Upload 11 files
Browse files- README.md +54 -1
- all_results.json +8 -0
- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +655 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,56 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- customized
|
| 6 |
+
model-index:
|
| 7 |
+
- name: finetune
|
| 8 |
+
results: []
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# finetune
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [/root/autodl-tmp/sikong/repo/LMFlow/output_models/Linly-Chinese-LLaMA-7b-hf](https://huggingface.co//root/autodl-tmp/sikong/repo/LMFlow/output_models/Linly-Chinese-LLaMA-7b-hf) on the customized dataset.
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 2e-05
|
| 36 |
+
- train_batch_size: 2
|
| 37 |
+
- eval_batch_size: 8
|
| 38 |
+
- seed: 42
|
| 39 |
+
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 4
|
| 41 |
+
- total_train_batch_size: 8
|
| 42 |
+
- total_eval_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 50.0
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
### Framework versions
|
| 52 |
+
|
| 53 |
+
- Transformers 4.28.0.dev0
|
| 54 |
+
- Pytorch 2.0.0+cu117
|
| 55 |
+
- Datasets 2.10.1
|
| 56 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 0.0559101588953109,
|
| 4 |
+
"train_runtime": 46787.7757,
|
| 5 |
+
"train_samples": 334,
|
| 6 |
+
"train_samples_per_second": 0.357,
|
| 7 |
+
"train_steps_per_second": 0.045
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/autodl-tmp/sikong/repo/LMFlow/output_models/Linly-Chinese-LLaMA-7b-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"rms_norm_eps": 1e-06,
|
| 18 |
+
"tie_word_embeddings": false,
|
| 19 |
+
"torch_dtype": "bfloat16",
|
| 20 |
+
"transformers_version": "4.28.0.dev0",
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"vocab_size": 32000
|
| 23 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0.dev0"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d45ad0fce33cbbc1ed5b547be3274d0c9837c498a70a06672236d6678d21fe37
|
| 3 |
+
size 13476942241
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token": "</s>"
|
| 3 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "",
|
| 3 |
+
"clean_up_tokenization_spaces": false,
|
| 4 |
+
"eos_token": "",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"special_tokens_map_file": "/root/autodl-tmp/sikong/repo/LMFlow/output_models/Linly-Chinese-LLaMA-7b-hf/special_tokens_map.json",
|
| 7 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 8 |
+
"unk_token": ""
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 0.0559101588953109,
|
| 4 |
+
"train_runtime": 46787.7757,
|
| 5 |
+
"train_samples": 334,
|
| 6 |
+
"train_samples_per_second": 0.357,
|
| 7 |
+
"train_steps_per_second": 0.045
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,655 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 2100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.48,
|
| 12 |
+
"learning_rate": 1.980952380952381e-05,
|
| 13 |
+
"loss": 1.4241,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.95,
|
| 18 |
+
"learning_rate": 1.961904761904762e-05,
|
| 19 |
+
"loss": 1.3539,
|
| 20 |
+
"step": 40
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.43,
|
| 24 |
+
"learning_rate": 1.942857142857143e-05,
|
| 25 |
+
"loss": 0.8083,
|
| 26 |
+
"step": 60
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.9,
|
| 30 |
+
"learning_rate": 1.923809523809524e-05,
|
| 31 |
+
"loss": 0.7274,
|
| 32 |
+
"step": 80
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.38,
|
| 36 |
+
"learning_rate": 1.904761904761905e-05,
|
| 37 |
+
"loss": 0.3911,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.86,
|
| 42 |
+
"learning_rate": 1.885714285714286e-05,
|
| 43 |
+
"loss": 0.2785,
|
| 44 |
+
"step": 120
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.33,
|
| 48 |
+
"learning_rate": 1.866666666666667e-05,
|
| 49 |
+
"loss": 0.1367,
|
| 50 |
+
"step": 140
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.81,
|
| 54 |
+
"learning_rate": 1.8476190476190478e-05,
|
| 55 |
+
"loss": 0.1004,
|
| 56 |
+
"step": 160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.29,
|
| 60 |
+
"learning_rate": 1.8285714285714288e-05,
