": "2 days, 23:24:15", "remaining_time": "4 days, 1:18:49"}
|
||||
{"current_steps": 1060, "total_steps": 2481, "loss": 0.0149, "lr": 1.4162296007497597e-05, "epoch": 1.2804472650347538, "percentage": 42.72, "elapsed_time": "3 days, 0:05:17", "remaining_time": "4 days, 0:38:20"}
|
||||
{"current_steps": 1070, "total_steps": 2481, "loss": 0.0131, "lr": 1.4033907513189189e-05, "epoch": 1.292535509217286, "percentage": 43.13, "elapsed_time": "3 days, 0:45:40", "remaining_time": "3 days, 23:56:59"}
|
||||
{"current_steps": 1080, "total_steps": 2481, "loss": 0.0129, "lr": 1.3904719865517233e-05, "epoch": 1.3046237533998186, "percentage": 43.53, "elapsed_time": "3 days, 1:26:54", "remaining_time": "3 days, 23:16:44"}
|
||||
{"current_steps": 1090, "total_steps": 2481, "loss": 0.0146, "lr": 1.3774758657716785e-05, "epoch": 1.3167119975823511, "percentage": 43.93, "elapsed_time": "3 days, 2:07:40", "remaining_time": "3 days, 22:35:52"}
|
||||
{"current_steps": 1100, "total_steps": 2481, "loss": 0.0141, "lr": 1.3644049636272115e-05, "epoch": 1.3288002417648836, "percentage": 44.34, "elapsed_time": "3 days, 2:48:10", "remaining_time": "3 days, 21:54:42"}
|
||||
{"current_steps": 1110, "total_steps": 2481, "loss": 0.0146, "lr": 1.3512618695816105e-05, "epoch": 1.3408884859474162, "percentage": 44.74, "elapsed_time": "3 days, 3:29:04", "remaining_time": "3 days, 21:14:00"}
|
||||
{"current_steps": 1120, "total_steps": 2481, "loss": 0.0142, "lr": 1.338049187400029e-05, "epoch": 1.3529767301299487, "percentage": 45.14, "elapsed_time": "3 days, 4:09:40", "remaining_time": "3 days, 20:32:57"}
|
||||
{"current_steps": 1130, "total_steps": 2481, "loss": 0.0137, "lr": 1.3247695346336553e-05, "epoch": 1.3650649743124812, "percentage": 45.55, "elapsed_time": "3 days, 4:50:10", "remaining_time": "3 days, 19:51:49"}
|
||||
{"current_steps": 1140, "total_steps": 2481, "loss": 0.0134, "lr": 1.311425542101154e-05, "epoch": 1.3771532184950135, "percentage": 45.95, "elapsed_time": "3 days, 5:30:41", "remaining_time": "3 days, 19:10:40"}
|
||||
{"current_steps": 1150, "total_steps": 2481, "loss": 0.0146, "lr": 1.2980198533674753e-05, "epoch": 1.3892414626775462, "percentage": 46.35, "elapsed_time": "3 days, 6:11:29", "remaining_time": "3 days, 18:29:53"}
|
||||
{"current_steps": 1160, "total_steps": 2481, "loss": 0.0144, "lr": 1.284555124220142e-05, "epoch": 1.4013297068600785, "percentage": 46.76, "elapsed_time": "3 days, 6:52:36", "remaining_time": "3 days, 17:49:27"}
|
||||
{"current_steps": 1170, "total_steps": 2481, "loss": 0.0141, "lr": 1.2710340221431143e-05, "epoch": 1.413417951042611, "percentage": 47.16, "elapsed_time": "3 days, 7:33:11", "remaining_time": "3 days, 17:08:25"}
|
||||
{"current_steps": 1180, "total_steps": 2481, "loss": 0.0125, "lr": 1.257459225788337e-05, "epoch": 1.4255061952251435, "percentage": 47.56, "elapsed_time": "3 days, 8:13:40", "remaining_time": "3 days, 16:27:16"}
|
||||
{"current_steps": 1190, "total_steps": 2481, "loss": 0.0139, "lr": 1.2438334244450731e-05, "epoch": 1.437594439407676, "percentage": 47.96, "elapsed_time": "3 days, 8:54:29", "remaining_time": "3 days, 15:46:30"}
|
||||
{"current_steps": 1200, "total_steps": 2481, "loss": 0.0126, "lr": 1.2301593175071341e-05, "epoch": 1.4496826835902086, "percentage": 48.37, "elapsed_time": "3 days, 9:35:10", "remaining_time": "3 days, 15:05:36"}
|
||||
{"current_steps": 1210, "total_steps": 2481, "loss": 0.0141, "lr": 1.2164396139381029e-05, "epoch": 1.461770927772741, "percentage": 48.77, "elapsed_time": "3 days, 10:16:40", "remaining_time": "3 days, 14:25:32"}
|
||||
{"current_steps": 1220, "total_steps": 2481, "loss": 0.0131, "lr": 1.2026770317346668e-05, "epoch": 1.4738591719552736, "percentage": 49.17, "elapsed_time": "3 days, 10:57:40", "remaining_time": "3 days, 13:44:57"}
|
||||
{"current_steps": 1230, "total_steps": 2481, "loss": 0.0127, "lr": 1.1888742973881544e-05, "epoch": 1.485947416137806, "percentage": 49.58, "elapsed_time": "3 days, 11:38:29", "remaining_time": "3 days, 13:04:10"}
