Upload 15 files
Browse files- README.md +50 -1
- added_tokens.json +3 -0
- all_results.json +18 -0
- bpe.codes +0 -0
- config.json +37 -0
- generated_predictions.txt +0 -0
- generation_config.json +9 -0
- predict_results.json +12 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +54 -0
- train_results.json +8 -0
- trainer_state.json +748 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,3 +1,52 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: vinai/bartpho-word-base
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: eval_bartpho_final
|
| 7 |
+
results: []
|
| 8 |
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# eval_bartpho_final
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [vinai/bartpho-word-base](https://huggingface.co/vinai/bartpho-word-base) on an unknown dataset.
|
| 16 |
+
|
| 17 |
+
## Model description
|
| 18 |
+
|
| 19 |
+
More information needed
|
| 20 |
+
|
| 21 |
+
## Intended uses & limitations
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Training and evaluation data
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training procedure
|
| 30 |
+
|
| 31 |
+
### Training hyperparameters
|
| 32 |
+
|
| 33 |
+
The following hyperparameters were used during training:
|
| 34 |
+
- learning_rate: 5e-05
|
| 35 |
+
- train_batch_size: 2
|
| 36 |
+
- eval_batch_size: 2
|
| 37 |
+
- seed: 42
|
| 38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
+
- lr_scheduler_type: linear
|
| 40 |
+
- lr_scheduler_warmup_steps: 20000
|
| 41 |
+
- num_epochs: 5.0
|
| 42 |
+
|
| 43 |
+
### Training results
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
### Framework versions
|
| 48 |
+
|
| 49 |
+
- Transformers 4.34.1
|
| 50 |
+
- Pytorch 2.1.0+cu118
|
| 51 |
+
- Datasets 2.14.5
|
| 52 |
+
- Tokenizers 0.14.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"predict_gen_len": 134.48478376935398,
|
| 4 |
+
"predict_loss": 1.6961811780929565,
|
| 5 |
+
"predict_rouge1": 69.2157,
|
| 6 |
+
"predict_rouge2": 35.4531,
|
| 7 |
+
"predict_rougeL": 39.6005,
|
| 8 |
+
"predict_rougeLsum": 64.1255,
|
| 9 |
+
"predict_runtime": 1512.6875,
|
| 10 |
+
"predict_samples": 1873,
|
| 11 |
+
"predict_samples_per_second": 1.238,
|
| 12 |
+
"predict_steps_per_second": 0.619,
|
| 13 |
+
"train_loss": 2.007782585069282,
|
| 14 |
+
"train_runtime": 8390.77,
|
| 15 |
+
"train_samples": 24084,
|
| 16 |
+
"train_samples_per_second": 14.351,
|
| 17 |
+
"train_steps_per_second": 7.176
|
| 18 |
+
}
|
bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "vinai/bartpho-word-base",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 768,
|
| 12 |
+
"decoder_attention_heads": 12,
|
| 13 |
+
"decoder_ffn_dim": 3072,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 2,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"encoder_attention_heads": 12,
|
| 19 |
+
"encoder_ffn_dim": 3072,
|
| 20 |
+
"encoder_layerdrop": 0.0,
|
| 21 |
+
"encoder_layers": 6,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"forced_eos_token_id": 2,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_position_embeddings": 1024,
|
| 28 |
+
"model_type": "mbart",
|
| 29 |
+
"num_hidden_layers": 6,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"scale_embedding": false,
|
| 32 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.34.1",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 64001
|
| 37 |
+
}
|
generated_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.34.1"
|
| 9 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_gen_len": 134.48478376935398,
|
| 3 |
+
"predict_loss": 1.6961811780929565,
|
| 4 |
+
"predict_rouge1": 69.2157,
|
| 5 |
+
"predict_rouge2": 35.4531,
|
| 6 |
+
"predict_rougeL": 39.6005,
|
| 7 |
+
"predict_rougeLsum": 64.1255,
|
| 8 |
+
"predict_runtime": 1512.6875,
|
| 9 |
+
"predict_samples": 1873,
|
| 10 |
+
"predict_samples_per_second": 1.238,
|
| 11 |
+
"predict_steps_per_second": 0.619
|
| 12 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec53295b205845ca7e582a9b3af7c2eb9662bffe0c471cba82ec293f2341dfa9
|
| 3 |
+
size 600223642
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"64000": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"pad_token": "<pad>",
|
| 51 |
+
"sep_token": "</s>",
|
| 52 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 53 |
+
