Upload 11 files
Browse files- config.json +33 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- trainer_state.json +106 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"problem_type": "regression",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.30.2",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 30522
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc3c08c50829812a21d897a3cb0db53c19e5e17bda79b4e1f00c278daea442de
|
3 |
+
size 437959756
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51b691f658a6457ec564b342ae249796302dd2ddad92f4e79625051e214fcdd1
|
3 |
+
size 876037381
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a5e2755de636828444a6cfb47cc68566f37cc4d0cd37f19133c034e1a48323d
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31558495b40f2ee0d94426e672d16587cc8116f4afc4aa78b49a4d4ee2d466f4
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 5972,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 2.9994976557267246e-05,
|
13 |
+
"loss": 0.0444,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.33,
|
18 |
+
"learning_rate": 2.500167448091092e-05,
|
19 |
+
"loss": 0.01,
|
20 |
+
"step": 995
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.33,
|
24 |
+
"eval_loss": 0.01052522286772728,
|
25 |
+
"eval_runtime": 579.4194,
|
26 |
+
"eval_samples_per_second": 88.345,
|
27 |
+
"eval_steps_per_second": 1.381,
|
28 |
+
"step": 995
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.67,
|
32 |
+
"learning_rate": 2.0003348961821836e-05,
|
33 |
+
"loss": 0.0087,
|
34 |
+
"step": 1990
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.67,
|
38 |
+
"eval_loss": 0.010309631004929543,
|
39 |
+
"eval_runtime": 580.7641,
|
40 |
+
"eval_samples_per_second": 88.141,
|
41 |
+
"eval_steps_per_second": 1.377,
|
42 |
+
"step": 1990
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.0,
|
46 |
+
"learning_rate": 1.5005023442732755e-05,
|
47 |
+
"loss": 0.0084,
|
48 |
+
"step": 2985
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.0,
|
52 |
+
"eval_loss": 0.01057281345129013,
|
53 |
+
"eval_runtime": 580.4744,
|
54 |
+
"eval_samples_per_second": 88.185,
|
55 |
+
"eval_steps_per_second": 1.378,
|
56 |
+
"step": 2985
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.33,
|
60 |
+
"learning_rate": 1.000669792364367e-05,
|
61 |
+
"loss": 0.0074,
|
62 |
+
"step": 3980
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.33,
|
66 |
+
"eval_loss": 0.01067323051393032,
|
67 |
+
"eval_runtime": 580.3889,
|
68 |
+
"eval_samples_per_second": 88.198,
|
69 |
+
"eval_steps_per_second": 1.378,
|
70 |
+
"step": 3980
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.67,
|
74 |
+
"learning_rate": 5.008372404554588e-06,
|
75 |
+
"loss": 0.0073,
|
76 |
+
"step": 4975
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 1.67,
|
80 |
+
"eval_loss": 0.01240999810397625,
|
81 |
+
"eval_runtime": 579.3778,
|
82 |
+
"eval_samples_per_second": 88.352,
|
83 |
+
"eval_steps_per_second": 1.381,
|
84 |
+
"step": 4975
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 2.0,
|
88 |
+
"learning_rate": 1.0046885465505694e-08,
|
89 |
+
"loss": 0.007,
|
90 |
+
"step": 5970
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.0,
|
94 |
+
"eval_loss": 0.01129997055977583,
|
95 |
+
"eval_runtime": 579.8667,
|
96 |
+
"eval_samples_per_second": 88.277,
|
97 |
+
"eval_steps_per_second": 1.38,
|
98 |
+
"step": 5970
|
99 |
+
}
|
100 |
+
],
|
101 |
+
"max_steps": 5972,
|
102 |
+
"num_train_epochs": 2,
|
103 |
+
"total_flos": 2.01113970314453e+17,
|
104 |
+
"trial_name": null,
|
105 |
+
"trial_params": null
|
106 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6fcebd1116ba4d99f3f2e008f794095742a90d27defc3077984f0d1c8893dd3
|
3 |
+
size 4027
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|