初始化项目，由ModelHub XC社区提供模型
Model: mlfoundations-dev/b2_math_length_3k Source: Original Platform
This commit is contained in:
ModelHub XC
56
.gitattributes
vendored
Normal file
56
.gitattributes
vendored
Normal file
@@ -0,0 +1,56 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-7B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: b2_math_length_3k
|
||||
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. -->
|
||||
|
||||
# b2_math_length_3k
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/b2_math_length_3k 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: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 4
|
||||
- gradient_accumulation_steps: 24
|
||||
- total_train_batch_size: 96
|
||||
- total_eval_batch_size: 32
|
||||
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 7.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.46.1
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 3.1.0
|
||||
- Tokenizers 0.20.3
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 6.850632911392405,
|
||||
"total_flos": 9.289277301231452e+17,
|
||||
"train_loss": 0.3896952799654433,
|
||||
"train_runtime": 26951.6631,
|
||||
"train_samples_per_second": 0.821,
|
||||
"train_steps_per_second": 0.008
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.46.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
37
configs.yaml
Normal file
37
configs.yaml
Normal file
@@ -0,0 +1,37 @@
|
||||
assistant_tag: gpt
|
||||
bf16: true
|
||||
content_tag: value
|
||||
cutoff_len: 16384
|
||||
dataloader_num_workers: 4
|
||||
dataloader_persistent_workers: true
|
||||
dataloader_pin_memory: true
|
||||
dataset: mlfoundations-dev/b2_math_length_3k
|
||||
dataset_dir: ONLINE
|
||||
ddp_timeout: 180000000
|
||||
deepspeed: dcft/train/zero3.json
|
||||
do_train: true
|
||||
enable_liger_kernel: true
|
||||
finetuning_type: full
|
||||
global_batch_size: 96
|
||||
gradient_accumulation_steps: 24
|
||||
hub_model_id: mlfoundations-dev/b2_math_length_3k
|
||||
learning_rate: 2.0e-05
|
||||
logging_steps: 1
|
||||
lr_scheduler_type: cosine
|
||||
messages: conversations
|
||||
model_name_or_path: Qwen/Qwen2.5-7B-Instruct
|
||||
num_train_epochs: 7.0
|
||||
output_dir: /data/cat/ws/ryma833h-dcft/checkpoints/b2_math_length_3k
|
||||
overwrite_cache: true
|
||||
per_device_train_batch_size: 1
|
||||
plot_loss: true
|
||||
preprocessing_num_workers: 16
|
||||
push_to_db: true
|
||||
push_to_hub: true
|
||||
report_to: wandb
|
||||
role_tag: from
|
||||
save_strategy: epoch
|
||||
stage: sft
|
||||
template: qwen25
|
||||
user_tag: human
|
||||
warmup_ratio: 0.1
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.46.1"
|
||||
}
|
||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
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 sha256:5ee17e3bd31f78d57c65abee85f03ebc8b129f50c4598b6a683c8f8020916387
|
||||
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:ccb0034be55e894799a2b693bce10dcd6b814b020f7368fbb57326c74df8f6a0
|
||||
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 sha256:6feefef9c4dba14b57d61e2577fec203122677d8ff0e9ada66c68c9270542c6a
|
||||
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 sha256:5be729bc9820bde60b676a23c408c31eac5608a9bd3248209ab5b91419d6b7f6
|
||||
size 1089994880
|
||||
346
model.safetensors.index.json
Normal file
346
model.safetensors.index.json
Normal file
@@ -0,0 +1,346 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 6.850632911392405,
|
||||
"total_flos": 9.289277301231452e+17,
|
||||
"train_loss": 0.3896952799654433,
|
||||
"train_runtime": 26951.6631,
|
||||
"train_samples_per_second": 0.821,
|
||||
"train_steps_per_second": 0.008
|
||||
}
|
||||
225
trainer_log.jsonl
Normal file
225
trainer_log.jsonl
Normal file
@@ -0,0 +1,225 @@
|
||||
{"current_steps": 1, "total_steps": 224, "loss": 0.7951, "lr": 8.695652173913044e-07, "epoch": 0.030379746835443037, "percentage": 0.45, "elapsed_time": "0:02:02", "remaining_time": "7:35:53"}
|
||||
{"current_steps": 2, "total_steps": 224, "loss": 0.7914, "lr": 1.7391304347826088e-06, "epoch": 0.060759493670886074, "percentage": 0.89, "elapsed_time": "0:03:59", "remaining_time": "7:22:46"}
|
||||
{"current_steps": 3, "total_steps": 224, "loss": 0.8256, "lr": 2.6086956521739132e-06, "epoch": 0.09113924050632911, "percentage": 1.34, "elapsed_time": "0:06:10", "remaining_time": "7:34:32"}
|
||||
{"current_steps": 4, "total_steps": 224, "loss": 0.8069, "lr": 3.4782608695652175e-06, "epoch": 0.12151898734177215, "percentage": 1.79, "elapsed_time": "0:08:16", "remaining_time": "7:34:46"}
|
||||
{"current_steps": 5, "total_steps": 224, "loss": 0.786, "lr": 4.347826086956522e-06, "epoch": 0.1518987341772152, "percentage": 2.23, "elapsed_time": "0:10:14", "remaining_time": "7:28:25"}
|
||||
{"current_steps": 6, "total_steps": 224, "loss": 0.7004, "lr": 5.2173913043478265e-06, "epoch": 0.18227848101265823, "percentage": 2.68, "elapsed_time": "0:12:11", "remaining_time": "7:22:59"}
|
||||
{"current_steps": 7, "total_steps": 224, "loss": 0.7298, "lr": 6.086956521739132e-06, "epoch": 0.21265822784810126, "percentage": 3.12, "elapsed_time": "0:14:14", "remaining_time": "7:21:16"}