|
||||
{"current_steps": 1240, "total_steps": 2481, "loss": 0.0118, "lr": 1.1750341453443966e-05, "epoch": 1.4980356603203384, "percentage": 49.98, "elapsed_time": "3 days, 12:19:05", "remaining_time": "3 days, 12:23:10"}
|
||||
{"current_steps": 1250, "total_steps": 2481, "loss": 0.0172, "lr": 1.1611593174620057e-05, "epoch": 1.510123904502871, "percentage": 50.38, "elapsed_time": "3 days, 12:59:46", "remaining_time": "3 days, 11:42:15"}
|
||||
{"current_steps": 1260, "total_steps": 2481, "loss": 0.0135, "lr": 1.1472525624691904e-05, "epoch": 1.5222121486854034, "percentage": 50.79, "elapsed_time": "3 days, 13:40:08", "remaining_time": "3 days, 11:01:02"}
|
||||
{"current_steps": 1270, "total_steps": 2481, "loss": 0.012, "lr": 1.133316635419206e-05, "epoch": 1.534300392867936, "percentage": 51.19, "elapsed_time": "3 days, 14:20:45", "remaining_time": "3 days, 10:20:04"}
|
||||
{"current_steps": 1280, "total_steps": 2481, "loss": 0.0122, "lr": 1.1193542971445564e-05, "epoch": 1.5463886370504685, "percentage": 51.59, "elapsed_time": "3 days, 15:01:44", "remaining_time": "3 days, 9:39:27"}
|
||||
{"current_steps": 1290, "total_steps": 2481, "loss": 0.0121, "lr": 1.1053683137100445e-05, "epoch": 1.558476881233001, "percentage": 52.0, "elapsed_time": "3 days, 15:42:32", "remaining_time": "3 days, 8:58:40"}
|
||||
{"current_steps": 1300, "total_steps": 2481, "loss": 0.0126, "lr": 1.0913614558647943e-05, "epoch": 1.5705651254155333, "percentage": 52.4, "elapsed_time": "3 days, 16:23:24", "remaining_time": "3 days, 8:17:56"}
|
||||
{"current_steps": 1310, "total_steps": 2481, "loss": 0.0127, "lr": 1.0773364984933363e-05, "epoch": 1.582653369598066, "percentage": 52.8, "elapsed_time": "3 days, 17:04:05", "remaining_time": "3 days, 7:37:02"}
|
||||
{"current_steps": 1320, "total_steps": 2481, "loss": 0.0142, "lr": 1.0632962200658816e-05, "epoch": 1.5947416137805983, "percentage": 53.2, "elapsed_time": "3 days, 17:44:59", "remaining_time": "3 days, 6:56:20"}
|
||||
{"current_steps": 1330, "total_steps": 2481, "loss": 0.0138, "lr": 1.0492434020878797e-05, "epoch": 1.6068298579631308, "percentage": 53.61, "elapsed_time": "3 days, 18:25:49", "remaining_time": "3 days, 6:15:35"}
|
||||
{"current_steps": 1340, "total_steps": 2481, "loss": 0.0121, "lr": 1.0351808285489771e-05, "epoch": 1.6189181021456633, "percentage": 54.01, "elapsed_time": "3 days, 19:06:47", "remaining_time": "3 days, 5:34:55"}
|
||||
{"current_steps": 1350, "total_steps": 2481, "loss": 0.0138, "lr": 1.0211112853714859e-05, "epoch": 1.6310063463281959, "percentage": 54.41, "elapsed_time": "3 days, 19:47:19", "remaining_time": "3 days, 4:53:55"}
|
||||
{"current_steps": 1360, "total_steps": 2481, "loss": 0.0119, "lr": 1.0070375598584658e-05, "epoch": 1.6430945905107284, "percentage": 54.82, "elapsed_time": "3 days, 20:28:05", "remaining_time": "3 days, 4:13:05"}
|
||||
{"current_steps": 1370, "total_steps": 2481, "loss": 0.0144, "lr": 9.929624401415344e-06, "epoch": 1.6551828346932607, "percentage": 55.22, "elapsed_time": "3 days, 21:08:37", "remaining_time": "3 days, 3:32:05"}
|
||||
{"current_steps": 1380, "total_steps": 2481, "loss": 0.0135, "lr": 9.788887146285144e-06, "epoch": 1.6672710788757934, "percentage": 55.62, "elapsed_time": "3 days, 21:49:04", "remaining_time": "3 days, 2:51:01"}
|
||||
{"current_steps": 1390, "total_steps": 2481, "loss": 0.0123, "lr": 9.648191714510234e-06, "epoch": 1.6793593230583257, "percentage": 56.03, "elapsed_time": "3 days, 22:29:46", "remaining_time": "3 days, 2:10:10"}
|
||||
{"current_steps": 1400, "total_steps": 2481, "loss": 0.0121, "lr": 9.507565979121208e-06, "epoch": 1.6914475672408584, "percentage": 56.43, "elapsed_time": "3 days, 23:10:27", "remaining_time": "3 days, 1:29:17"}
|
||||