|
| 61 |
+
"loss": 0.0718,
|
| 62 |
+
"step": 180
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.76,
|
| 66 |
+
"learning_rate": 1.8095238095238097e-05,
|
| 67 |
+
"loss": 0.0588,
|
| 68 |
+
"step": 200
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.24,
|
| 72 |
+
"learning_rate": 1.7904761904761907e-05,
|
| 73 |
+
"loss": 0.0456,
|
| 74 |
+
"step": 220
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 5.71,
|
| 78 |
+
"learning_rate": 1.7714285714285717e-05,
|
| 79 |
+
"loss": 0.0378,
|
| 80 |
+
"step": 240
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.19,
|
| 84 |
+
"learning_rate": 1.7523809523809526e-05,
|
| 85 |
+
"loss": 0.0297,
|
| 86 |
+
"step": 260
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 6.67,
|
| 90 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 91 |
+
"loss": 0.0232,
|
| 92 |
+
"step": 280
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.14,
|
| 96 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 97 |
+
"loss": 0.0231,
|
| 98 |
+
"step": 300
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.62,
|
| 102 |
+
"learning_rate": 1.6952380952380955e-05,
|
| 103 |
+
"loss": 0.016,
|
| 104 |
+
"step": 320
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.1,
|
| 108 |
+
"learning_rate": 1.6761904761904764e-05,
|
| 109 |
+
"loss": 0.016,
|
| 110 |
+
"step": 340
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 8.57,
|
| 114 |
+
"learning_rate": 1.6571428571428574e-05,
|
| 115 |
+
"loss": 0.0109,
|
| 116 |
+
"step": 360
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.05,
|
| 120 |
+
"learning_rate": 1.6380952380952384e-05,
|
| 121 |
+
"loss": 0.0114,
|
| 122 |
+
"step": 380
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 9.52,
|
| 126 |
+
"learning_rate": 1.6190476190476193e-05,
|
| 127 |
+
"loss": 0.0078,
|
| 128 |
+
"step": 400
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.0,
|
| 132 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 133 |
+
"loss": 0.0103,
|
| 134 |
+
"step": 420
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.48,
|
| 138 |
+
"learning_rate": 1.580952380952381e-05,
|
| 139 |
+
"loss": 0.0061,
|
| 140 |
+
"step": 440
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 10.95,
|
| 144 |
+
"learning_rate": 1.5619047619047622e-05,
|
| 145 |
+
"loss": 0.0085,
|
| 146 |
+
"step": 460
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 11.43,
|
| 150 |
+
"learning_rate": 1.542857142857143e-05,
|
| 151 |
+
"loss": 0.005,
|
| 152 |
+
"step": 480
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 11.9,
|
| 156 |
+
"learning_rate": 1.523809523809524e-05,
|
| 157 |
+
"loss": 0.0093,
|
| 158 |
+
"step": 500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 12.38,
|
| 162 |
+
"learning_rate": 1.5047619047619049e-05,
|
| 163 |
+
"loss": 0.0066,
|
| 164 |
+
"step": 520
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 12.86,
|
| 168 |
+
"learning_rate": 1.4857142857142858e-05,
|
| 169 |
+
"loss": 0.0061,
|
| 170 |
+
"step": 540
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 13.33,
|
| 174 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 175 |
+
"loss": 0.0048,
|
| 176 |
+
"step": 560
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.81,
|
| 180 |
+
"learning_rate": 1.4476190476190478e-05,
|
| 181 |
+
"loss": 0.0051,
|
| 182 |
+
"step": 580
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 14.29,
|
| 186 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 187 |
+
"loss": 0.0036,
|
| 188 |
+
"step": 600
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 14.76,
|
| 192 |
+
"learning_rate": 1.4095238095238097e-05,
|
| 193 |
+
"loss": 0.0053,
|
| 194 |
+
"step": 620
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 15.24,
|
| 198 |
+
"learning_rate": 1.3904761904761905e-05,
|
| 199 |
+
"loss": 0.0052,
|
| 200 |
+
"step": 640
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 15.71,
|
| 204 |
+
"learning_rate": 1.3714285714285716e-05,
|
| 205 |
+
"loss": 0.0054,
|
| 206 |
+
"step": 660
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 16.19,
|
| 210 |
+
"learning_rate": 1.3523809523809525e-05,
|
| 211 |
+
"loss": 0.0049,