|
||||
{"current_steps": 8, "total_steps": 224, "loss": 0.6914, "lr": 6.956521739130435e-06, "epoch": 0.2430379746835443, "percentage": 3.57, "elapsed_time": "0:16:07", "remaining_time": "7:15:31"}
|
||||
{"current_steps": 9, "total_steps": 224, "loss": 0.6995, "lr": 7.82608695652174e-06, "epoch": 0.27341772151898736, "percentage": 4.02, "elapsed_time": "0:18:16", "remaining_time": "7:16:31"}
|
||||
{"current_steps": 10, "total_steps": 224, "loss": 0.6807, "lr": 8.695652173913044e-06, "epoch": 0.3037974683544304, "percentage": 4.46, "elapsed_time": "0:20:11", "remaining_time": "7:12:11"}
|
||||
{"current_steps": 11, "total_steps": 224, "loss": 0.6618, "lr": 9.565217391304349e-06, "epoch": 0.3341772151898734, "percentage": 4.91, "elapsed_time": "0:22:18", "remaining_time": "7:12:02"}
|
||||
{"current_steps": 12, "total_steps": 224, "loss": 0.6354, "lr": 1.0434782608695653e-05, "epoch": 0.36455696202531646, "percentage": 5.36, "elapsed_time": "0:24:22", "remaining_time": "7:10:42"}
|
||||
{"current_steps": 13, "total_steps": 224, "loss": 0.6327, "lr": 1.1304347826086957e-05, "epoch": 0.3949367088607595, "percentage": 5.8, "elapsed_time": "0:26:22", "remaining_time": "7:07:58"}
|
||||
{"current_steps": 14, "total_steps": 224, "loss": 0.6265, "lr": 1.2173913043478263e-05, "epoch": 0.4253164556962025, "percentage": 6.25, "elapsed_time": "0:28:10", "remaining_time": "7:02:44"}
|
||||
{"current_steps": 15, "total_steps": 224, "loss": 0.6016, "lr": 1.3043478260869566e-05, "epoch": 0.45569620253164556, "percentage": 6.7, "elapsed_time": "0:30:16", "remaining_time": "7:01:44"}
|
||||
{"current_steps": 16, "total_steps": 224, "loss": 0.6376, "lr": 1.391304347826087e-05, "epoch": 0.4860759493670886, "percentage": 7.14, "elapsed_time": "0:32:15", "remaining_time": "6:59:19"}
|
||||
{"current_steps": 17, "total_steps": 224, "loss": 0.5866, "lr": 1.4782608695652174e-05, "epoch": 0.5164556962025316, "percentage": 7.59, "elapsed_time": "0:34:25", "remaining_time": "6:59:09"}
|
||||
{"current_steps": 18, "total_steps": 224, "loss": 0.5703, "lr": 1.565217391304348e-05, "epoch": 0.5468354430379747, "percentage": 8.04, "elapsed_time": "0:36:22", "remaining_time": "6:56:16"}
|
||||
{"current_steps": 19, "total_steps": 224, "loss": 0.5505, "lr": 1.6521739130434785e-05, "epoch": 0.5772151898734177, "percentage": 8.48, "elapsed_time": "0:38:16", "remaining_time": "6:52:57"}
|
||||
{"current_steps": 20, "total_steps": 224, "loss": 0.5687, "lr": 1.739130434782609e-05, "epoch": 0.6075949367088608, "percentage": 8.93, "elapsed_time": "0:40:05", "remaining_time": "6:48:56"}
|
||||
{"current_steps": 21, "total_steps": 224, "loss": 0.5613, "lr": 1.8260869565217393e-05, "epoch": 0.6379746835443038, "percentage": 9.38, "elapsed_time": "0:41:57", "remaining_time": "6:45:40"}
|
||||
{"current_steps": 22, "total_steps": 224, "loss": 0.5463, "lr": 1.9130434782608697e-05, "epoch": 0.6683544303797468, "percentage": 9.82, "elapsed_time": "0:44:00", "remaining_time": "6:44:02"}
|
||||
{"current_steps": 23, "total_steps": 224, "loss": 0.5378, "lr": 2e-05, "epoch": 0.6987341772151898, "percentage": 10.27, "elapsed_time": "0:45:56", "remaining_time": "6:41:30"}
|
||||
{"current_steps": 24, "total_steps": 224, "loss": 0.5425, "lr": 1.999877856940653e-05, "epoch": 0.7291139240506329, "percentage": 10.71, "elapsed_time": "0:47:53", "remaining_time": "6:39:07"}
|
||||
{"current_steps": 25, "total_steps": 224, "loss": 0.5394, "lr": 1.999511457600466e-05, "epoch": 0.759493670886076, "percentage": 11.16, "elapsed_time": "0:50:02", "remaining_time": "6:38:21"}
|
||||
{"current_steps": 26, "total_steps": 224, "loss": 0.5322, "lr": 1.9989008914857115e-05, "epoch": 0.789873417721519, "percentage": 11.61, "elapsed_time": "0:51:57", "remaining_time": "6:35:37"}
|
||||
{"current_steps": 27, "total_steps": 224, "loss": 0.5197, "lr": 1.998046307749216e-05, "epoch": 0.8202531645569621, "percentage": 12.05, "elapsed_time": "0:53:53", "remaining_time": "6:33:13"}
|
||||
{"current_steps": 28, "total_steps": 224, "loss": 0.53, "lr": 1.9969479151539238e-05, "epoch": 0.850632911392405, "percentage": 12.5, "elapsed_time": "0:55:49", "remaining_time": "6:30:45"}
|
||||
{"current_steps": 29, "total_steps": 224, "loss": 0.5197, "lr": 1.9956059820218982e-05, "epoch": 0.8810126582278481, "percentage": 12.95, "elapsed_time": "0:57:43", "remaining_time": "6:28:10"}
|
||||
{"current_steps": 30, "total_steps": 224, "loss": 0.5176, "lr": 1.9940208361687762e-05, "epoch": 0.9113924050632911, "percentage": 13.39, "elapsed_time": "0:59:45", "remaining_time": "6:26:24"}
|
||||
{"current_steps": 31, "total_steps": 224, "loss": 0.5096, "lr": 1.9921928648236855e-05, "epoch": 0.9417721518987342, "percentage": 13.84, "elapsed_time": "1:01:42", "remaining_time": "6:24:10"}
|
||||
{"current_steps": 32, "total_steps": 224, "loss": 0.5026, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "1:03:39", "remaining_time": "6:21:59"}
|
||||
{"current_steps": 33, "total_steps": 224, "loss": 0.4982, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "1:06:10", "remaining_time": "6:23:01"}