"unk_token": "<unk>"
|
| 54 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 2.007782585069282,
|
| 4 |
+
"train_runtime": 8390.77,
|
| 5 |
+
"train_samples": 24084,
|
| 6 |
+
"train_samples_per_second": 14.351,
|
| 7 |
+
"train_steps_per_second": 7.176
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,748 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 60210,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 1.25e-06,
|
| 14 |
+
"loss": 7.7769,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 2.5e-06,
|
| 20 |
+
"loss": 4.9602,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.12,
|
| 25 |
+
"learning_rate": 3.75e-06,
|
| 26 |
+
"loss": 4.1666,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.17,
|
| 31 |
+
"learning_rate": 5e-06,
|
| 32 |
+
"loss": 3.688,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.21,
|
| 37 |
+
"learning_rate": 6.25e-06,
|
| 38 |
+
"loss": 3.4594,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.25,
|
| 43 |
+
"learning_rate": 7.5e-06,
|
| 44 |
+
"loss": 3.2406,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.29,
|
| 49 |
+
"learning_rate": 8.75e-06,
|
| 50 |
+
"loss": 3.1113,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.33,
|
| 55 |
+
"learning_rate": 1e-05,
|
| 56 |
+
"loss": 2.9628,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.37,
|
| 61 |
+
"learning_rate": 1.125e-05,
|
| 62 |
+
"loss": 2.8324,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.42,
|
| 67 |
+
"learning_rate": 1.25e-05,
|
| 68 |
+
"loss": 2.7406,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.46,
|
| 73 |
+
"learning_rate": 1.3750000000000002e-05,
|
| 74 |
+
"loss": 2.6505,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.5,
|
| 79 |
+
"learning_rate": 1.5e-05,
|
| 80 |
+
"loss": 2.5864,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.54,
|
| 85 |
+
"learning_rate": 1.6250000000000002e-05,
|
| 86 |
+
"loss": 2.5592,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.58,
|
| 91 |
+
"learning_rate": 1.75e-05,
|
| 92 |
+
"loss": 2.513,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.62,
|
| 97 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 98 |
+
"loss": 2.4164,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.66,
|
| 103 |
+
"learning_rate": 2e-05,
|
| 104 |
+
"loss": 2.4196,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.71,
|
| 109 |
+
"learning_rate": 2.125e-05,
|
| 110 |
+
"loss": 2.387,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.75,
|
| 115 |
+
"learning_rate": 2.25e-05,
|
| 116 |
+
"loss": 2.3328,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.79,
|
| 121 |
+
"learning_rate": 2.375e-05,
|
| 122 |
+
"loss": 2.307,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.83,
|
| 127 |
+
"learning_rate": 2.5e-05,
|
| 128 |
+
"loss": 2.2919,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.87,
|
| 133 |
+
"learning_rate": 2.625e-05,
|
| 134 |
+
"loss": 2.2488,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.91,
|
| 139 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 140 |
+
"loss": 2.2451,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.95,
|
| 145 |
+
"learning_rate": 2.8749999999999997e-05,
|
| 146 |
+
"loss": 2.228,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.0,
|
| 151 |
+
"learning_rate": 3e-05,
|
| 152 |
+
"loss": 2.2017,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.04,
|
| 157 |
+
"learning_rate": 3.125e-05,
|
| 158 |
+
"loss": 2.1533,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.08,
|
| 163 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 164 |
+
"loss": 2.1322,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.12,
|
| 169 |
+
"learning_rate": 3.375000000000001e-05,
|
| 170 |
+
"loss": 2.1557,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.16,
|
| 175 |
+
"learning_rate": 3.5e-05,
|
| 176 |
+
"loss": 2.1209,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.2,
|
| 181 |
+
"learning_rate": 3.625e-05,
|
| 182 |
+
"loss": 2.103,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.25,
|
| 187 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 188 |
+
"loss": 2.1099,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.29,
|
| 193 |
+
"learning_rate": 3.875e-05,
|
| 194 |
+
"loss": 2.1024,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.33,