{"current_steps": 1410, "total_steps": 2481, "loss": 0.0161, "lr": 9.367037799341187e-06, "epoch": 1.7035358114233907, "percentage": 56.83, "elapsed_time": "3 days, 23:51:40", "remaining_time": "3 days, 0:48:49"}
|
||||
{"current_steps": 1420, "total_steps": 2481, "loss": 0.0125, "lr": 9.226635015066637e-06, "epoch": 1.7156240556059232, "percentage": 57.23, "elapsed_time": "4 days, 0:32:36", "remaining_time": "3 days, 0:08:08"}
|
||||
{"current_steps": 1430, "total_steps": 2481, "loss": 0.0135, "lr": 9.08638544135206e-06, "epoch": 1.7277122997884558, "percentage": 57.64, "elapsed_time": "4 days, 1:13:09", "remaining_time": "2 days, 23:27:09"}
|
||||
{"current_steps": 1440, "total_steps": 2481, "loss": 0.0129, "lr": 8.946316862899558e-06, "epoch": 1.7398005439709883, "percentage": 58.04, "elapsed_time": "4 days, 1:54:03", "remaining_time": "2 days, 22:46:26"}
|
||||
{"current_steps": 1450, "total_steps": 2481, "loss": 0.0132, "lr": 8.80645702855444e-06, "epoch": 1.7518887881535208, "percentage": 58.44, "elapsed_time": "4 days, 2:34:38", "remaining_time": "2 days, 22:05:30"}
|
||||
{"current_steps": 1460, "total_steps": 2481, "loss": 0.0134, "lr": 8.666833645807941e-06, "epoch": 1.763977032336053, "percentage": 58.85, "elapsed_time": "4 days, 3:15:36", "remaining_time": "2 days, 21:24:50"}
|
||||
{"current_steps": 1470, "total_steps": 2481, "loss": 0.0124, "lr": 8.527474375308103e-06, "epoch": 1.7760652765185858, "percentage": 59.25, "elapsed_time": "4 days, 3:56:15", "remaining_time": "2 days, 20:43:57"}
|
||||
{"current_steps": 1480, "total_steps": 2481, "loss": 0.0118, "lr": 8.388406825379945e-06, "epoch": 1.788153520701118, "percentage": 59.65, "elapsed_time": "4 days, 4:36:52", "remaining_time": "2 days, 20:03:02"}
|
||||
{"current_steps": 1490, "total_steps": 2481, "loss": 0.0133, "lr": 8.24965854655604e-06, "epoch": 1.8002417648836506, "percentage": 60.06, "elapsed_time": "4 days, 5:17:28", "remaining_time": "2 days, 19:22:07"}
|
||||
{"current_steps": 1500, "total_steps": 2481, "loss": 0.012, "lr": 8.111257026118461e-06, "epoch": 1.8123300090661831, "percentage": 60.46, "elapsed_time": "4 days, 5:58:04", "remaining_time": "2 days, 18:41:13"}
|
||||
{"current_steps": 1510, "total_steps": 2481, "loss": 0.0119, "lr": 7.973229682653337e-06, "epoch": 1.8244182532487156, "percentage": 60.86, "elapsed_time": "4 days, 6:38:37", "remaining_time": "2 days, 18:00:17"}
|
||||
{"current_steps": 1520, "total_steps": 2481, "loss": 0.0122, "lr": 7.835603860618973e-06, "epoch": 1.8365064974312482, "percentage": 61.27, "elapsed_time": "4 days, 7:19:35", "remaining_time": "2 days, 17:19:36"}
|
||||
{"current_steps": 1530, "total_steps": 2481, "loss": 0.0129, "lr": 7.69840682492866e-06, "epoch": 1.8485947416137805, "percentage": 61.67, "elapsed_time": "4 days, 8:00:11", "remaining_time": "2 days, 16:38:42"}
|
||||
{"current_steps": 1540, "total_steps": 2481, "loss": 0.0131, "lr": 7.5616657555492716e-06, "epoch": 1.8606829857963132, "percentage": 62.07, "elapsed_time": "4 days, 8:41:06", "remaining_time": "2 days, 15:57:59"}
|
||||
{"current_steps": 1550, "total_steps": 2481, "loss": 0.0126, "lr": 7.425407742116635e-06, "epoch": 1.8727712299788455, "percentage": 62.47, "elapsed_time": "4 days, 9:21:43", "remaining_time": "2 days, 15:17:06"}
|
||||
{"current_steps": 1560, "total_steps": 2481, "loss": 0.0127, "lr": 7.289659778568856e-06, "epoch": 1.8848594741613782, "percentage": 62.88, "elapsed_time": "4 days, 10:02:18", "remaining_time": "2 days, 14:36:12"}
|
||||
{"current_steps": 1570, "total_steps": 2481, "loss": 0.0114, "lr": 7.154448757798582e-06, "epoch": 1.8969477183439105, "percentage": 63.28, "elapsed_time": "4 days, 10:43:28", "remaining_time": "2 days, 13:55:39"}
|
||||
{"current_steps": 1580, "total_steps": 2481, "loss": 0.0125, "lr": 7.019801466325253e-06, "epoch": 1.909035962526443, "percentage": 63.68, "elapsed_time": "4 days, 11:24:29", "remaining_time": "2 days, 13:14:59"}
|
||||