|
||||
{"current_steps": 34, "total_steps": 224, "loss": 0.4825, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "1:08:13", "remaining_time": "6:21:13"}
|
||||
{"current_steps": 35, "total_steps": 224, "loss": 0.4927, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "1:10:13", "remaining_time": "6:19:13"}
|
||||
{"current_steps": 36, "total_steps": 224, "loss": 0.4858, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "1:12:16", "remaining_time": "6:17:26"}
|
||||
{"current_steps": 37, "total_steps": 224, "loss": 0.4878, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "1:14:05", "remaining_time": "6:14:27"}
|
||||
{"current_steps": 38, "total_steps": 224, "loss": 0.48, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "1:15:58", "remaining_time": "6:11:50"}
|
||||
{"current_steps": 39, "total_steps": 224, "loss": 0.4767, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "1:17:44", "remaining_time": "6:08:44"}
|
||||
{"current_steps": 40, "total_steps": 224, "loss": 0.4748, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "1:19:46", "remaining_time": "6:06:58"}
|
||||
{"current_steps": 41, "total_steps": 224, "loss": 0.4827, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "1:21:51", "remaining_time": "6:05:23"}
|
||||
{"current_steps": 42, "total_steps": 224, "loss": 0.4745, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "1:23:52", "remaining_time": "6:03:27"}
|
||||
{"current_steps": 43, "total_steps": 224, "loss": 0.4794, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "1:26:04", "remaining_time": "6:02:19"}
|
||||
{"current_steps": 44, "total_steps": 224, "loss": 0.458, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "1:28:03", "remaining_time": "6:00:15"}
|
||||
{"current_steps": 45, "total_steps": 224, "loss": 0.455, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "1:29:54", "remaining_time": "5:57:39"}
|
||||
{"current_steps": 46, "total_steps": 224, "loss": 0.4572, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "1:31:45", "remaining_time": "5:55:04"}
|
||||
{"current_steps": 47, "total_steps": 224, "loss": 0.4616, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "1:33:45", "remaining_time": "5:53:06"}
|
||||
{"current_steps": 48, "total_steps": 224, "loss": 0.4527, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "1:35:37", "remaining_time": "5:50:37"}
|
||||
{"current_steps": 49, "total_steps": 224, "loss": 0.4671, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "1:37:33", "remaining_time": "5:48:24"}
|
||||
{"current_steps": 50, "total_steps": 224, "loss": 0.4615, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "1:39:19", "remaining_time": "5:45:40"}
|
||||
{"current_steps": 51, "total_steps": 224, "loss": 0.4628, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "1:41:16", "remaining_time": "5:43:30"}
|
||||
{"current_steps": 52, "total_steps": 224, "loss": 0.4509, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "1:43:07", "remaining_time": "5:41:06"}
|
||||
{"current_steps": 53, "total_steps": 224, "loss": 0.458, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "1:45:06", "remaining_time": "5:39:07"}
|
||||
{"current_steps": 54, "total_steps": 224, "loss": 0.4619, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "1:47:04", "remaining_time": "5:37:04"}
|
||||
{"current_steps": 55, "total_steps": 224, "loss": 0.474, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "1:49:11", "remaining_time": "5:35:31"}
|
||||
{"current_steps": 56, "total_steps": 224, "loss": 0.4236, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "1:51:02", "remaining_time": "5:33:08"}
|
||||
{"current_steps": 57, "total_steps": 224, "loss": 0.4623, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "1:53:04", "remaining_time": "5:31:17"}
|
||||
{"current_steps": 58, "total_steps": 224, "loss": 0.4471, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "1:55:00", "remaining_time": "5:29:09"}
|
||||
{"current_steps": 59, "total_steps": 224, "loss": 0.4508, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "1:56:58", "remaining_time": "5:27:08"}
|
||||
{"current_steps": 60, "total_steps": 224, "loss": 0.47, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "1:58:53", "remaining_time": "5:24:59"}
|
||||
{"current_steps": 61, "total_steps": 224, "loss": 0.455, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "2:00:58", "remaining_time": "5:23:16"}
|
||||
{"current_steps": 62, "total_steps": 224, "loss": 0.4526, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "2:03:01", "remaining_time": "5:21:28"}
|
||||
{"current_steps": 63, "total_steps": 224, "loss": 0.4546, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "2:05:02", "remaining_time": "5:19:33"}
|
||||
{"current_steps": 64, "total_steps": 224, "loss": 0.4472, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "2:07:03", "remaining_time": "5:17:38"}
|
||||
{"current_steps": 65, "total_steps": 224, "loss": 0.4544, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:09:03", "remaining_time": "5:15:41"}