|
| 199 |
+
"learning_rate": 4e-05,
|
| 200 |
+
"loss": 2.0618,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.37,
|
| 205 |
+
"learning_rate": 4.125e-05,
|
| 206 |
+
"loss": 2.073,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.41,
|
| 211 |
+
"learning_rate": 4.25e-05,
|
| 212 |
+
"loss": 2.0616,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.45,
|
| 217 |
+
"learning_rate": 4.375e-05,
|
| 218 |
+
"loss": 2.0967,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.49,
|
| 223 |
+
"learning_rate": 4.5e-05,
|
| 224 |
+
"loss": 2.0628,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.54,
|
| 229 |
+
"learning_rate": 4.6250000000000006e-05,
|
| 230 |
+
"loss": 2.0786,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.58,
|
| 235 |
+
"learning_rate": 4.75e-05,
|
| 236 |
+
"loss": 2.0524,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.62,
|
| 241 |
+
"learning_rate": 4.875e-05,
|
| 242 |
+
"loss": 2.0508,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.66,
|
| 247 |
+
"learning_rate": 5e-05,
|
| 248 |
+
"loss": 2.0352,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.7,
|
| 253 |
+
"learning_rate": 4.937826411340463e-05,
|
| 254 |
+
"loss": 2.0348,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.74,
|
| 259 |
+
"learning_rate": 4.8756528226809256e-05,
|
| 260 |
+
"loss": 2.0173,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.79,
|
| 265 |
+
"learning_rate": 4.813479234021388e-05,
|
| 266 |
+
"loss": 2.0102,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.83,
|
| 271 |
+
"learning_rate": 4.7513056453618504e-05,
|
| 272 |
+
"loss": 1.9995,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.87,
|
| 277 |
+
"learning_rate": 4.689132056702313e-05,
|
| 278 |
+
"loss": 2.0089,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.91,
|
| 283 |
+
"learning_rate": 4.626958468042776e-05,
|
| 284 |
+
"loss": 1.9712,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.95,
|
| 289 |
+
"learning_rate": 4.5647848793832385e-05,
|
| 290 |
+
"loss": 1.9776,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.99,
|
| 295 |
+
"learning_rate": 4.5026112907237005e-05,
|
| 296 |
+
"loss": 1.9573,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.03,
|
| 301 |
+
"learning_rate": 4.440437702064163e-05,
|
| 302 |
+
"loss": 1.877,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.08,
|
| 307 |
+
"learning_rate": 4.378264113404626e-05,
|
| 308 |
+
"loss": 1.8312,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.12,
|
| 313 |
+
"learning_rate": 4.3160905247450886e-05,
|
| 314 |
+
"loss": 1.8694,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.16,
|
| 319 |
+
"learning_rate": 4.253916936085551e-05,
|
| 320 |
+
"loss": 1.8549,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.2,
|
| 325 |
+
"learning_rate": 4.191743347426014e-05,
|
| 326 |
+
"loss": 1.8445,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.24,
|
| 331 |
+
"learning_rate": 4.129569758766476e-05,
|
| 332 |
+
"loss": 1.8301,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.28,
|
| 337 |
+
"learning_rate": 4.067396170106939e-05,
|
| 338 |
+
"loss": 1.8494,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.33,
|
| 343 |
+
"learning_rate": 4.0052225814474015e-05,
|
| 344 |
+
"loss": 1.8504,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.37,
|
| 349 |
+
"learning_rate": 3.943048992787864e-05,
|
| 350 |
+
"loss": 1.8388,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.41,
|
| 355 |
+
"learning_rate": 3.880875404128326e-05,
|
| 356 |
+
"loss": 1.8036,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.45,
|
| 361 |
+
"learning_rate": 3.8187018154687896e-05,
|
| 362 |
+
"loss": 1.825,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.49,
|
| 367 |
+
"learning_rate": 3.7565282268092516e-05,
|
| 368 |
+
"loss": 1.8174,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.53,
|
| 373 |
+
"learning_rate": 3.694354638149714e-05,
|
| 374 |
+
"loss": 1.8188,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.57,
|
| 379 |
+
"learning_rate": 3.632181049490177e-05,
|
| 380 |
+
"loss": 1.8334,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.62,
|
| 385 |
+
"learning_rate": 3.57000746083064e-05,
|
| 386 |
+
"loss": 1.8342,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.66,
