williamLyh
commited on
Commit
•
c126241
1
Parent(s):
35a7126
v1.0
Browse files- config.json +43 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- trainer_state.json +592 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3,
|
| 26 |
+
"LABEL_4": 4,
|
| 27 |
+
"LABEL_5": 5,
|
| 28 |
+
"LABEL_6": 6
|
| 29 |
+
},
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "distilbert",
|
| 32 |
+
"n_heads": 12,
|
| 33 |
+
"n_layers": 6,
|
| 34 |
+
"pad_token_id": 0,
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"qa_dropout": 0.1,
|
| 37 |
+
"seq_classif_dropout": 0.2,
|
| 38 |
+
"sinusoidal_pos_embds": false,
|
| 39 |
+
"tie_weights_": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.24.0",
|
| 42 |
+
"vocab_size": 30522
|
| 43 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f52fa524584d77d13365b0c92d437ee8caae5c352f36847ea6c74f9bc641ad49
|
| 3 |
+
size 267870893
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cdd7312e866c56b1356c73bb41ddc3f98f70e39df9a4f8abc9011ef186ea0bc
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f1da2175bdd96ff9c0b9f946ca2e7c8d2cd09e4417af27f98c1d1660643b70b
|
| 3 |
+
size 627
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": true,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "distilbert-base-uncased",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,592 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9775689803480447,
|
| 5 |
+
"global_step": 45000,
|
| 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": 8e-05,
|
| 13 |
+
"loss": 1.5093,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 7.91079194451259e-05,
|
| 19 |
+
"loss": 1.2959,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 7.82158388902518e-05,
|
| 25 |
+
"loss": 1.2604,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.13,
|
| 30 |
+
"learning_rate": 7.732375833537769e-05,
|
| 31 |
+
"loss": 1.2426,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.17,
|
| 36 |
+
"learning_rate": 7.643167778050358e-05,
|
| 37 |
+
"loss": 1.2368,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.2,
|
| 42 |
+
"learning_rate": 7.553959722562947e-05,
|
| 43 |
+
"loss": 1.2252,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.23,
|
| 48 |
+
"learning_rate": 7.464751667075538e-05,
|
| 49 |
+
"loss": 1.2204,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.26,
|
| 54 |
+
"learning_rate": 7.375543611588127e-05,
|
| 55 |
+
"loss": 1.2146,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.3,
|
| 60 |
+
"learning_rate": 7.286335556100716e-05,
|
| 61 |
+
"loss": 1.2081,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.33,
|
| 66 |
+
"learning_rate": 7.197127500613307e-05,
|
| 67 |
+
"loss": 1.2069,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.36,
|
| 72 |
+
"learning_rate": 7.107919445125896e-05,
|
| 73 |
+
"loss": 1.2017,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.4,
|
| 78 |
+
"learning_rate": 7.018711389638485e-05,
|
| 79 |
+
"loss": 1.2015,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.43,
|
| 84 |
+
"learning_rate": 6.929503334151074e-05,
|
| 85 |
+
"loss": 1.1906,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.46,
|
| 90 |
+
"learning_rate": 6.840295278663664e-05,
|
| 91 |
+
"loss": 1.1962,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.5,
|
| 96 |
+
"learning_rate": 6.751087223176253e-05,
|
| 97 |
+
"loss": 1.1939,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.53,
|
| 102 |
+
"learning_rate": 6.661879167688842e-05,
|
| 103 |
+
"loss": 1.1844,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.56,
|
| 108 |
+
"learning_rate": 6.572671112201433e-05,
|
| 109 |
+
"loss": 1.1923,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.6,
|
| 114 |
+
"learning_rate": 6.483463056714022e-05,
|
| 115 |
+
"loss": 1.1864,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.63,
|
| 120 |
+
"learning_rate": 6.394255001226611e-05,
|
| 121 |
+
"loss": 1.1801,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.66,
|
| 126 |
+
"learning_rate": 6.305046945739202e-05,
|
| 127 |
+
"loss": 1.1832,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.66,
|
| 132 |
+
"eval_accuracy": 0.5757644176483154,
|
| 133 |
+
"eval_loss": 1.1787368059158325,
|
| 134 |
+
"eval_runtime": 214.7637,
|
| 135 |
+
"eval_samples_per_second": 4547.505,