{"current_steps": 1590, "total_steps": 2481, "loss": 0.0115, "lr": 6.885744578988463e-06, "epoch": 1.9211242067089755, "percentage": 64.09, "elapsed_time": "4 days, 12:05:03", "remaining_time": "2 days, 12:34:04"}
|
||||
{"current_steps": 1600, "total_steps": 2481, "loss": 0.0117, "lr": 6.752304653663451e-06, "epoch": 1.933212450891508, "percentage": 64.49, "elapsed_time": "4 days, 12:45:31", "remaining_time": "2 days, 11:53:07"}
|
||||
{"current_steps": 1610, "total_steps": 2481, "loss": 0.0129, "lr": 6.619508125999713e-06, "epoch": 1.9453006950740406, "percentage": 64.89, "elapsed_time": "4 days, 13:27:25", "remaining_time": "2 days, 11:12:56"}
|
||||
{"current_steps": 1620, "total_steps": 2481, "loss": 0.0125, "lr": 6.4873813041838975e-06, "epoch": 1.9573889392565729, "percentage": 65.3, "elapsed_time": "4 days, 14:07:51", "remaining_time": "2 days, 10:31:57"}
|
||||
{"current_steps": 1630, "total_steps": 2481, "loss": 0.0121, "lr": 6.3559503637278896e-06, "epoch": 1.9694771834391056, "percentage": 65.7, "elapsed_time": "4 days, 14:48:56", "remaining_time": "2 days, 9:51:19"}
|
||||
{"current_steps": 1640, "total_steps": 2481, "loss": 0.0117, "lr": 6.225241342283217e-06, "epoch": 1.981565427621638, "percentage": 66.1, "elapsed_time": "4 days, 15:29:28", "remaining_time": "2 days, 9:10:23"}
|
||||
{"current_steps": 1650, "total_steps": 2481, "loss": 0.0126, "lr": 6.095280134482771e-06, "epoch": 1.9936536718041704, "percentage": 66.51, "elapsed_time": "4 days, 16:09:58", "remaining_time": "2 days, 8:29:27"}
|
||||
{"current_steps": 1660, "total_steps": 2481, "loss": 0.0107, "lr": 5.966092486810818e-06, "epoch": 2.004835297673013, "percentage": 66.91, "elapsed_time": "4 days, 16:47:50", "remaining_time": "2 days, 7:47:13"}
|
||||
{"current_steps": 1670, "total_steps": 2481, "loss": 0.0096, "lr": 5.837703992502406e-06, "epoch": 2.0169235418555456, "percentage": 67.31, "elapsed_time": "4 days, 17:29:15", "remaining_time": "2 days, 7:06:46"}
|
||||
{"current_steps": 1680, "total_steps": 2481, "loss": 0.0085, "lr": 5.7101400864731294e-06, "epoch": 2.029011786038078, "percentage": 67.71, "elapsed_time": "4 days, 18:10:11", "remaining_time": "2 days, 6:26:04"}
|
||||
{"current_steps": 1690, "total_steps": 2481, "loss": 0.0095, "lr": 5.5834260402802055e-06, "epoch": 2.0411000302206106, "percentage": 68.12, "elapsed_time": "4 days, 18:51:23", "remaining_time": "2 days, 5:45:29"}
|
||||
{"current_steps": 1700, "total_steps": 2481, "loss": 0.0096, "lr": 5.457586957115988e-06, "epoch": 2.053188274403143, "percentage": 68.52, "elapsed_time": "4 days, 19:32:34", "remaining_time": "2 days, 5:04:54"}
|
||||
{"current_steps": 1710, "total_steps": 2481, "loss": 0.0088, "lr": 5.33264776683478e-06, "epoch": 2.0652765185856756, "percentage": 68.92, "elapsed_time": "4 days, 20:13:05", "remaining_time": "2 days, 4:24:00"}
|
||||
{"current_steps": 1720, "total_steps": 2481, "loss": 0.0092, "lr": 5.20863322101401e-06, "epoch": 2.077364762768208, "percentage": 69.33, "elapsed_time": "4 days, 20:53:57", "remaining_time": "2 days, 3:43:16"}
|
||||
{"current_steps": 1730, "total_steps": 2481, "loss": 0.0083, "lr": 5.085567888050722e-06, "epoch": 2.08945300695074, "percentage": 69.73, "elapsed_time": "4 days, 21:34:45", "remaining_time": "2 days, 3:02:30"}
|
||||
{"current_steps": 1740, "total_steps": 2481, "loss": 0.0099, "lr": 4.963476148294356e-06, "epoch": 2.101541251133273, "percentage": 70.13, "elapsed_time": "4 days, 22:15:39", "remaining_time": "2 days, 2:21:46"}
|
||||
{"current_steps": 1750, "total_steps": 2481, "loss": 0.0098, "lr": 4.8423821892167745e-06, "epoch": 2.1136294953158052, "percentage": 70.54, "elapsed_time": "4 days, 22:56:26", "remaining_time": "2 days, 1:40:59"}
|
||||
{"current_steps": 1760, "total_steps": 2481, "loss": 0.0088, "lr": 4.722310000620517e-06, "epoch": 2.125717739498338, "percentage": 70.94, "elapsed_time": "4 days, 23:37:16", "remaining_time": "2 days, 1:00:14"}
|
||||