|
| 391 |
+
"learning_rate": 3.507833872171102e-05,
|
| 392 |
+
"loss": 1.8119,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.7,
|
| 397 |
+
"learning_rate": 3.4456602835115645e-05,
|
| 398 |
+
"loss": 1.8034,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.74,
|
| 403 |
+
"learning_rate": 3.383486694852027e-05,
|
| 404 |
+
"loss": 1.7964,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.78,
|
| 409 |
+
"learning_rate": 3.32131310619249e-05,
|
| 410 |
+
"loss": 1.7865,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.82,
|
| 415 |
+
"learning_rate": 3.259139517532952e-05,
|
| 416 |
+
"loss": 1.7937,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.86,
|
| 421 |
+
"learning_rate": 3.196965928873415e-05,
|
| 422 |
+
"loss": 1.7982,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.91,
|
| 427 |
+
"learning_rate": 3.134792340213877e-05,
|
| 428 |
+
"loss": 1.7969,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.95,
|
| 433 |
+
"learning_rate": 3.07261875155434e-05,
|
| 434 |
+
"loss": 1.7892,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.99,
|
| 439 |
+
"learning_rate": 3.010445162894802e-05,
|
| 440 |
+
"loss": 1.769,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.03,
|
| 445 |
+
"learning_rate": 2.948271574235265e-05,
|
| 446 |
+
"loss": 1.6569,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.07,
|
| 451 |
+
"learning_rate": 2.8860979855757274e-05,
|
| 452 |
+
"loss": 1.6269,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.11,
|
| 457 |
+
"learning_rate": 2.8239243969161898e-05,
|
| 458 |
+
"loss": 1.6806,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.16,
|
| 463 |
+
"learning_rate": 2.761750808256653e-05,
|
| 464 |
+
"loss": 1.6658,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.2,
|
| 469 |
+
"learning_rate": 2.6995772195971152e-05,
|
| 470 |
+
"loss": 1.654,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.24,
|
| 475 |
+
"learning_rate": 2.6374036309375776e-05,
|
| 476 |
+
"loss": 1.6672,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.28,
|
| 481 |
+
"learning_rate": 2.5752300422780406e-05,
|
| 482 |
+
"loss": 1.6427,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.32,
|
| 487 |
+
"learning_rate": 2.513056453618503e-05,
|
| 488 |
+
"loss": 1.6182,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.36,
|
| 493 |
+
"learning_rate": 2.4508828649589653e-05,
|
| 494 |
+
"loss": 1.6515,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.4,
|
| 499 |
+
"learning_rate": 2.388709276299428e-05,
|
| 500 |
+
"loss": 1.6646,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 3.45,
|
| 505 |
+
"learning_rate": 2.3265356876398904e-05,
|
| 506 |
+
"loss": 1.644,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.49,
|
| 511 |
+
"learning_rate": 2.264362098980353e-05,
|
| 512 |
+
"loss": 1.6337,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.53,
|
| 517 |
+
"learning_rate": 2.2021885103208158e-05,
|
| 518 |
+
"loss": 1.6412,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.57,
|
| 523 |
+
"learning_rate": 2.1400149216612782e-05,
|
| 524 |
+
"loss": 1.6222,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.61,
|
| 529 |
+
"learning_rate": 2.077841333001741e-05,
|
| 530 |
+
"loss": 1.6513,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.65,
|
| 535 |
+
"learning_rate": 2.0156677443422033e-05,
|
| 536 |
+
"loss": 1.6642,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.7,
|
| 541 |
+
"learning_rate": 1.953494155682666e-05,
|
| 542 |
+
"loss": 1.6336,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.74,
|
| 547 |
+
"learning_rate": 1.8913205670231287e-05,
|
| 548 |
+
"loss": 1.6307,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.78,
|
| 553 |
+
"learning_rate": 1.829146978363591e-05,
|
| 554 |
+
"loss": 1.6365,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.82,
|
| 559 |
+
"learning_rate": 1.7669733897040537e-05,
|
| 560 |
+
"loss": 1.6427,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.86,
|
| 565 |
+
"learning_rate": 1.704799801044516e-05,
|
| 566 |
+
"loss": 1.6439,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.9,
|
| 571 |
+
"learning_rate": 1.6426262123849788e-05,
|
| 572 |
+
"loss": 1.6309,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.94,
|
| 577 |
+