|
| 212 |
+
"step": 680
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 16.67,
|
| 216 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 217 |
+
"loss": 0.0055,
|
| 218 |
+
"step": 700
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 17.14,
|
| 222 |
+
"learning_rate": 1.3142857142857145e-05,
|
| 223 |
+
"loss": 0.0046,
|
| 224 |
+
"step": 720
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 17.62,
|
| 228 |
+
"learning_rate": 1.2952380952380954e-05,
|
| 229 |
+
"loss": 0.004,
|
| 230 |
+
"step": 740
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 18.1,
|
| 234 |
+
"learning_rate": 1.2761904761904762e-05,
|
| 235 |
+
"loss": 0.0047,
|
| 236 |
+
"step": 760
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 18.57,
|
| 240 |
+
"learning_rate": 1.2571428571428572e-05,
|
| 241 |
+
"loss": 0.0047,
|
| 242 |
+
"step": 780
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 19.05,
|
| 246 |
+
"learning_rate": 1.2380952380952383e-05,
|
| 247 |
+
"loss": 0.0047,
|
| 248 |
+
"step": 800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 19.52,
|
| 252 |
+
"learning_rate": 1.2190476190476192e-05,
|
| 253 |
+
"loss": 0.0038,
|
| 254 |
+
"step": 820
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 20.0,
|
| 258 |
+
"learning_rate": 1.2e-05,
|
| 259 |
+
"loss": 0.0046,
|
| 260 |
+
"step": 840
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 20.48,
|
| 264 |
+
"learning_rate": 1.180952380952381e-05,
|
| 265 |
+
"loss": 0.0034,
|
| 266 |
+
"step": 860
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 20.95,
|
| 270 |
+
"learning_rate": 1.1619047619047621e-05,
|
| 271 |
+
"loss": 0.004,
|
| 272 |
+
"step": 880
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 21.43,
|
| 276 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 277 |
+
"loss": 0.0032,
|
| 278 |
+
"step": 900
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 21.9,
|
| 282 |
+
"learning_rate": 1.1238095238095239e-05,
|
| 283 |
+
"loss": 0.0039,
|
| 284 |
+
"step": 920
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 22.38,
|
| 288 |
+
"learning_rate": 1.104761904761905e-05,
|
| 289 |
+
"loss": 0.0033,
|
| 290 |
+
"step": 940
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 22.86,
|
| 294 |
+
"learning_rate": 1.0857142857142858e-05,
|
| 295 |
+
"loss": 0.0032,
|
| 296 |
+
"step": 960
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 23.33,
|
| 300 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 301 |
+
"loss": 0.0033,
|
| 302 |
+
"step": 980
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 23.81,
|
| 306 |
+
"learning_rate": 1.0476190476190477e-05,
|
| 307 |
+
"loss": 0.003,
|
| 308 |
+
"step": 1000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 24.29,
|
| 312 |
+
"learning_rate": 1.0285714285714285e-05,
|
| 313 |
+
"loss": 0.003,
|
| 314 |
+
"step": 1020
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 24.76,
|
| 318 |
+
"learning_rate": 1.0095238095238096e-05,
|
| 319 |
+
"loss": 0.003,
|
| 320 |
+
"step": 1040
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 25.24,
|
| 324 |
+
"learning_rate": 9.904761904761906e-06,
|
| 325 |
+
"loss": 0.0034,
|
| 326 |
+
"step": 1060
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 25.71,
|
| 330 |
+
"learning_rate": 9.714285714285715e-06,
|
| 331 |
+
"loss": 0.0029,
|
| 332 |
+
"step": 1080
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 26.19,
|
| 336 |
+
"learning_rate": 9.523809523809525e-06,
|
| 337 |
+
"loss": 0.0031,
|
| 338 |
+
"step": 1100
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 26.67,
|
| 342 |
+
"learning_rate": 9.333333333333334e-06,
|
| 343 |
+
"loss": 0.0032,
|
| 344 |
+
"step": 1120
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 27.14,
|
| 348 |
+
"learning_rate": 9.142857142857144e-06,
|
| 349 |
+
"loss": 0.0032,
|
| 350 |
+
"step": 1140
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 27.62,
|
| 354 |
+
"learning_rate": 8.952380952380953e-06,
|
| 355 |
+
"loss": 0.003,
|
| 356 |
+
"step": 1160
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 28.1,
|
| 360 |
+
"learning_rate": 8.761904761904763e-06,
|
| 361 |
+
"loss": 0.0031,
|
| 362 |
