Theoreticallyhugo commited on
Commit
dc1fed1
1 Parent(s): a7de85e

Training in progress, epoch 1, checkpoint

Browse files
checkpoint-4628/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.38.2",
32
+ "vocab_size": 30522
33
+ }
checkpoint-4628/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0f915737a39bdfcab78d0d4da824969099279459a66257cf6a6236174262114
3
+ size 267832560
checkpoint-4628/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f89af67f9a0918e329c771bbf8e20e77e65bff643e334ebfbbec412d1458af
3
+ size 535727290
checkpoint-4628/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac5904dacd5ef71f108da1c8f22bcd7b8e38f85490fed73c466a30e4e14a2b3
3
+ size 14244
checkpoint-4628/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa572e3f3cfe5c84c25b09e9edd570728039bddb90178fd43e0ac9ea7a040fb
3
+ size 1064
checkpoint-4628/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
+ }
checkpoint-4628/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4628/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
+ }
checkpoint-4628/trainer_state.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 5.741369932366069e-06,
3
+ "best_model_checkpoint": "insuff_supported_arguments/checkpoint-4628",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4628,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11,
13
+ "grad_norm": 0.03457513824105263,
14
+ "learning_rate": 1.9279746470757707e-05,
15
+ "loss": 0.1457,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.22,
20
+ "grad_norm": 0.0055348570458590984,
21
+ "learning_rate": 1.8559492941515416e-05,
22
+ "loss": 0.0066,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.32,
27
+ "grad_norm": 0.002291068434715271,
28
+ "learning_rate": 1.783923941227312e-05,
29
+ "loss": 0.0014,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.43,
34
+ "grad_norm": 0.003473889548331499,
35
+ "learning_rate": 1.7118985883030827e-05,
36
+ "loss": 0.0114,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.54,
41
+ "grad_norm": 0.0016763019375503063,
42
+ "learning_rate": 1.6398732353788535e-05,
43
+ "loss": 0.0031,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.65,
48
+ "grad_norm": 0.0010241195559501648,
49
+ "learning_rate": 1.567847882454624e-05,
50
+ "loss": 0.0012,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.76,
55
+ "grad_norm": 0.00029286000062711537,
56
+ "learning_rate": 1.4958225295303948e-05,
57
+ "loss": 0.0,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.86,
62
+ "grad_norm": 0.0003028396749868989,
63
+ "learning_rate": 1.4237971766061655e-05,
64
+ "loss": 0.0,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.97,
69
+ "grad_norm": 0.0002893279306590557,
70
+ "learning_rate": 1.3517718236819362e-05,
71
+ "loss": 0.0,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 1.0,
76
+ "eval_NEGATIVE": {
77
+ "f1-score": 1.0,
78
+ "precision": 1.0,
79
+ "recall": 1.0,
80
+ "support": 13620.0
81
+ },
82
+ "eval_POSITIVE": {
83
+ "f1-score": 1.0,
84
+ "precision": 1.0,
85
+ "recall": 1.0,
86
+ "support": 6960.0
87
+ },
88
+ "eval_accuracy": 1.0,
89
+ "eval_loss": 5.741369932366069e-06,
90
+ "eval_macro avg": {
91
+ "f1-score": 1.0,
92
+ "precision": 1.0,
93
+ "recall": 1.0,
94
+ "support": 20580.0
95
+ },
96
+ "eval_runtime": 11.5238,
97
+ "eval_samples_per_second": 1785.875,
98
+ "eval_steps_per_second": 111.682,
99
+ "eval_weighted avg": {
100
+ "f1-score": 1.0,
101
+ "precision": 1.0,
102
+ "recall": 1.0,
103
+ "support": 20580.0
104
+ },
105
+ "step": 4628
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 13884,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 3,
112
+ "save_steps": 500,
113
+ "total_flos": 2984335256486880.0,
114
+ "train_batch_size": 16,
115
+ "trial_name": null,
116
+ "trial_params": null
117
+ }
checkpoint-4628/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adcc91ae6efcb4a19e77c6c0c5e98c1e2ddf87cbe2bd793b17ef56c157e4dc5d
3
+ size 4984
checkpoint-4628/vocab.txt ADDED
The diff for this file is too large to render. See raw diff