|
| 136 |
+
"eval_steps_per_second": 15.161,
|
| 137 |
+
"step": 10000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.69,
|
| 141 |
+
"learning_rate": 6.215838890251789e-05,
|
| 142 |
+
"loss": 1.1804,
|
| 143 |
+
"step": 10500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.73,
|
| 147 |
+
"learning_rate": 6.12663083476438e-05,
|
| 148 |
+
"loss": 1.1813,
|
| 149 |
+
"step": 11000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.76,
|
| 153 |
+
"learning_rate": 6.037422779276969e-05,
|
| 154 |
+
"loss": 1.1795,
|
| 155 |
+
"step": 11500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.79,
|
| 159 |
+
"learning_rate": 5.9482147237895586e-05,
|
| 160 |
+
"loss": 1.178,
|
| 161 |
+
"step": 12000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.83,
|
| 165 |
+
"learning_rate": 5.8590066683021484e-05,
|
| 166 |
+
"loss": 1.1815,
|
| 167 |
+
"step": 12500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.86,
|
| 171 |
+
"learning_rate": 5.769798612814738e-05,
|
| 172 |
+
"loss": 1.1745,
|
| 173 |
+
"step": 13000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.89,
|
| 177 |
+
"learning_rate": 5.680590557327327e-05,
|
| 178 |
+
"loss": 1.1744,
|
| 179 |
+
"step": 13500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.93,
|
| 183 |
+
"learning_rate": 5.591382501839917e-05,
|
| 184 |
+
"loss": 1.1745,
|
| 185 |
+
"step": 14000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.96,
|
| 189 |
+
"learning_rate": 5.5021744463525054e-05,
|
| 190 |
+
"loss": 1.1712,
|
| 191 |
+
"step": 14500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.99,
|
| 195 |
+
"learning_rate": 5.412966390865095e-05,
|
| 196 |
+
"loss": 1.1686,
|
| 197 |
+
"step": 15000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.03,
|
| 201 |
+
"learning_rate": 5.323758335377685e-05,
|
| 202 |
+
"loss": 1.1572,
|
| 203 |
+
"step": 15500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.06,
|
| 207 |
+
"learning_rate": 5.234550279890275e-05,
|
| 208 |
+
"loss": 1.1503,
|
| 209 |
+
"step": 16000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.09,
|
| 213 |
+
"learning_rate": 5.145342224402864e-05,
|
| 214 |
+
"loss": 1.1519,
|
| 215 |
+
"step": 16500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.12,
|
| 219 |
+
"learning_rate": 5.0561341689154536e-05,
|
| 220 |
+
"loss": 1.1502,
|
| 221 |
+
"step": 17000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.16,
|
| 225 |
+
"learning_rate": 4.9669261134280434e-05,
|
| 226 |
+
"loss": 1.1465,
|
| 227 |
+
"step": 17500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.19,
|
| 231 |
+
"learning_rate": 4.877718057940632e-05,
|
| 232 |
+
"loss": 1.1534,
|
| 233 |
+
"step": 18000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.22,
|
| 237 |
+
"learning_rate": 4.7885100024532215e-05,
|
| 238 |
+
"loss": 1.1505,
|
| 239 |
+
"step": 18500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.26,
|
| 243 |
+
"learning_rate": 4.699301946965811e-05,
|
| 244 |
+
"loss": 1.1492,
|
| 245 |
+
"step": 19000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.29,
|
| 249 |
+
"learning_rate": 4.610093891478401e-05,
|
| 250 |
+
"loss": 1.1518,
|
| 251 |
+
"step": 19500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.32,
|
| 255 |
+
"learning_rate": 4.52088583599099e-05,
|
| 256 |
+
"loss": 1.1492,
|
| 257 |
+
"step": 20000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.32,
|
| 261 |
+
"eval_accuracy": 0.5826605558395386,
|
| 262 |
+
"eval_loss": 1.1605184078216553,
|
| 263 |
+
"eval_runtime": 207.3392,
|
| 264 |
+
"eval_samples_per_second": 4710.344,
|
| 265 |
+
"eval_steps_per_second": 15.704,
|
| 266 |
+
"step": 20000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.36,
|
| 270 |
+
"learning_rate": 4.43167778050358e-05,
|
| 271 |
+
"loss": 1.1465,
|
| 272 |
+
"step": 20500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.39,
|
| 276 |
+
"learning_rate": 4.34246972501617e-05,
|
| 277 |
+
"loss": 1.1472,
|
| 278 |
+
"step": 21000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.42,
|
| 282 |
+
"learning_rate": 4.2532616695287595e-05,
|
| 283 |
+
"loss": 1.1507,
|
| 284 |
+
"step": 21500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.46,
|
| 288 |
+
"learning_rate": 4.164053614041348e-05,
|
| 289 |
+
"loss": 1.1466,
|
| 290 |
