caracena
commited on
Commit
•
1d4c154
1
Parent(s):
2fe7fff
initial commit
Browse files- README.md +50 -0
- all_results.json +8 -0
- config.json +27 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +8 -0
- trainer_state.json +595 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: bert-clincal-scratch-wl-es
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# bert-clincal-scratch-wl-es
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on an unknown dataset.
|
| 15 |
+
|
| 16 |
+
## Model description
|
| 17 |
+
|
| 18 |
+
More information needed
|
| 19 |
+
|
| 20 |
+
## Intended uses & limitations
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Training and evaluation data
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
### Training hyperparameters
|
| 31 |
+
|
| 32 |
+
The following hyperparameters were used during training:
|
| 33 |
+
- learning_rate: 5e-05
|
| 34 |
+
- train_batch_size: 16
|
| 35 |
+
- eval_batch_size: 8
|
| 36 |
+
- seed: 42
|
| 37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 38 |
+
- lr_scheduler_type: linear
|
| 39 |
+
- num_epochs: 3.0
|
| 40 |
+
|
| 41 |
+
### Training results
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
### Framework versions
|
| 46 |
+
|
| 47 |
+
- Transformers 4.20.0.dev0
|
| 48 |
+
- Pytorch 1.11.0+cu113
|
| 49 |
+
- Datasets 2.2.1
|
| 50 |
+
- Tokenizers 0.12.1
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 5.50125317320702,
|
| 4 |
+
"train_runtime": 8519.4079,
|
| 5 |
+
"train_samples": 253650,
|
| 6 |
+
"train_samples_per_second": 89.32,
|
| 7 |
+
"train_steps_per_second": 5.583
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.20.0.dev0",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 31002
|
| 27 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b23e5d04438510574be93f00f1e3eb2e7176a24cf75c58d060a59996b7b4ff7
|
| 3 |
+
size 439605291
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": "/home/plncmm/.cache/huggingface/transformers/78141ed1e8dcc5ff370950397ca0d1c5c9da478f54ec14544187d8a93eff1a26.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66",
|
| 12 |
+
"strip_accents": false,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 5.50125317320702,
|
| 4 |
+
"train_runtime": 8519.4079,
|
| 5 |
+
"train_samples": 253650,
|
| 6 |
+
"train_samples_per_second": 89.32,
|
| 7 |
+
"train_steps_per_second": 5.583
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,595 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 47562,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.9474370295614146e-05,
|
| 13 |
+
"loss": 6.7026,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 4.894874059122829e-05,
|
| 19 |
+
"loss": 5.9908,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 4.842311088684244e-05,
|
| 25 |
+
"loss": 5.8689,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.13,
|
| 30 |
+
"learning_rate": 4.7897481182456584e-05,
|
| 31 |
+
"loss": 5.8051,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.16,
|
| 36 |
+
"learning_rate": 4.7371851478070734e-05,
|
| 37 |
+
"loss": 5.7614,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.19,
|
| 42 |
+
"learning_rate": 4.684622177368488e-05,
|
| 43 |
+
"loss": 5.7379,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22,
|
| 48 |
+
"learning_rate": 4.632059206929902e-05,
|
| 49 |
+
"loss": 5.732,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.25,
|
| 54 |
+
"learning_rate": 4.579496236491317e-05,
|
| 55 |
+
"loss": 5.6936,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"learning_rate": 4.5269332660527315e-05,
|
| 61 |
+
"loss": 5.6739,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.32,
|
| 66 |
+
"learning_rate": 4.474370295614146e-05,
|
| 67 |
+
"loss": 5.6779,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.35,
|
| 72 |
+
"learning_rate": 4.42180732517556e-05,
|
| 73 |
+
"loss": 5.6697,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.38,
|
| 78 |
+
"learning_rate": 4.3692443547369746e-05,
|
| 79 |
+
"loss": 5.6401,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.41,