|
||||
{"current_steps": 66, "total_steps": 224, "loss": 0.4304, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:11:50", "remaining_time": "5:15:37"}
|
||||
{"current_steps": 67, "total_steps": 224, "loss": 0.4278, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "2:13:54", "remaining_time": "5:13:47"}
|
||||
{"current_steps": 68, "total_steps": 224, "loss": 0.389, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "2:15:45", "remaining_time": "5:11:27"}
|
||||
{"current_steps": 69, "total_steps": 224, "loss": 0.4189, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "2:17:51", "remaining_time": "5:09:41"}
|
||||
{"current_steps": 70, "total_steps": 224, "loss": 0.4029, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "2:19:51", "remaining_time": "5:07:40"}
|
||||
{"current_steps": 71, "total_steps": 224, "loss": 0.4116, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "2:21:50", "remaining_time": "5:05:39"}
|
||||
{"current_steps": 72, "total_steps": 224, "loss": 0.3974, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "2:23:54", "remaining_time": "5:03:48"}
|
||||
{"current_steps": 73, "total_steps": 224, "loss": 0.3987, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "2:25:45", "remaining_time": "5:01:30"}
|
||||
{"current_steps": 74, "total_steps": 224, "loss": 0.4096, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "2:27:47", "remaining_time": "4:59:34"}
|
||||
{"current_steps": 75, "total_steps": 224, "loss": 0.4152, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "2:29:48", "remaining_time": "4:57:37"}
|
||||
{"current_steps": 76, "total_steps": 224, "loss": 0.4082, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "2:31:51", "remaining_time": "4:55:43"}
|
||||
{"current_steps": 77, "total_steps": 224, "loss": 0.398, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "2:33:49", "remaining_time": "4:53:39"}
|
||||
{"current_steps": 78, "total_steps": 224, "loss": 0.4009, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "2:35:42", "remaining_time": "4:51:26"}
|
||||
{"current_steps": 79, "total_steps": 224, "loss": 0.4108, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "2:37:31", "remaining_time": "4:49:06"}
|
||||
{"current_steps": 80, "total_steps": 224, "loss": 0.4034, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "2:39:20", "remaining_time": "4:46:48"}
|
||||
{"current_steps": 81, "total_steps": 224, "loss": 0.393, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "2:41:01", "remaining_time": "4:44:17"}
|
||||
{"current_steps": 82, "total_steps": 224, "loss": 0.4089, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "2:43:01", "remaining_time": "4:42:17"}
|
||||
{"current_steps": 83, "total_steps": 224, "loss": 0.3894, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "2:44:58", "remaining_time": "4:40:15"}
|
||||
{"current_steps": 84, "total_steps": 224, "loss": 0.4039, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "2:47:03", "remaining_time": "4:38:25"}
|
||||
{"current_steps": 85, "total_steps": 224, "loss": 0.3961, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "2:49:06", "remaining_time": "4:36:32"}
|
||||
{"current_steps": 86, "total_steps": 224, "loss": 0.3863, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "2:51:08", "remaining_time": "4:34:37"}
|
||||
{"current_steps": 87, "total_steps": 224, "loss": 0.3994, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "2:53:03", "remaining_time": "4:32:30"}
|
||||
{"current_steps": 88, "total_steps": 224, "loss": 0.4003, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "2:55:00", "remaining_time": "4:30:28"}
|
||||
{"current_steps": 89, "total_steps": 224, "loss": 0.3899, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "2:57:01", "remaining_time": "4:28:31"}
|
||||
{"current_steps": 90, "total_steps": 224, "loss": 0.3932, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "2:58:56", "remaining_time": "4:26:24"}
|
||||
{"current_steps": 91, "total_steps": 224, "loss": 0.4052, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "3:00:51", "remaining_time": "4:24:19"}
|
||||
{"current_steps": 92, "total_steps": 224, "loss": 0.4164, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "3:02:58", "remaining_time": "4:22:31"}
|
||||
{"current_steps": 93, "total_steps": 224, "loss": 0.4016, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "3:05:02", "remaining_time": "4:20:38"}
|
||||
{"current_steps": 94, "total_steps": 224, "loss": 0.3997, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "3:06:58", "remaining_time": "4:18:34"}
|
||||
{"current_steps": 95, "total_steps": 224, "loss": 0.4197, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "3:08:55", "remaining_time": "4:16:32"}
|
||||
{"current_steps": 96, "total_steps": 224, "loss": 0.4058, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "3:11:05", "remaining_time": "4:14:47"}
|
||||
{"current_steps": 97, "total_steps": 224, "loss": 0.3994, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:13:00", "remaining_time": "4:12:42"}
|
||||