+
"step": 1180
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 28.57,
|
| 366 |
+
"learning_rate": 8.571428571428571e-06,
|
| 367 |
+
"loss": 0.0026,
|
| 368 |
+
"step": 1200
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 29.05,
|
| 372 |
+
"learning_rate": 8.380952380952382e-06,
|
| 373 |
+
"loss": 0.0032,
|
| 374 |
+
"step": 1220
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 29.52,
|
| 378 |
+
"learning_rate": 8.190476190476192e-06,
|
| 379 |
+
"loss": 0.0026,
|
| 380 |
+
"step": 1240
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 30.0,
|
| 384 |
+
"learning_rate": 8.000000000000001e-06,
|
| 385 |
+
"loss": 0.004,
|
| 386 |
+
"step": 1260
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 30.48,
|
| 390 |
+
"learning_rate": 7.809523809523811e-06,
|
| 391 |
+
"loss": 0.0031,
|
| 392 |
+
"step": 1280
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 30.95,
|
| 396 |
+
"learning_rate": 7.61904761904762e-06,
|
| 397 |
+
"loss": 0.0034,
|
| 398 |
+
"step": 1300
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 31.43,
|
| 402 |
+
"learning_rate": 7.428571428571429e-06,
|
| 403 |
+
"loss": 0.0032,
|
| 404 |
+
"step": 1320
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 31.9,
|
| 408 |
+
"learning_rate": 7.238095238095239e-06,
|
| 409 |
+
"loss": 0.0031,
|
| 410 |
+
"step": 1340
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 32.38,
|
| 414 |
+
"learning_rate": 7.047619047619048e-06,
|
| 415 |
+
"loss": 0.0029,
|
| 416 |
+
"step": 1360
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 32.86,
|
| 420 |
+
"learning_rate": 6.857142857142858e-06,
|
| 421 |
+
"loss": 0.0031,
|
| 422 |
+
"step": 1380
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 33.33,
|
| 426 |
+
"learning_rate": 6.666666666666667e-06,
|
| 427 |
+
"loss": 0.0033,
|
| 428 |
+
"step": 1400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 33.81,
|
| 432 |
+
"learning_rate": 6.476190476190477e-06,
|
| 433 |
+
"loss": 0.0031,
|
| 434 |
+
"step": 1420
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 34.29,
|
| 438 |
+
"learning_rate": 6.285714285714286e-06,
|
| 439 |
+
"loss": 0.0027,
|
| 440 |
+
"step": 1440
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 34.76,
|
| 444 |
+
"learning_rate": 6.095238095238096e-06,
|
| 445 |
+
"loss": 0.0028,
|
| 446 |
+
"step": 1460
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 35.24,
|
| 450 |
+
"learning_rate": 5.904761904761905e-06,
|
| 451 |
+
"loss": 0.0027,
|
| 452 |
+
"step": 1480
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 35.71,
|
| 456 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 457 |
+
"loss": 0.0029,
|
| 458 |
+
"step": 1500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 36.19,
|
| 462 |
+
"learning_rate": 5.523809523809525e-06,
|
| 463 |
+
"loss": 0.0026,
|
| 464 |
+
"step": 1520
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 36.67,
|
| 468 |
+
"learning_rate": 5.333333333333334e-06,
|
| 469 |
+
"loss": 0.0024,
|
| 470 |
+
"step": 1540
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 37.14,
|
| 474 |
+
"learning_rate": 5.142857142857142e-06,
|
| 475 |
+
"loss": 0.0029,
|
| 476 |
+
"step": 1560
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 37.62,
|
| 480 |
+
"learning_rate": 4.952380952380953e-06,
|
| 481 |
+
"loss": 0.0023,
|
| 482 |
+
"step": 1580
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 38.1,
|
| 486 |
+
"learning_rate": 4.761904761904762e-06,
|
| 487 |
+
"loss": 0.0029,
|
| 488 |
+
"step": 1600
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 38.57,
|
| 492 |
+
"learning_rate": 4.571428571428572e-06,
|
| 493 |
+
"loss": 0.0023,
|
| 494 |
+
"step": 1620
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 39.05,
|
| 498 |
+
"learning_rate": 4.3809523809523815e-06,
|
| 499 |
+
"loss": 0.0027,
|
| 500 |
+
"step": 1640
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 39.52,
|
| 504 |
+
"learning_rate": 4.190476190476191e-06,
|
| 505 |
+
"loss": 0.0022,
|
| 506 |
+
"step": 1660
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 40.0,
|
| 510 |
+
"learning_rate": 4.000000000000001e-06,
|
| 511 |
+
"loss": 0.0028,
|
| 512 |