{"current_steps": 1770, "total_steps": 2481, "loss": 0.0095, "lr": 4.603283369886205e-06, "epoch": 2.1378059836808703, "percentage": 71.34, "elapsed_time": "5 days, 0:18:05", "remaining_time": "2 days, 0:19:28"}
|
||||
{"current_steps": 1780, "total_steps": 2481, "loss": 0.0101, "lr": 4.485325877260025e-06, "epoch": 2.149894227863403, "percentage": 71.75, "elapsed_time": "5 days, 0:59:03", "remaining_time": "1 day, 23:38:45"}
|
||||
{"current_steps": 1790, "total_steps": 2481, "loss": 0.0103, "lr": 4.368460891182313e-06, "epoch": 2.1619824720459353, "percentage": 72.15, "elapsed_time": "5 days, 1:40:22", "remaining_time": "1 day, 22:58:11"}
|
||||
{"current_steps": 1800, "total_steps": 2481, "loss": 0.0093, "lr": 4.252711563658005e-06, "epoch": 2.174070716228468, "percentage": 72.55, "elapsed_time": "5 days, 2:21:32", "remaining_time": "1 day, 22:17:33"}
|
||||
{"current_steps": 1810, "total_steps": 2481, "loss": 0.0093, "lr": 4.138100825670068e-06, "epoch": 2.1861589604110003, "percentage": 72.95, "elapsed_time": "5 days, 3:03:13", "remaining_time": "1 day, 21:37:05"}
|
||||
{"current_steps": 1820, "total_steps": 2481, "loss": 0.01, "lr": 4.024651382636613e-06, "epoch": 2.1982472045935326, "percentage": 73.36, "elapsed_time": "5 days, 3:43:19", "remaining_time": "1 day, 20:56:03"}
|
||||
{"current_steps": 1830, "total_steps": 2481, "loss": 0.0086, "lr": 3.912385709912794e-06, "epoch": 2.2103354487760654, "percentage": 73.76, "elapsed_time": "5 days, 4:24:05", "remaining_time": "1 day, 20:15:15"}
|
||||
{"current_steps": 1840, "total_steps": 2481, "loss": 0.0101, "lr": 3.8013260483382143e-06, "epoch": 2.2224236929585977, "percentage": 74.16, "elapsed_time": "5 days, 5:05:00", "remaining_time": "1 day, 19:34:30"}
|
||||
{"current_steps": 1850, "total_steps": 2481, "loss": 0.0097, "lr": 3.691494399830813e-06, "epoch": 2.2345119371411304, "percentage": 74.57, "elapsed_time": "5 days, 5:45:42", "remaining_time": "1 day, 18:53:41"}
|
||||
{"current_steps": 1860, "total_steps": 2481, "loss": 0.0095, "lr": 3.5829125230281014e-06, "epoch": 2.2466001813236627, "percentage": 74.97, "elapsed_time": "5 days, 6:26:07", "remaining_time": "1 day, 18:12:47"}
|
||||
{"current_steps": 1870, "total_steps": 2481, "loss": 0.0096, "lr": 3.4756019289765765e-06, "epoch": 2.2586884255061954, "percentage": 75.37, "elapsed_time": "5 days, 7:06:38", "remaining_time": "1 day, 17:31:54"}
|
||||
{"current_steps": 1880, "total_steps": 2481, "loss": 0.0089, "lr": 3.3695838768701805e-06, "epoch": 2.2707766696887277, "percentage": 75.78, "elapsed_time": "5 days, 7:47:17", "remaining_time": "1 day, 16:51:05"}
|
||||
{"current_steps": 1890, "total_steps": 2481, "loss": 0.0091, "lr": 3.2648793698386747e-06, "epoch": 2.2828649138712604, "percentage": 76.18, "elapsed_time": "5 days, 8:28:23", "remaining_time": "1 day, 16:10:24"}
|
||||
{"current_steps": 1900, "total_steps": 2481, "loss": 0.0091, "lr": 3.161509150786728e-06, "epoch": 2.2949531580537927, "percentage": 76.58, "elapsed_time": "5 days, 9:09:07", "remaining_time": "1 day, 15:29:36"}
|
||||
{"current_steps": 1910, "total_steps": 2481, "loss": 0.0086, "lr": 3.0594936982845445e-06, "epoch": 2.307041402236325, "percentage": 76.99, "elapsed_time": "5 days, 9:50:04", "remaining_time": "1 day, 14:48:51"}
|
||||
{"current_steps": 1920, "total_steps": 2481, "loss": 0.0095, "lr": 2.958853222510906e-06, "epoch": 2.3191296464188578, "percentage": 77.39, "elapsed_time": "5 days, 10:30:47", "remaining_time": "1 day, 14:08:03"}
|
||||
{"current_steps": 1930, "total_steps": 2481, "loss": 0.01, "lr": 2.8596076612493282e-06, "epoch": 2.33121789060139, "percentage": 77.79, "elapsed_time": "5 days, 11:11:51", "remaining_time": "1 day, 13:27:21"}
|
||||
{"current_steps": 1940, "total_steps": 2481, "loss": 0.0078, "lr": 2.761776675938208e-06, "epoch": 2.343306134783923, "percentage": 78.19, "elapsed_time": "5 days, 11:52:33", "remaining_time": "1 day, 12:46:32"}
|
||||