|
| 84 |
+
"learning_rate": 4.3166813842983896e-05,
|
| 85 |
+
"loss": 5.645,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.44,
|
| 90 |
+
"learning_rate": 4.264118413859805e-05,
|
| 91 |
+
"loss": 5.6403,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.47,
|
| 96 |
+
"learning_rate": 4.211555443421219e-05,
|
| 97 |
+
"loss": 5.612,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.5,
|
| 102 |
+
"learning_rate": 4.1589924729826334e-05,
|
| 103 |
+
"loss": 5.5909,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.54,
|
| 108 |
+
"learning_rate": 4.106429502544048e-05,
|
| 109 |
+
"loss": 5.6036,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.57,
|
| 114 |
+
"learning_rate": 4.053866532105463e-05,
|
| 115 |
+
"loss": 5.5978,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.6,
|
| 120 |
+
"learning_rate": 4.001303561666877e-05,
|
| 121 |
+
"loss": 5.5889,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.63,
|
| 126 |
+
"learning_rate": 3.9487405912282915e-05,
|
| 127 |
+
"loss": 5.5751,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.66,
|
| 132 |
+
"learning_rate": 3.896177620789706e-05,
|
| 133 |
+
"loss": 5.5676,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.69,
|
| 138 |
+
"learning_rate": 3.84361465035112e-05,
|
| 139 |
+
"loss": 5.5704,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.73,
|
| 144 |
+
"learning_rate": 3.791051679912536e-05,
|
| 145 |
+
"loss": 5.5815,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.76,
|
| 150 |
+
"learning_rate": 3.73848870947395e-05,
|
| 151 |
+
"loss": 5.5608,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.79,
|
| 156 |
+
"learning_rate": 3.685925739035365e-05,
|
| 157 |
+
"loss": 5.5582,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.82,
|
| 162 |
+
"learning_rate": 3.633362768596779e-05,
|
| 163 |
+
"loss": 5.5498,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.85,
|
| 168 |
+
"learning_rate": 3.5807997981581934e-05,
|
| 169 |
+
"loss": 5.5301,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.88,
|
| 174 |
+
"learning_rate": 3.5282368277196084e-05,
|
| 175 |
+
"loss": 5.554,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.91,
|
| 180 |
+
"learning_rate": 3.475673857281023e-05,
|
| 181 |
+
"loss": 5.5397,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.95,
|
| 186 |
+
"learning_rate": 3.423110886842437e-05,
|
| 187 |
+
"loss": 5.5245,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.98,
|
| 192 |
+
"learning_rate": 3.3705479164038515e-05,
|
| 193 |
+
"loss": 5.525,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.01,
|
| 198 |
+
"learning_rate": 3.3179849459652665e-05,
|
| 199 |
+
"loss": 5.5016,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.04,
|
| 204 |
+
"learning_rate": 3.2654219755266816e-05,
|
| 205 |
+
"loss": 5.5208,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.07,
|
| 210 |
+
"learning_rate": 3.212859005088096e-05,
|
| 211 |
+
"loss": 5.5018,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.1,
|
| 216 |
+
"learning_rate": 3.16029603464951e-05,
|
| 217 |
+
"loss": 5.5157,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.14,
|
| 222 |
+
"learning_rate": 3.107733064210925e-05,
|
| 223 |
+
"loss": 5.4933,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.17,
|
| 228 |
+
"learning_rate": 3.055170093772339e-05,
|
| 229 |
+
"loss": 5.4974,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.2,
|
| 234 |
+
"learning_rate": 3.0026071233337537e-05,
|
| 235 |
+
"loss": 5.4927,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.23,
|
| 240 |
+
"learning_rate": 2.9500441528951684e-05,
|
| 241 |
+
"loss": 5.4934,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.26,
|
| 246 |
+
"learning_rate": 2.8974811824565835e-05,
|
| 247 |
+
"loss": 5.4849,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.29,
|
| 252 |
+
"learning_rate": 2.8449182120179978e-05,
|
| 253 |
+
"loss": 5.4777,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.32,
|
| 258 |
+