+
"step": 22000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.49,
|
| 294 |
+
"learning_rate": 4.074845558553938e-05,
|
| 295 |
+
"loss": 1.1479,
|
| 296 |
+
"step": 22500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.52,
|
| 300 |
+
"learning_rate": 3.985637503066527e-05,
|
| 301 |
+
"loss": 1.1425,
|
| 302 |
+
"step": 23000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.55,
|
| 306 |
+
"learning_rate": 3.8964294475791165e-05,
|
| 307 |
+
"loss": 1.1497,
|
| 308 |
+
"step": 23500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.59,
|
| 312 |
+
"learning_rate": 3.807221392091706e-05,
|
| 313 |
+
"loss": 1.1394,
|
| 314 |
+
"step": 24000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.62,
|
| 318 |
+
"learning_rate": 3.718013336604296e-05,
|
| 319 |
+
"loss": 1.1472,
|
| 320 |
+
"step": 24500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.65,
|
| 324 |
+
"learning_rate": 3.628805281116885e-05,
|
| 325 |
+
"loss": 1.1444,
|
| 326 |
+
"step": 25000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.69,
|
| 330 |
+
"learning_rate": 3.539597225629475e-05,
|
| 331 |
+
"loss": 1.1439,
|
| 332 |
+
"step": 25500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.72,
|
| 336 |
+
"learning_rate": 3.450389170142064e-05,
|
| 337 |
+
"loss": 1.1468,
|
| 338 |
+
"step": 26000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.75,
|
| 342 |
+
"learning_rate": 3.361181114654654e-05,
|
| 343 |
+
"loss": 1.1467,
|
| 344 |
+
"step": 26500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.79,
|
| 348 |
+
"learning_rate": 3.271973059167243e-05,
|
| 349 |
+
"loss": 1.1417,
|
| 350 |
+
"step": 27000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.82,
|
| 354 |
+
"learning_rate": 3.182765003679833e-05,
|
| 355 |
+
"loss": 1.1423,
|
| 356 |
+
"step": 27500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.85,
|
| 360 |
+
"learning_rate": 3.0935569481924224e-05,
|
| 361 |
+
"loss": 1.1444,
|
| 362 |
+
"step": 28000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.89,
|
| 366 |
+
"learning_rate": 3.0043488927050112e-05,
|
| 367 |
+
"loss": 1.1382,
|
| 368 |
+
"step": 28500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.92,
|
| 372 |
+
"learning_rate": 2.915140837217601e-05,
|
| 373 |
+
"loss": 1.1392,
|
| 374 |
+
"step": 29000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.95,
|
| 378 |
+
"learning_rate": 2.8259327817301904e-05,
|
| 379 |
+
"loss": 1.1407,
|
| 380 |
+
"step": 29500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.99,
|
| 384 |
+
"learning_rate": 2.73672472624278e-05,
|
| 385 |
+
"loss": 1.143,
|
| 386 |
+
"step": 30000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.99,
|
| 390 |
+
"eval_accuracy": 0.5862544775009155,
|
| 391 |
+
"eval_loss": 1.1498275995254517,
|
| 392 |
+
"eval_runtime": 205.0061,
|
| 393 |
+
"eval_samples_per_second": 4763.951,
|
| 394 |
+
"eval_steps_per_second": 15.882,
|
| 395 |
+
"step": 30000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.02,
|
| 399 |
+
"learning_rate": 2.6475166707553693e-05,
|
| 400 |
+
"loss": 1.1246,
|
| 401 |
+
"step": 30500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.05,
|
| 405 |
+
"learning_rate": 2.5583086152679587e-05,
|
| 406 |
+
"loss": 1.1176,
|
| 407 |
+
"step": 31000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.08,
|
| 411 |
+
"learning_rate": 2.4691005597805485e-05,
|
| 412 |
+
"loss": 1.1131,
|
| 413 |
+
"step": 31500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.12,
|
| 417 |
+
"learning_rate": 2.379892504293138e-05,
|
| 418 |
+
"loss": 1.1106,
|
| 419 |
+
"step": 32000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.15,
|
| 423 |
+
"learning_rate": 2.2906844488057273e-05,
|
| 424 |
+
"loss": 1.1104,
|
| 425 |
+
"step": 32500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.18,
|
| 429 |
+
"learning_rate": 2.2014763933183168e-05,
|
| 430 |
+
"loss": 1.1127,
|
| 431 |
+
"step": 33000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.22,
|
| 435 |
+
"learning_rate": 2.1122683378309062e-05,
|
| 436 |
+
"loss": 1.1113,
|
| 437 |
+
"step": 33500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.25,
|
| 441 |
+
"learning_rate": 2.023060282343496e-05,
|
| 442 |
+
"loss": 1.1151,
|
| 443 |
+
"step": 34000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.28,