{"current_steps": 1950, "total_steps": 2481, "loss": 0.0092, "lr": 2.665379647775743e-06, "epoch": 2.355394378966455, "percentage": 78.6, "elapsed_time": "5 days, 12:33:18", "remaining_time": "1 day, 12:05:44"}
|
||||
{"current_steps": 1960, "total_steps": 2481, "loss": 0.008, "lr": 2.5704356738802973e-06, "epoch": 2.3674826231489874, "percentage": 79.0, "elapsed_time": "5 days, 13:14:02", "remaining_time": "1 day, 11:24:56"}
|
||||
{"current_steps": 1970, "total_steps": 2481, "loss": 0.0091, "lr": 2.4769635635071278e-06, "epoch": 2.37957086733152, "percentage": 79.4, "elapsed_time": "5 days, 13:55:18", "remaining_time": "1 day, 10:44:17"}
|
||||
{"current_steps": 1980, "total_steps": 2481, "loss": 0.0094, "lr": 2.3849818343220864e-06, "epoch": 2.3916591115140524, "percentage": 79.81, "elapsed_time": "5 days, 14:36:29", "remaining_time": "1 day, 10:03:35"}
|
||||
{"current_steps": 1990, "total_steps": 2481, "loss": 0.008, "lr": 2.294508708733104e-06, "epoch": 2.403747355696585, "percentage": 80.21, "elapsed_time": "5 days, 15:17:29", "remaining_time": "1 day, 9:22:51"}
|
||||
{"current_steps": 2000, "total_steps": 2481, "loss": 0.0099, "lr": 2.205562110280174e-06, "epoch": 2.4158355998791174, "percentage": 80.61, "elapsed_time": "5 days, 15:58:28", "remaining_time": "1 day, 8:42:06"}
|
||||
{"current_steps": 2010, "total_steps": 2481, "loss": 0.0086, "lr": 2.11815966008452e-06, "epoch": 2.42792384406165, "percentage": 81.02, "elapsed_time": "5 days, 16:40:39", "remaining_time": "1 day, 8:01:38"}
|
||||
{"current_steps": 2020, "total_steps": 2481, "loss": 0.0084, "lr": 2.0323186733577193e-06, "epoch": 2.4400120882441825, "percentage": 81.42, "elapsed_time": "5 days, 17:21:30", "remaining_time": "1 day, 7:20:51"}
|
||||
{"current_steps": 2030, "total_steps": 2481, "loss": 0.0088, "lr": 1.9480561559713875e-06, "epoch": 2.452100332426715, "percentage": 81.82, "elapsed_time": "5 days, 18:02:09", "remaining_time": "1 day, 6:40:01"}
|
||||
{"current_steps": 2040, "total_steps": 2481, "loss": 0.0101, "lr": 1.8653888010881637e-06, "epoch": 2.4641885766092475, "percentage": 82.22, "elapsed_time": "5 days, 18:43:22", "remaining_time": "1 day, 5:59:19"}
|
||||
{"current_steps": 2050, "total_steps": 2481, "loss": 0.0092, "lr": 1.784332985854641e-06, "epoch": 2.47627682079178, "percentage": 82.63, "elapsed_time": "5 days, 19:24:50", "remaining_time": "1 day, 5:18:39"}
|
||||
{"current_steps": 2060, "total_steps": 2481, "loss": 0.0088, "lr": 1.7049047681569286e-06, "epoch": 2.4883650649743125, "percentage": 83.03, "elapsed_time": "5 days, 20:05:37", "remaining_time": "1 day, 4:37:50"}
|
||||
{"current_steps": 2070, "total_steps": 2481, "loss": 0.0084, "lr": 1.6271198834394041e-06, "epoch": 2.500453309156845, "percentage": 83.43, "elapsed_time": "5 days, 20:45:51", "remaining_time": "1 day, 3:56:55"}
|
||||
{"current_steps": 2080, "total_steps": 2481, "loss": 0.0088, "lr": 1.550993741587411e-06, "epoch": 2.5125415533393776, "percentage": 83.84, "elapsed_time": "5 days, 21:26:53", "remaining_time": "1 day, 3:16:10"}
|
||||
{"current_steps": 2090, "total_steps": 2481, "loss": 0.0082, "lr": 1.4765414238744103e-06, "epoch": 2.52462979752191, "percentage": 84.24, "elapsed_time": "5 days, 22:07:52", "remaining_time": "1 day, 2:35:24"}
|
||||
{"current_steps": 2100, "total_steps": 2481, "loss": 0.0093, "lr": 1.4037776799742408e-06, "epoch": 2.5367180417044426, "percentage": 84.64, "elapsed_time": "5 days, 22:48:41", "remaining_time": "1 day, 1:54:36"}
|
||||
{"current_steps": 2110, "total_steps": 2481, "loss": 0.0088, "lr": 1.3327169250390847e-06, "epoch": 2.548806285886975, "percentage": 85.05, "elapsed_time": "5 days, 23:29:09", "remaining_time": "1 day, 1:13:44"}
|
||||
{"current_steps": 2120, "total_steps": 2481, "loss": 0.0088, "lr": 1.263373236843687e-06, "epoch": 2.5608945300695076, "percentage": 85.45, "elapsed_time": "6 days, 0:09:39", "remaining_time": "1 day, 0:32:53"}
|
||||
