Upload 6 files
Browse files- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +40 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2e97a54b1673d2321ce4255854c59814512024e3d9cd0e85b5a7baa4902348c
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/home/work/chenming6/ee/text-similarity/promcse_zh/promcse/bert_pytorch", "do_basic_tokenize": true, "never_split": null}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.984819734345351,
|
| 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": 0.95,
|
| 12 |
+
"learning_rate": 2.715370018975332e-05,
|
| 13 |
+
"loss": 1.2474,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.9,
|
| 18 |
+
"learning_rate": 2.4307400379506644e-05,
|
| 19 |
+
"loss": 0.9239,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.85,
|
| 24 |
+
"learning_rate": 2.146110056925996e-05,
|
| 25 |
+
"loss": 0.8101,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 3.8,
|
| 30 |
+
"learning_rate": 1.861480075901328e-05,
|
| 31 |
+
"loss": 0.731,
|
| 32 |
+
"step": 2000
|
| 33 |
+
}
|
| 34 |
+
],
|
| 35 |
+
"max_steps": 5270,
|
| 36 |
+
"num_train_epochs": 10,
|
| 37 |
+
"total_flos": 126741142877995008,
|
| 38 |
+
"trial_name": null,
|
| 39 |
+
"trial_params": null
|
| 40 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3b736552ed9c44bd4b61373b647bbeec116d0b8e5ad6d0962c39927f2d12153
|
| 3 |
+
size 2095
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|