"learning_rate": 2.7923552415794125e-05,
|
| 259 |
+
"loss": 5.4695,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.36,
|
| 264 |
+
"learning_rate": 2.739792271140827e-05,
|
| 265 |
+
"loss": 5.4752,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.39,
|
| 270 |
+
"learning_rate": 2.6872293007022416e-05,
|
| 271 |
+
"loss": 5.4666,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.42,
|
| 276 |
+
"learning_rate": 2.634666330263656e-05,
|
| 277 |
+
"loss": 5.4621,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.45,
|
| 282 |
+
"learning_rate": 2.5821033598250703e-05,
|
| 283 |
+
"loss": 5.4808,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.48,
|
| 288 |
+
"learning_rate": 2.529540389386485e-05,
|
| 289 |
+
"loss": 5.4628,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.51,
|
| 294 |
+
"learning_rate": 2.4769774189478997e-05,
|
| 295 |
+
"loss": 5.4594,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.55,
|
| 300 |
+
"learning_rate": 2.4244144485093144e-05,
|
| 301 |
+
"loss": 5.4557,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.58,
|
| 306 |
+
"learning_rate": 2.3718514780707288e-05,
|
| 307 |
+
"loss": 5.4599,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.61,
|
| 312 |
+
"learning_rate": 2.319288507632143e-05,
|
| 313 |
+
"loss": 5.4493,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.64,
|
| 318 |
+
"learning_rate": 2.266725537193558e-05,
|
| 319 |
+
"loss": 5.4542,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.67,
|
| 324 |
+
"learning_rate": 2.2141625667549725e-05,
|
| 325 |
+
"loss": 5.4319,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.7,
|
| 330 |
+
"learning_rate": 2.1615995963163872e-05,
|
| 331 |
+
"loss": 5.4439,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.73,
|
| 336 |
+
"learning_rate": 2.1090366258778016e-05,
|
| 337 |
+
"loss": 5.4309,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.77,
|
| 342 |
+
"learning_rate": 2.0564736554392163e-05,
|
| 343 |
+
"loss": 5.4249,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.8,
|
| 348 |
+
"learning_rate": 2.003910685000631e-05,
|
| 349 |
+
"loss": 5.4351,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.83,
|
| 354 |
+
"learning_rate": 1.9513477145620453e-05,
|
| 355 |
+
"loss": 5.427,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.86,
|
| 360 |
+
"learning_rate": 1.89878474412346e-05,
|
| 361 |
+
"loss": 5.4111,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.89,
|
| 366 |
+
"learning_rate": 1.8462217736848747e-05,
|
| 367 |
+
"loss": 5.4172,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.92,
|
| 372 |
+
"learning_rate": 1.793658803246289e-05,
|
| 373 |
+
"loss": 5.4098,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.96,
|
| 378 |
+
"learning_rate": 1.7410958328077038e-05,
|
| 379 |
+
"loss": 5.3989,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.99,
|
| 384 |
+
"learning_rate": 1.688532862369118e-05,
|
| 385 |
+
"loss": 5.4145,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.02,
|
| 390 |
+
"learning_rate": 1.635969891930533e-05,
|
| 391 |
+
"loss": 5.4077,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.05,
|
| 396 |
+
"learning_rate": 1.5834069214919476e-05,
|
| 397 |
+
"loss": 5.4025,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.08,
|
| 402 |
+
"learning_rate": 1.530843951053362e-05,
|
| 403 |
+
"loss": 5.4119,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.11,
|
| 408 |
+
"learning_rate": 1.4782809806147766e-05,
|
| 409 |
+
"loss": 5.3939,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.14,
|
| 414 |
+
"learning_rate": 1.425718010176191e-05,
|
| 415 |
+
"loss": 5.4162,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.18,
|
| 420 |
+
"learning_rate": 1.3731550397376058e-05,
|
| 421 |
+
"loss": 5.4015,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.21,
|
| 426 |
+
"learning_rate": 1.3205920692990204e-05,
|
| 427 |
+
"loss": 5.4026,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.24,
|
| 432 |
+
"learning_rate": 1.2680290988604349e-05,
|
| 433 |