+
"step": 1680
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 40.48,
|
| 516 |
+
"learning_rate": 3.80952380952381e-06,
|
| 517 |
+
"loss": 0.0024,
|
| 518 |
+
"step": 1700
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 40.95,
|
| 522 |
+
"learning_rate": 3.6190476190476194e-06,
|
| 523 |
+
"loss": 0.0025,
|
| 524 |
+
"step": 1720
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 41.43,
|
| 528 |
+
"learning_rate": 3.428571428571429e-06,
|
| 529 |
+
"loss": 0.0022,
|
| 530 |
+
"step": 1740
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 41.9,
|
| 534 |
+
"learning_rate": 3.2380952380952385e-06,
|
| 535 |
+
"loss": 0.0026,
|
| 536 |
+
"step": 1760
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 42.38,
|
| 540 |
+
"learning_rate": 3.047619047619048e-06,
|
| 541 |
+
"loss": 0.0021,
|
| 542 |
+
"step": 1780
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 42.86,
|
| 546 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 547 |
+
"loss": 0.0027,
|
| 548 |
+
"step": 1800
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 43.33,
|
| 552 |
+
"learning_rate": 2.666666666666667e-06,
|
| 553 |
+
"loss": 0.0023,
|
| 554 |
+
"step": 1820
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 43.81,
|
| 558 |
+
"learning_rate": 2.4761904761904764e-06,
|
| 559 |
+
"loss": 0.0025,
|
| 560 |
+
"step": 1840
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 44.29,
|
| 564 |
+
"learning_rate": 2.285714285714286e-06,
|
| 565 |
+
"loss": 0.0022,
|
| 566 |
+
"step": 1860
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 44.76,
|
| 570 |
+
"learning_rate": 2.0952380952380955e-06,
|
| 571 |
+
"loss": 0.0024,
|
| 572 |
+
"step": 1880
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 45.24,
|
| 576 |
+
"learning_rate": 1.904761904761905e-06,
|
| 577 |
+
"loss": 0.0023,
|
| 578 |
+
"step": 1900
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 45.71,
|
| 582 |
+
"learning_rate": 1.7142857142857145e-06,
|
| 583 |
+
"loss": 0.0023,
|
| 584 |
+
"step": 1920
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 46.19,
|
| 588 |
+
"learning_rate": 1.523809523809524e-06,
|
| 589 |
+
"loss": 0.0022,
|
| 590 |
+
"step": 1940
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 46.67,
|
| 594 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 595 |
+
"loss": 0.0024,
|
| 596 |
+
"step": 1960
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 47.14,
|
| 600 |
+
"learning_rate": 1.142857142857143e-06,
|
| 601 |
+
"loss": 0.002,
|
| 602 |
+
"step": 1980
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 47.62,
|
| 606 |
+
"learning_rate": 9.523809523809525e-07,
|
| 607 |
+
"loss": 0.0021,
|
| 608 |
+
"step": 2000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 48.1,
|
| 612 |
+
"learning_rate": 7.61904761904762e-07,
|
| 613 |
+
"loss": 0.0023,
|
| 614 |
+
"step": 2020
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 48.57,
|
| 618 |
+
"learning_rate": 5.714285714285715e-07,
|
| 619 |
+
"loss": 0.0022,
|
| 620 |
+
"step": 2040
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 49.05,
|
| 624 |
+
"learning_rate": 3.80952380952381e-07,
|
| 625 |
+
"loss": 0.0021,
|
| 626 |
+
"step": 2060
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 49.52,
|
| 630 |
+
"learning_rate": 1.904761904761905e-07,
|
| 631 |
+
"loss": 0.0021,
|
| 632 |
+
"step": 2080
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 50.0,
|
| 636 |
+
"learning_rate": 0.0,
|
| 637 |
+
"loss": 0.0021,
|
| 638 |
+
"step": 2100
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 50.0,
|
| 642 |
+
"step": 2100,
|
| 643 |
+
"total_flos": 13733996789760.0,
|
| 644 |
+
"train_loss": 0.0559101588953109,
|
| 645 |
+
"train_runtime": 46787.7757,
|
| 646 |
+
"train_samples_per_second": 0.357,
|
| 647 |
+
"train_steps_per_second": 0.045
|
| 648 |
+
}
|
| 649 |
+
],
|
| 650 |
+
"max_steps": 2100,
|
| 651 |
+
"num_train_epochs": 50,
|
| 652 |
+
"total_flos": 13733996789760.0,
|
| 653 |
+
"trial_name": null,
|
| 654 |
+
"trial_params": null
|
| 655 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fed3813b2a1aedbdf84fca1633b71ad3222b7b5a09e6a06612ebff7db9e1a06
|
| 3 |
+
size 4923
|