{"current_steps": 2130, "total_steps": 2481, "loss": 0.0077, "lr": 1.195760352996429e-06, "epoch": 2.57298277425204, "percentage": 85.85, "elapsed_time": "6 days, 0:50:26", "remaining_time": "23:52:05"}
|
||||
{"current_steps": 2140, "total_steps": 2481, "loss": 0.0089, "lr": 1.129891668217783e-06, "epoch": 2.585071018434572, "percentage": 86.26, "elapsed_time": "6 days, 1:30:51", "remaining_time": "23:11:13"}
|
||||
{"current_steps": 2150, "total_steps": 2481, "loss": 0.0081, "lr": 1.0657802316866972e-06, "epoch": 2.597159262617105, "percentage": 86.66, "elapsed_time": "6 days, 2:11:46", "remaining_time": "22:30:26"}
|
||||
{"current_steps": 2160, "total_steps": 2481, "loss": 0.0093, "lr": 1.0034387444554273e-06, "epoch": 2.6092475067996372, "percentage": 87.06, "elapsed_time": "6 days, 2:52:42", "remaining_time": "21:49:39"}
|
||||
{"current_steps": 2170, "total_steps": 2481, "loss": 0.009, "lr": 9.42879556933366e-07, "epoch": 2.62133575098217, "percentage": 87.46, "elapsed_time": "6 days, 3:33:14", "remaining_time": "21:08:49"}
|
||||
{"current_steps": 2180, "total_steps": 2481, "loss": 0.008, "lr": 8.8411466644029e-07, "epoch": 2.6334239951647023, "percentage": 87.87, "elapsed_time": "6 days, 4:13:36", "remaining_time": "20:27:58"}
|
||||
{"current_steps": 2190, "total_steps": 2481, "loss": 0.0085, "lr": 8.271557148295995e-07, "epoch": 2.6455122393472346, "percentage": 88.27, "elapsed_time": "6 days, 4:54:02", "remaining_time": "19:47:07"}
|
||||
{"current_steps": 2200, "total_steps": 2481, "loss": 0.0083, "lr": 7.720139861819576e-07, "epoch": 2.6576004835297673, "percentage": 88.67, "elapsed_time": "6 days, 5:34:35", "remaining_time": "19:06:17"}
|
||||
{"current_steps": 2210, "total_steps": 2481, "loss": 0.0089, "lr": 7.187004045698087e-07, "epoch": 2.6696887277123, "percentage": 89.08, "elapsed_time": "6 days, 6:16:14", "remaining_time": "18:25:36"}
|
||||
{"current_steps": 2220, "total_steps": 2481, "loss": 0.0082, "lr": 6.672255318932342e-07, "epoch": 2.6817769718948323, "percentage": 89.48, "elapsed_time": "6 days, 6:56:51", "remaining_time": "17:44:47"}
|
||||
{"current_steps": 2230, "total_steps": 2481, "loss": 0.0098, "lr": 6.175995657875255e-07, "epoch": 2.6938652160773646, "percentage": 89.88, "elapsed_time": "6 days, 7:37:28", "remaining_time": "17:03:58"}
|
||||
{"current_steps": 2240, "total_steps": 2481, "loss": 0.0081, "lr": 5.698323376029568e-07, "epoch": 2.7059534602598974, "percentage": 90.29, "elapsed_time": "6 days, 8:17:38", "remaining_time": "16:23:06"}
|
||||
{"current_steps": 2250, "total_steps": 2481, "loss": 0.008, "lr": 5.239333104571009e-07, "epoch": 2.7180417044424297, "percentage": 90.69, "elapsed_time": "6 days, 8:58:22", "remaining_time": "15:42:18"}
|
||||
{"current_steps": 2260, "total_steps": 2481, "loss": 0.0082, "lr": 4.799115773600982e-07, "epoch": 2.7301299486249624, "percentage": 91.09, "elapsed_time": "6 days, 9:38:56", "remaining_time": "15:01:29"}
|
||||
{"current_steps": 2270, "total_steps": 2481, "loss": 0.0084, "lr": 4.377758594132542e-07, "epoch": 2.7422181928074947, "percentage": 91.5, "elapsed_time": "6 days, 10:19:14", "remaining_time": "14:20:39"}
|
||||
{"current_steps": 2280, "total_steps": 2481, "loss": 0.0086, "lr": 3.97534504081305e-07, "epoch": 2.754306436990027, "percentage": 91.9, "elapsed_time": "6 days, 10:59:44", "remaining_time": "13:39:50"}
|
||||
{"current_steps": 2290, "total_steps": 2481, "loss": 0.0083, "lr": 3.591954835387168e-07, "epoch": 2.7663946811725597, "percentage": 92.3, "elapsed_time": "6 days, 11:40:11", "remaining_time": "12:59:01"}
|
||||
{"current_steps": 2300, "total_steps": 2481, "loss": 0.0081, "lr": 3.22766393090318e-07, "epoch": 2.7784829253550924, "percentage": 92.7, "elapsed_time": "6 days, 12:20:25", "remaining_time": "12:18:11"}
|
||||
{"current_steps": 2310, "total_steps": 2481, "loss": 0.0074, "lr": 2.8825444966661064e-07, "epoch": 2.7905711695376247, "percentage": 93.11, "elapsed_time": "6 days, 13:00:52", "remaining_time": "11:37:23"}
|
||||