+
"loss": 5.3821,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.27,
|
| 438 |
+
"learning_rate": 1.2154661284218494e-05,
|
| 439 |
+
"loss": 5.3729,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.3,
|
| 444 |
+
"learning_rate": 1.162903157983264e-05,
|
| 445 |
+
"loss": 5.3854,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.33,
|
| 450 |
+
"learning_rate": 1.1103401875446785e-05,
|
| 451 |
+
"loss": 5.3743,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.37,
|
| 456 |
+
"learning_rate": 1.0577772171060932e-05,
|
| 457 |
+
"loss": 5.3816,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.4,
|
| 462 |
+
"learning_rate": 1.0052142466675077e-05,
|
| 463 |
+
"loss": 5.3738,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.43,
|
| 468 |
+
"learning_rate": 9.526512762289224e-06,
|
| 469 |
+
"loss": 5.3845,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.46,
|
| 474 |
+
"learning_rate": 9.000883057903368e-06,
|
| 475 |
+
"loss": 5.3781,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.49,
|
| 480 |
+
"learning_rate": 8.475253353517515e-06,
|
| 481 |
+
"loss": 5.3802,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.52,
|
| 486 |
+
"learning_rate": 7.94962364913166e-06,
|
| 487 |
+
"loss": 5.3651,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.55,
|
| 492 |
+
"learning_rate": 7.423993944745806e-06,
|
| 493 |
+
"loss": 5.3736,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.59,
|
| 498 |
+
"learning_rate": 6.8983642403599515e-06,
|
| 499 |
+
"loss": 5.3689,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.62,
|
| 504 |
+
"learning_rate": 6.372734535974097e-06,
|
| 505 |
+
"loss": 5.3817,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.65,
|
| 510 |
+
"learning_rate": 5.847104831588243e-06,
|
| 511 |
+
"loss": 5.3764,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.68,
|
| 516 |
+
"learning_rate": 5.321475127202389e-06,
|
| 517 |
+
"loss": 5.3618,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.71,
|
| 522 |
+
"learning_rate": 4.795845422816534e-06,
|
| 523 |
+
"loss": 5.361,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.74,
|
| 528 |
+
"learning_rate": 4.27021571843068e-06,
|
| 529 |
+
"loss": 5.3575,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.78,
|
| 534 |
+
"learning_rate": 3.744586014044826e-06,
|
| 535 |
+
"loss": 5.3689,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.81,
|
| 540 |
+
"learning_rate": 3.2189563096589715e-06,
|
| 541 |
+
"loss": 5.3684,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.84,
|
| 546 |
+
"learning_rate": 2.6933266052731173e-06,
|
| 547 |
+
"loss": 5.3442,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.87,
|
| 552 |
+
"learning_rate": 2.167696900887263e-06,
|
| 553 |
+
"loss": 5.3602,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.9,
|
| 558 |
+
"learning_rate": 1.6420671965014087e-06,
|
| 559 |
+
"loss": 5.3636,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.93,
|
| 564 |
+
"learning_rate": 1.1164374921155544e-06,
|
| 565 |
+
"loss": 5.3474,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.96,
|
| 570 |
+
"learning_rate": 5.908077877297002e-07,
|
| 571 |
+
"loss": 5.3501,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.0,
|
| 576 |
+
"learning_rate": 6.517808334384593e-08,
|
| 577 |
+
"loss": 5.3521,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.0,
|
| 582 |
+
"step": 47562,
|
| 583 |
+
"total_flos": 2.00286824366592e+17,
|
| 584 |
+
"train_loss": 5.50125317320702,
|
| 585 |
+
"train_runtime": 8519.4079,
|
| 586 |
+
"train_samples_per_second": 89.32,
|
| 587 |
+
"train_steps_per_second": 5.583
|
| 588 |
+
}
|
| 589 |
+
],
|
| 590 |
+
"max_steps": 47562,
|
| 591 |
+
"num_train_epochs": 3,
|
| 592 |
+
"total_flos": 2.00286824366592e+17,
|
| 593 |
+
"trial_name": null,
|
| 594 |
+
"trial_params": null
|
| 595 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2228c7c3560e92685b52e0da5da9796867d6757cfb03c5a32dfc8586d33d60ee
|
| 3 |
+
size 3247
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|