{"current_steps": 98, "total_steps": 224, "loss": 0.4089, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:15:01", "remaining_time": "4:10:45"}
|
||||
{"current_steps": 99, "total_steps": 224, "loss": 0.3687, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:17:40", "remaining_time": "4:09:35"}
|
||||
{"current_steps": 100, "total_steps": 224, "loss": 0.3729, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "3:19:38", "remaining_time": "4:07:33"}
|
||||
{"current_steps": 101, "total_steps": 224, "loss": 0.3558, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "3:21:48", "remaining_time": "4:05:45"}
|
||||
{"current_steps": 102, "total_steps": 224, "loss": 0.3496, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "3:23:41", "remaining_time": "4:03:37"}
|
||||
{"current_steps": 103, "total_steps": 224, "loss": 0.3591, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "3:25:28", "remaining_time": "4:01:23"}
|
||||
{"current_steps": 104, "total_steps": 224, "loss": 0.3646, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "3:27:23", "remaining_time": "3:59:17"}
|
||||
{"current_steps": 105, "total_steps": 224, "loss": 0.3495, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "3:29:19", "remaining_time": "3:57:14"}
|
||||
{"current_steps": 106, "total_steps": 224, "loss": 0.3549, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "3:31:18", "remaining_time": "3:55:13"}
|
||||
{"current_steps": 107, "total_steps": 224, "loss": 0.3635, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "3:33:21", "remaining_time": "3:53:18"}
|
||||
{"current_steps": 108, "total_steps": 224, "loss": 0.3397, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "3:35:09", "remaining_time": "3:51:05"}
|
||||
{"current_steps": 109, "total_steps": 224, "loss": 0.3396, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "3:36:47", "remaining_time": "3:48:43"}
|
||||
{"current_steps": 110, "total_steps": 224, "loss": 0.3487, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "3:38:43", "remaining_time": "3:46:40"}
|
||||
{"current_steps": 111, "total_steps": 224, "loss": 0.3619, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "3:40:58", "remaining_time": "3:44:56"}
|
||||
{"current_steps": 112, "total_steps": 224, "loss": 0.3476, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "3:42:53", "remaining_time": "3:42:53"}
|
||||
{"current_steps": 113, "total_steps": 224, "loss": 0.3562, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "3:45:08", "remaining_time": "3:41:09"}
|
||||
{"current_steps": 114, "total_steps": 224, "loss": 0.3618, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:47:07", "remaining_time": "3:39:09"}
|
||||
{"current_steps": 115, "total_steps": 224, "loss": 0.3626, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:49:19", "remaining_time": "3:37:21"}
|
||||
{"current_steps": 116, "total_steps": 224, "loss": 0.3615, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:51:18", "remaining_time": "3:35:21"}
|
||||
{"current_steps": 117, "total_steps": 224, "loss": 0.3533, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "3:53:20", "remaining_time": "3:33:24"}
|
||||
{"current_steps": 118, "total_steps": 224, "loss": 0.3636, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "3:55:26", "remaining_time": "3:31:30"}
|
||||
{"current_steps": 119, "total_steps": 224, "loss": 0.3514, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "3:57:17", "remaining_time": "3:29:22"}
|
||||
{"current_steps": 120, "total_steps": 224, "loss": 0.3366, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "3:59:16", "remaining_time": "3:27:22"}
|
||||
{"current_steps": 121, "total_steps": 224, "loss": 0.3494, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "4:01:20", "remaining_time": "3:25:26"}
|
||||
{"current_steps": 122, "total_steps": 224, "loss": 0.354, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "4:03:25", "remaining_time": "3:23:31"}
|
||||
{"current_steps": 123, "total_steps": 224, "loss": 0.3504, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "4:05:15", "remaining_time": "3:21:23"}
|
||||
{"current_steps": 124, "total_steps": 224, "loss": 0.356, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "4:07:15", "remaining_time": "3:19:23"}
|
||||
{"current_steps": 125, "total_steps": 224, "loss": 0.3416, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "4:09:20", "remaining_time": "3:17:29"}
|
||||
{"current_steps": 126, "total_steps": 224, "loss": 0.3424, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "4:11:15", "remaining_time": "3:15:25"}
|
||||
{"current_steps": 127, "total_steps": 224, "loss": 0.3602, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "4:13:21", "remaining_time": "3:13:30"}
|
||||
{"current_steps": 128, "total_steps": 224, "loss": 0.3585, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "4:15:26", "remaining_time": "3:11:34"}
|
||||
{"current_steps": 129, "total_steps": 224, "loss": 0.3554, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "4:17:31", "remaining_time": "3:09:38"}
|
||||
{"current_steps": 130, "total_steps": 224, "loss": 0.3497, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:19:25", "remaining_time": "3:07:35"}
