AilingDAI commited on
Commit
15f0aed
·
verified ·
1 Parent(s): 2a0bcfa

Training in progress, epoch 3

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b56433d425c1c5233d43980b8cacc41ea7ffd6169e01838e3d9d0e5d2067a8ca
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f500bac759882aa4fa447765923ac065ade0781957e1fd44f4777f5fa1d16b
3
  size 267832560
run-1/checkpoint-3207/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-3207/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f500bac759882aa4fa447765923ac065ade0781957e1fd44f4777f5fa1d16b
3
+ size 267832560
run-1/checkpoint-3207/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfca1b38e1f9be3dcee3614e081f8fbafae072f7e3db6657d011da5e2892bff
3
+ size 535727290
run-1/checkpoint-3207/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:632922a2d963c0d3aebf639416d896b42acdf51bf4fa2c9878d31ff749bfdedd
3
+ size 14308
run-1/checkpoint-3207/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f3e13d848b02e8bd8ab811e8c41be7a57d374879bff967692055b8ed7c20976
3
+ size 1064
run-1/checkpoint-3207/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
+ }
run-1/checkpoint-3207/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-3207/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-3207/trainer_state.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.34259983822816975,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-3207",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3207,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "grad_norm": 3.3132574558258057,
14
+ "learning_rate": 5.3487951435688824e-05,
15
+ "loss": 0.6128,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.94,
20
+ "grad_norm": 10.235213279724121,
21
+ "learning_rate": 4.360838892447921e-05,
22
+ "loss": 0.5719,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.6078479886054993,
28
+ "eval_matthews_correlation": 0.17287049484713765,
29
+ "eval_runtime": 0.8538,
30
+ "eval_samples_per_second": 1221.595,
31
+ "eval_steps_per_second": 77.301,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4,
36
+ "grad_norm": 9.716071128845215,
37
+ "learning_rate": 3.3728826413269603e-05,
38
+ "loss": 0.445,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 1.87,
43
+ "grad_norm": 7.158620834350586,
44
+ "learning_rate": 2.3849263902059996e-05,
45
+ "loss": 0.4148,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.7100014090538025,
51
+ "eval_matthews_correlation": 0.3237133903096396,
52
+ "eval_runtime": 0.8592,
53
+ "eval_samples_per_second": 1213.872,
54
+ "eval_steps_per_second": 76.813,
55
+ "step": 2138
56
+ },
57
+ {
58
+ "epoch": 2.34,
59
+ "grad_norm": 5.8206868171691895,
60
+ "learning_rate": 1.3969701390850386e-05,
61
+ "loss": 0.287,
62
+ "step": 2500
63
+ },
64
+ {
65
+ "epoch": 2.81,
66
+ "grad_norm": 0.13527898490428925,
67
+ "learning_rate": 4.090138879640778e-06,
68
+ "loss": 0.2581,
69
+ "step": 3000
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "eval_loss": 1.0142927169799805,
74
+ "eval_matthews_correlation": 0.34259983822816975,
75
+ "eval_runtime": 0.7591,
76
+ "eval_samples_per_second": 1373.987,
77
+ "eval_steps_per_second": 86.944,
78
+ "step": 3207
79
+ }
80
+ ],
81
+ "logging_steps": 500,
82
+ "max_steps": 3207,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 3,
85
+ "save_steps": 500,
86
+ "total_flos": 113168295788916.0,
87
+ "train_batch_size": 8,
88
+ "trial_name": null,
89
+ "trial_params": {
90
+ "learning_rate": 6.336751394689843e-05,
91
+ "num_train_epochs": 3,
92
+ "per_device_train_batch_size": 8,
93
+ "seed": 33
94
+ }
95
+ }
run-1/checkpoint-3207/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6767fea303015c1edac213c398e0894020cd1b6ef3eb74b74eb055ccb779eab2
3
+ size 4984
run-1/checkpoint-3207/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160395.52e0cb6c1736.459.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a8618eeb803809dbaf10d6fbbed664e4aa7417da4901061ffbbf6fd955a27c3
3
- size 6310
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee938309d58c9f5f31b3b3e8b6941ff103a69edc3b381f66395995a322d274a3
3
+ size 7210