"learning_rate": 1.5804526237254415e-05,
|
| 578 |
+
"loss": 1.6301,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.99,
|
| 583 |
+
"learning_rate": 1.518279035065904e-05,
|
| 584 |
+
"loss": 1.6172,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.03,
|
| 589 |
+
"learning_rate": 1.4561054464063667e-05,
|
| 590 |
+
"loss": 1.55,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.07,
|
| 595 |
+
"learning_rate": 1.3939318577468291e-05,
|
| 596 |
+
"loss": 1.5255,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.11,
|
| 601 |
+
"learning_rate": 1.3317582690872918e-05,
|
| 602 |
+
"loss": 1.5083,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.15,
|
| 607 |
+
"learning_rate": 1.2695846804277545e-05,
|
| 608 |
+
"loss": 1.524,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.19,
|
| 613 |
+
"learning_rate": 1.2074110917682169e-05,
|
| 614 |
+
"loss": 1.5256,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.24,
|
| 619 |
+
"learning_rate": 1.1452375031086796e-05,
|
| 620 |
+
"loss": 1.5113,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.28,
|
| 625 |
+
"learning_rate": 1.0830639144491421e-05,
|
| 626 |
+
"loss": 1.5289,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 4.32,
|
| 631 |
+
"learning_rate": 1.0208903257896047e-05,
|
| 632 |
+
"loss": 1.5078,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.36,
|
| 637 |
+
"learning_rate": 9.587167371300672e-06,
|
| 638 |
+
"loss": 1.5072,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.4,
|
| 643 |
+
"learning_rate": 8.965431484705297e-06,
|
| 644 |
+
"loss": 1.4986,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 4.44,
|
| 649 |
+
"learning_rate": 8.343695598109923e-06,
|
| 650 |
+
"loss": 1.5014,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 4.48,
|
| 655 |
+
"learning_rate": 7.72195971151455e-06,
|
| 656 |
+
"loss": 1.5196,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 4.53,
|
| 661 |
+
"learning_rate": 7.100223824919175e-06,
|
| 662 |
+
"loss": 1.5027,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 4.57,
|
| 667 |
+
"learning_rate": 6.4784879383238e-06,
|
| 668 |
+
"loss": 1.4911,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 4.61,
|
| 673 |
+
"learning_rate": 5.856752051728426e-06,
|
| 674 |
+
"loss": 1.4912,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.65,
|
| 679 |
+
"learning_rate": 5.235016165133052e-06,
|
| 680 |
+
"loss": 1.4958,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 4.69,
|
| 685 |
+
"learning_rate": 4.613280278537677e-06,
|
| 686 |
+
"loss": 1.5077,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 4.73,
|
| 691 |
+
"learning_rate": 3.9915443919423026e-06,
|
| 692 |
+
"loss": 1.4834,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 4.77,
|
| 697 |
+
"learning_rate": 3.3698085053469288e-06,
|
| 698 |
+
"loss": 1.4964,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 4.82,
|
| 703 |
+
"learning_rate": 2.748072618751554e-06,
|
| 704 |
+
"loss": 1.5195,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.86,
|
| 709 |
+
"learning_rate": 2.12633673215618e-06,
|
| 710 |
+
"loss": 1.5117,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 4.9,
|
| 715 |
+
"learning_rate": 1.5046008455608059e-06,
|
| 716 |
+
"loss": 1.507,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 4.94,
|
| 721 |
+
"learning_rate": 8.828649589654314e-07,
|
| 722 |
+
"loss": 1.5086,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.98,
|
| 727 |
+
"learning_rate": 2.6112907237005724e-07,
|
| 728 |
+
"loss": 1.5051,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 5.0,
|
| 733 |
+
"step": 60210,
|
| 734 |
+
"total_flos": 4721678852567040.0,
|
| 735 |
+
"train_loss": 2.007782585069282,
|
| 736 |
+
"train_runtime": 8390.77,
|
| 737 |
+
"train_samples_per_second": 14.351,
|
| 738 |
+
"train_steps_per_second": 7.176
|
| 739 |
+
}
|
| 740 |
+
],
|
| 741 |
+
"logging_steps": 500,
|
| 742 |
+
"max_steps": 60210,
|
| 743 |
+
"num_train_epochs": 5,
|
| 744 |
+
"save_steps": 500,
|
| 745 |
+
"total_flos": 4721678852567040.0,
|
| 746 |
+
"trial_name": null,
|
| 747 |
+
"trial_params": null
|
| 748 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9681bdb0bea4258596e2714f5c981f62608a7064dd78e2617a73c53a4652ad1
|
| 3 |
+
size 4792
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|