|
||||
{"current_steps": 131, "total_steps": 224, "loss": 0.3368, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:22:14", "remaining_time": "3:06:10"}
|
||||
{"current_steps": 132, "total_steps": 224, "loss": 0.3178, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:24:18", "remaining_time": "3:04:12"}
|
||||
{"current_steps": 133, "total_steps": 224, "loss": 0.3166, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "4:26:15", "remaining_time": "3:02:10"}
|
||||
{"current_steps": 134, "total_steps": 224, "loss": 0.3157, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "4:28:12", "remaining_time": "3:00:08"}
|
||||
{"current_steps": 135, "total_steps": 224, "loss": 0.3051, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "4:30:04", "remaining_time": "2:58:02"}
|
||||
{"current_steps": 136, "total_steps": 224, "loss": 0.3134, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "4:32:13", "remaining_time": "2:56:09"}
|
||||
{"current_steps": 137, "total_steps": 224, "loss": 0.3179, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "4:34:01", "remaining_time": "2:54:01"}
|
||||
{"current_steps": 138, "total_steps": 224, "loss": 0.3074, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "4:35:58", "remaining_time": "2:51:58"}
|
||||
{"current_steps": 139, "total_steps": 224, "loss": 0.3273, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "4:38:08", "remaining_time": "2:50:04"}
|
||||
{"current_steps": 140, "total_steps": 224, "loss": 0.3194, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "4:39:56", "remaining_time": "2:47:58"}
|
||||
{"current_steps": 141, "total_steps": 224, "loss": 0.3199, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "4:41:54", "remaining_time": "2:45:56"}
|
||||
{"current_steps": 142, "total_steps": 224, "loss": 0.3065, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "4:43:54", "remaining_time": "2:43:56"}
|
||||
{"current_steps": 143, "total_steps": 224, "loss": 0.3085, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "4:45:59", "remaining_time": "2:41:59"}
|
||||
{"current_steps": 144, "total_steps": 224, "loss": 0.3209, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "4:47:57", "remaining_time": "2:39:58"}
|
||||
{"current_steps": 145, "total_steps": 224, "loss": 0.3043, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "4:49:44", "remaining_time": "2:37:51"}
|
||||
{"current_steps": 146, "total_steps": 224, "loss": 0.3164, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "4:51:55", "remaining_time": "2:35:57"}
|
||||
{"current_steps": 147, "total_steps": 224, "loss": 0.3199, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "4:53:46", "remaining_time": "2:33:53"}
|
||||
{"current_steps": 148, "total_steps": 224, "loss": 0.3267, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "4:55:57", "remaining_time": "2:31:58"}
|
||||
{"current_steps": 149, "total_steps": 224, "loss": 0.3021, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "4:57:54", "remaining_time": "2:29:57"}
|
||||
{"current_steps": 150, "total_steps": 224, "loss": 0.318, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "4:59:56", "remaining_time": "2:27:58"}
|
||||
{"current_steps": 151, "total_steps": 224, "loss": 0.3095, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "5:02:04", "remaining_time": "2:26:02"}
|
||||
{"current_steps": 152, "total_steps": 224, "loss": 0.311, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "5:04:06", "remaining_time": "2:24:03"}
|
||||
{"current_steps": 153, "total_steps": 224, "loss": 0.3068, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "5:06:04", "remaining_time": "2:22:02"}
|
||||
{"current_steps": 154, "total_steps": 224, "loss": 0.302, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "5:07:57", "remaining_time": "2:19:58"}
|
||||
{"current_steps": 155, "total_steps": 224, "loss": 0.3027, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "5:09:55", "remaining_time": "2:17:58"}
|
||||
{"current_steps": 156, "total_steps": 224, "loss": 0.3114, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "5:11:46", "remaining_time": "2:15:54"}
|
||||
{"current_steps": 157, "total_steps": 224, "loss": 0.3114, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "5:13:37", "remaining_time": "2:13:50"}
|
||||
{"current_steps": 158, "total_steps": 224, "loss": 0.309, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "5:15:38", "remaining_time": "2:11:51"}
|
||||
{"current_steps": 159, "total_steps": 224, "loss": 0.3146, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "5:17:26", "remaining_time": "2:09:46"}
|
||||
{"current_steps": 160, "total_steps": 224, "loss": 0.3094, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "5:19:27", "remaining_time": "2:07:47"}
|
||||
{"current_steps": 161, "total_steps": 224, "loss": 0.2999, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "5:21:20", "remaining_time": "2:05:44"}
|
||||
{"current_steps": 162, "total_steps": 224, "loss": 0.3264, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:23:21", "remaining_time": "2:03:45"}