|
| 447 |
+
"learning_rate": 1.9338522268560854e-05,
|
| 448 |
+
"loss": 1.1177,
|
| 449 |
+
"step": 34500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.32,
|
| 453 |
+
"learning_rate": 1.8446441713686748e-05,
|
| 454 |
+
"loss": 1.113,
|
| 455 |
+
"step": 35000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.35,
|
| 459 |
+
"learning_rate": 1.7554361158812642e-05,
|
| 460 |
+
"loss": 1.11,
|
| 461 |
+
"step": 35500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.38,
|
| 465 |
+
"learning_rate": 1.6662280603938537e-05,
|
| 466 |
+
"loss": 1.1172,
|
| 467 |
+
"step": 36000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.42,
|
| 471 |
+
"learning_rate": 1.577020004906443e-05,
|
| 472 |
+
"loss": 1.1127,
|
| 473 |
+
"step": 36500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.45,
|
| 477 |
+
"learning_rate": 1.4878119494190325e-05,
|
| 478 |
+
"loss": 1.1116,
|
| 479 |
+
"step": 37000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.48,
|
| 483 |
+
"learning_rate": 1.3986038939316221e-05,
|
| 484 |
+
"loss": 1.1093,
|
| 485 |
+
"step": 37500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.51,
|
| 489 |
+
"learning_rate": 1.3093958384442116e-05,
|
| 490 |
+
"loss": 1.1152,
|
| 491 |
+
"step": 38000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.55,
|
| 495 |
+
"learning_rate": 1.2201877829568012e-05,
|
| 496 |
+
"loss": 1.1084,
|
| 497 |
+
"step": 38500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.58,
|
| 501 |
+
"learning_rate": 1.1309797274693906e-05,
|
| 502 |
+
"loss": 1.1095,
|
| 503 |
+
"step": 39000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.61,
|
| 507 |
+
"learning_rate": 1.0417716719819802e-05,
|
| 508 |
+
"loss": 1.1071,
|
| 509 |
+
"step": 39500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.65,
|
| 513 |
+
"learning_rate": 9.525636164945695e-06,
|
| 514 |
+
"loss": 1.1088,
|
| 515 |
+
"step": 40000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.65,
|
| 519 |
+
"eval_accuracy": 0.5878129005432129,
|
| 520 |
+
"eval_loss": 1.149354338645935,
|
| 521 |
+
"eval_runtime": 211.165,
|
| 522 |
+
"eval_samples_per_second": 4625.004,
|
| 523 |
+
"eval_steps_per_second": 15.419,
|
| 524 |
+
"step": 40000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.68,
|
| 528 |
+
"learning_rate": 8.63355561007159e-06,
|
| 529 |
+
"loss": 1.1103,
|
| 530 |
+
"step": 40500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.71,
|
| 534 |
+
"learning_rate": 7.741475055197485e-06,
|
| 535 |
+
"loss": 1.113,
|
| 536 |
+
"step": 41000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.75,
|
| 540 |
+
"learning_rate": 6.849394500323379e-06,
|
| 541 |
+
"loss": 1.108,
|
| 542 |
+
"step": 41500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.78,
|
| 546 |
+
"learning_rate": 5.9573139454492745e-06,
|
| 547 |
+
"loss": 1.1082,
|
| 548 |
+
"step": 42000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.81,
|
| 552 |
+
"learning_rate": 5.06523339057517e-06,
|
| 553 |
+
"loss": 1.1121,
|
| 554 |
+
"step": 42500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.85,
|
| 558 |
+
"learning_rate": 4.173152835701064e-06,
|
| 559 |
+
"loss": 1.1051,
|
| 560 |
+
"step": 43000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.88,
|
| 564 |
+
"learning_rate": 3.281072280826959e-06,
|
| 565 |
+
"loss": 1.1057,
|
| 566 |
+
"step": 43500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.91,
|
| 570 |
+
"learning_rate": 2.3889917259528535e-06,
|
| 571 |
+
"loss": 1.1155,
|
| 572 |
+
"step": 44000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.94,
|
| 576 |
+
"learning_rate": 1.4969111710787484e-06,
|
| 577 |
+
"loss": 1.1102,
|
| 578 |
+
"step": 44500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.98,
|
| 582 |
+
"learning_rate": 6.048306162046434e-07,
|
| 583 |
+
"loss": 1.1091,
|
| 584 |
+
"step": 45000
|
| 585 |
+
}
|
| 586 |
+
],
|
| 587 |
+
"max_steps": 45339,
|
| 588 |
+
"num_train_epochs": 3,
|
| 589 |
+
"total_flos": 1.1008030583503237e+17,
|
| 590 |
+
"trial_name": null,
|
| 591 |
+
"trial_params": null
|
| 592 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8d7c48dbfcbf8f0953c3a45d3d538575ba289436d7c48a78ad41e95c27bca62
|
| 3 |
+
size 3387
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|