{"current_steps": 2320, "total_steps": 2481, "loss": 0.0081, "lr": 2.556664903940187e-07, "epoch": 2.802659413720157, "percentage": 93.51, "elapsed_time": "6 days, 13:41:03", "remaining_time": "10:56:33"}
|
||||
{"current_steps": 2330, "total_steps": 2481, "loss": 0.0087, "lr": 2.250089712404102e-07, "epoch": 2.8147476579026898, "percentage": 93.91, "elapsed_time": "6 days, 14:22:18", "remaining_time": "10:15:48"}
|
||||
{"current_steps": 2340, "total_steps": 2481, "loss": 0.0087, "lr": 1.9628796573609166e-07, "epoch": 2.826835902085222, "percentage": 94.32, "elapsed_time": "6 days, 15:02:32", "remaining_time": "9:34:59"}
|
||||
{"current_steps": 2350, "total_steps": 2481, "loss": 0.0085, "lr": 1.6950916377060034e-07, "epoch": 2.838924146267755, "percentage": 94.72, "elapsed_time": "6 days, 15:43:10", "remaining_time": "8:54:12"}
|
||||
{"current_steps": 2360, "total_steps": 2481, "loss": 0.0082, "lr": 1.4467787046548388e-07, "epoch": 2.851012390450287, "percentage": 95.12, "elapsed_time": "6 days, 16:23:50", "remaining_time": "8:13:25"}
|
||||
{"current_steps": 2370, "total_steps": 2481, "loss": 0.0092, "lr": 1.2179900512330312e-07, "epoch": 2.8631006346328194, "percentage": 95.53, "elapsed_time": "6 days, 17:03:44", "remaining_time": "7:32:36"}
|
||||
{"current_steps": 2380, "total_steps": 2481, "loss": 0.009, "lr": 1.0087710025307951e-07, "epoch": 2.875188878815352, "percentage": 95.93, "elapsed_time": "6 days, 17:44:23", "remaining_time": "6:51:49"}
|
||||
{"current_steps": 2390, "total_steps": 2481, "loss": 0.0089, "lr": 8.191630067236e-08, "epoch": 2.8872771229978844, "percentage": 96.33, "elapsed_time": "6 days, 18:25:08", "remaining_time": "6:11:02"}
|
||||
{"current_steps": 2400, "total_steps": 2481, "loss": 0.0098, "lr": 6.492036268609725e-08, "epoch": 2.899365367180417, "percentage": 96.74, "elapsed_time": "6 days, 19:05:29", "remaining_time": "5:30:15"}
|
||||
{"current_steps": 2410, "total_steps": 2481, "loss": 0.008, "lr": 4.9892653342483724e-08, "epoch": 2.9114536113629494, "percentage": 97.14, "elapsed_time": "6 days, 19:46:59", "remaining_time": "4:49:30"}
|
||||
{"current_steps": 2420, "total_steps": 2481, "loss": 0.0089, "lr": 3.683614976591643e-08, "epoch": 2.923541855545482, "percentage": 97.54, "elapsed_time": "6 days, 20:27:38", "remaining_time": "4:08:43"}
|
||||
{"current_steps": 2430, "total_steps": 2481, "loss": 0.0084, "lr": 2.5753438567196475e-08, "epoch": 2.9356300997280145, "percentage": 97.94, "elapsed_time": "6 days, 21:08:15", "remaining_time": "3:27:57"}
|
||||
{"current_steps": 2440, "total_steps": 2481, "loss": 0.0077, "lr": 1.6646715331102292e-08, "epoch": 2.947718343910547, "percentage": 98.35, "elapsed_time": "6 days, 21:48:30", "remaining_time": "2:47:10"}
|
||||
{"current_steps": 2450, "total_steps": 2481, "loss": 0.0091, "lr": 9.517784181422018e-09, "epoch": 2.9598065880930795, "percentage": 98.75, "elapsed_time": "6 days, 22:28:58", "remaining_time": "2:06:23"}
|
||||
{"current_steps": 2460, "total_steps": 2481, "loss": 0.0085, "lr": 4.368057423542737e-09, "epoch": 2.971894832275612, "percentage": 99.15, "elapsed_time": "6 days, 23:09:28", "remaining_time": "1:25:37"}
|
||||
{"current_steps": 2470, "total_steps": 2481, "loss": 0.0083, "lr": 1.198555264656509e-09, "epoch": 2.9839830764581445, "percentage": 99.56, "elapsed_time": "6 days, 23:50:39", "remaining_time": "0:44:50"}
|
||||
{"current_steps": 2480, "total_steps": 2481, "loss": 0.0103, "lr": 9.905611650928847e-12, "epoch": 2.996071320640677, "percentage": 99.96, "elapsed_time": "7 days, 0:31:24", "remaining_time": "0:04:04"}
|
||||
{"current_steps": 2481, "total_steps": 2481, "epoch": 2.99728014505893, "percentage": 100.0, "elapsed_time": "7 days, 0:36:19", "remaining_time": "0:00:00"}
|
||||
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 sha256:8110ddbc78ccde7d33d42a61550dc7795a3566bea3362a7d2cc4a455d6433e22
|
||||
size 7800
|
||||
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