|
||||
{"current_steps": 163, "total_steps": 224, "loss": 0.3122, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:25:18", "remaining_time": "2:01:44"}
|
||||
{"current_steps": 164, "total_steps": 224, "loss": 0.291, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:28:00", "remaining_time": "2:00:00"}
|
||||
{"current_steps": 165, "total_steps": 224, "loss": 0.2864, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "5:29:50", "remaining_time": "1:57:56"}
|
||||
{"current_steps": 166, "total_steps": 224, "loss": 0.2827, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "5:31:52", "remaining_time": "1:55:57"}
|
||||
{"current_steps": 167, "total_steps": 224, "loss": 0.2725, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "5:33:45", "remaining_time": "1:53:55"}
|
||||
{"current_steps": 168, "total_steps": 224, "loss": 0.2927, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "5:35:46", "remaining_time": "1:51:55"}
|
||||
{"current_steps": 169, "total_steps": 224, "loss": 0.2989, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "5:37:46", "remaining_time": "1:49:55"}
|
||||
{"current_steps": 170, "total_steps": 224, "loss": 0.2802, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "5:39:57", "remaining_time": "1:47:59"}
|
||||
{"current_steps": 171, "total_steps": 224, "loss": 0.2839, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "5:42:03", "remaining_time": "1:46:01"}
|
||||
{"current_steps": 172, "total_steps": 224, "loss": 0.2878, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "5:44:09", "remaining_time": "1:44:02"}
|
||||
{"current_steps": 173, "total_steps": 224, "loss": 0.2927, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "5:46:03", "remaining_time": "1:42:01"}
|
||||
{"current_steps": 174, "total_steps": 224, "loss": 0.281, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "5:48:01", "remaining_time": "1:40:00"}
|
||||
{"current_steps": 175, "total_steps": 224, "loss": 0.2822, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "5:49:55", "remaining_time": "1:37:58"}
|
||||
{"current_steps": 176, "total_steps": 224, "loss": 0.2708, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "5:51:46", "remaining_time": "1:35:56"}
|
||||
{"current_steps": 177, "total_steps": 224, "loss": 0.2884, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "5:53:38", "remaining_time": "1:33:54"}
|
||||
{"current_steps": 178, "total_steps": 224, "loss": 0.2759, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "5:55:32", "remaining_time": "1:31:52"}
|
||||
{"current_steps": 179, "total_steps": 224, "loss": 0.2855, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "5:57:33", "remaining_time": "1:29:53"}
|
||||
{"current_steps": 180, "total_steps": 224, "loss": 0.2779, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "5:59:31", "remaining_time": "1:27:53"}
|
||||
{"current_steps": 181, "total_steps": 224, "loss": 0.2778, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "6:01:27", "remaining_time": "1:25:52"}
|
||||
{"current_steps": 182, "total_steps": 224, "loss": 0.2973, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "6:03:33", "remaining_time": "1:23:53"}
|
||||
{"current_steps": 183, "total_steps": 224, "loss": 0.2793, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "6:05:27", "remaining_time": "1:21:52"}
|
||||
{"current_steps": 184, "total_steps": 224, "loss": 0.2822, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "6:07:29", "remaining_time": "1:19:53"}
|
||||
{"current_steps": 185, "total_steps": 224, "loss": 0.2891, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "6:09:29", "remaining_time": "1:17:53"}
|
||||
{"current_steps": 186, "total_steps": 224, "loss": 0.2735, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "6:11:27", "remaining_time": "1:15:53"}
|
||||
{"current_steps": 187, "total_steps": 224, "loss": 0.2847, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "6:13:27", "remaining_time": "1:13:53"}
|
||||
{"current_steps": 188, "total_steps": 224, "loss": 0.2918, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "6:15:33", "remaining_time": "1:11:54"}
|
||||
{"current_steps": 189, "total_steps": 224, "loss": 0.2896, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "6:17:26", "remaining_time": "1:09:53"}
|
||||
{"current_steps": 190, "total_steps": 224, "loss": 0.2874, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "6:19:22", "remaining_time": "1:07:53"}
|
||||
{"current_steps": 191, "total_steps": 224, "loss": 0.277, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "6:21:20", "remaining_time": "1:05:53"}
|
||||
{"current_steps": 192, "total_steps": 224, "loss": 0.2854, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "6:23:14", "remaining_time": "1:03:52"}
|
||||
{"current_steps": 193, "total_steps": 224, "loss": 0.2803, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "6:25:13", "remaining_time": "1:01:52"}
|
||||
{"current_steps": 194, "total_steps": 224, "loss": 0.2796, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "6:27:12", "remaining_time": "0:59:52"}
|
||||
{"current_steps": 195, "total_steps": 224, "loss": 0.2872, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "6:29:15", "remaining_time": "0:57:53"}
|
||||
{"current_steps": 196, "total_steps": 224, "loss": 0.2867, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "6:31:11", "remaining_time": "0:55:53"}
|
||||
{"current_steps": 197, "total_steps": 224, "loss": 0.2692, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "6:34:02", "remaining_time": "0:54:00"}
|
||||
{"current_steps": 198, "total_steps": 224, "loss": 0.2589, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "6:35:58", "remaining_time": "0:51:59"}
|
||||
{"current_steps": 199, "total_steps": 224, "loss": 0.2787, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "6:38:01", "remaining_time": "0:50:00"}
|
||||
{"current_steps": 200, "total_steps": 224, "loss": 0.2741, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "6:39:59", "remaining_time": "0:47:59"}
|
||||
{"current_steps": 201, "total_steps": 224, "loss": 0.2825, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "6:41:52", "remaining_time": "0:45:59"}
|
||||
{"current_steps": 202, "total_steps": 224, "loss": 0.2657, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "6:43:50", "remaining_time": "0:43:58"}
|
||||
{"current_steps": 203, "total_steps": 224, "loss": 0.2633, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "6:45:49", "remaining_time": "0:41:58"}
|
||||
{"current_steps": 204, "total_steps": 224, "loss": 0.2826, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "6:47:47", "remaining_time": "0:39:58"}
|
||||
{"current_steps": 205, "total_steps": 224, "loss": 0.2786, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "6:49:46", "remaining_time": "0:37:58"}
|
||||
{"current_steps": 206, "total_steps": 224, "loss": 0.2749, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "6:51:38", "remaining_time": "0:35:58"}
|
||||
{"current_steps": 207, "total_steps": 224, "loss": 0.2747, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "6:53:44", "remaining_time": "0:33:58"}
|
||||
{"current_steps": 208, "total_steps": 224, "loss": 0.2729, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "6:55:49", "remaining_time": "0:31:59"}
|
||||
{"current_steps": 209, "total_steps": 224, "loss": 0.2712, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "6:57:58", "remaining_time": "0:29:59"}
|
||||
{"current_steps": 210, "total_steps": 224, "loss": 0.2785, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "6:59:55", "remaining_time": "0:27:59"}
|
||||
{"current_steps": 211, "total_steps": 224, "loss": 0.268, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "7:02:05", "remaining_time": "0:26:00"}
|
||||
{"current_steps": 212, "total_steps": 224, "loss": 0.2702, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "7:04:03", "remaining_time": "0:24:00"}
|
||||
{"current_steps": 213, "total_steps": 224, "loss": 0.2747, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "7:06:03", "remaining_time": "0:22:00"}
|
||||
{"current_steps": 214, "total_steps": 224, "loss": 0.2646, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "7:08:03", "remaining_time": "0:20:00"}
|
||||
{"current_steps": 215, "total_steps": 224, "loss": 0.2624, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "7:09:52", "remaining_time": "0:17:59"}
|
||||
{"current_steps": 216, "total_steps": 224, "loss": 0.2684, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "7:11:41", "remaining_time": "0:15:59"}
|
||||
{"current_steps": 217, "total_steps": 224, "loss": 0.2686, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "7:13:36", "remaining_time": "0:13:59"}
|
||||
{"current_steps": 218, "total_steps": 224, "loss": 0.269, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "7:15:31", "remaining_time": "0:11:59"}
|
||||
{"current_steps": 219, "total_steps": 224, "loss": 0.2693, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "7:17:24", "remaining_time": "0:09:59"}
|
||||
{"current_steps": 220, "total_steps": 224, "loss": 0.269, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "7:19:24", "remaining_time": "0:07:59"}
|
||||
{"current_steps": 221, "total_steps": 224, "loss": 0.2632, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "7:21:20", "remaining_time": "0:05:59"}
|
||||
{"current_steps": 222, "total_steps": 224, "loss": 0.2705, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "7:23:26", "remaining_time": "0:03:59"}
|
||||
{"current_steps": 223, "total_steps": 224, "loss": 0.2785, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "7:25:17", "remaining_time": "0:01:59"}
|
||||
{"current_steps": 224, "total_steps": 224, "loss": 0.2724, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "7:27:20", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "7:29:09", "remaining_time": "0:00:00"}
|
||||
1610
trainer_state.json
Normal file
1610
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1a977672733482d3c2a2334764af24bbb2fde69644a1f614ef19a16c80ef34ff
|
||||
size 7288
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 42 KiB |
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user