joseph10 commited on
Commit
e8ad578
1 Parent(s): 03c174e

Training in progress, epoch 8

Browse files
logs/events.out.tfevents.1702273519.joseph_legion.22340.17 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be9ceeb65a2d4c542e2bd5f292fa093efdb9f206a40e01665a4f766bd6681061
3
- size 7806
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4acaa654f23aae5d49bc471745be1690fda192214da6645714f529c686bea1
3
+ size 8640
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d7c9b620b2968a05857cf53a1d2e01d7da46688609b42ec4641f33a64ea5cb7
3
  size 44692608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219f1b8f2951fb85d2f6e004e1afa8aa6b08b20144aee377cf17acfc094d58db
3
  size 44692608
run-4/checkpoint-1576/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-4/checkpoint-1576/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219f1b8f2951fb85d2f6e004e1afa8aa6b08b20144aee377cf17acfc094d58db
3
+ size 44692608
run-4/checkpoint-1576/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17dcf3a012a9c96a907039f02428888ba0c8e371aebcfede9780ae4e9899fef8
3
+ size 89430010
run-4/checkpoint-1576/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122b0085e1abf041f99bc171f20126b5b68e4be68ec478e6a72e399dceb6c126
3
+ size 14308
run-4/checkpoint-1576/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9bdc50b93f7c3362130b585ff657702becd3008213d1f559e6261381f2be19
3
+ size 1064
run-4/checkpoint-1576/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-4/checkpoint-1576/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-4/checkpoint-1576/trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7722345747637577,
3
+ "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-4\\checkpoint-1182",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1576,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 2.1327047597286744e-06,
14
+ "loss": 0.3205,
15
+ "step": 197
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7181767648693719,
20
+ "eval_loss": 0.3056386411190033,
21
+ "eval_runtime": 125.6972,
22
+ "eval_samples_per_second": 57.249,
23
+ "eval_steps_per_second": 0.453,
24
+ "step": 197
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.8280326511960069e-06,
29
+ "loss": 0.3065,
30
+ "step": 394
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.7493051695386326,
35
+ "eval_loss": 0.2966243028640747,
36
+ "eval_runtime": 125.6168,
37
+ "eval_samples_per_second": 57.285,
38
+ "eval_steps_per_second": 0.454,
39
+ "step": 394
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 1.523360542663339e-06,
44
+ "loss": 0.3012,
45
+ "step": 591
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7602834908282379,
50
+ "eval_loss": 0.292987197637558,
51
+ "eval_runtime": 125.5971,
52
+ "eval_samples_per_second": 57.294,
53
+ "eval_steps_per_second": 0.454,
54
+ "step": 591
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 1.2186884341306712e-06,
59
+ "loss": 0.2993,
60
+ "step": 788
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.7659811006114509,
65
+ "eval_loss": 0.2911587357521057,
66
+ "eval_runtime": 125.8135,
67
+ "eval_samples_per_second": 57.196,
68
+ "eval_steps_per_second": 0.453,
69
+ "step": 788
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 9.140163255980034e-07,
74
+ "loss": 0.2978,
75
+ "step": 985
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.7695942190105615,
80
+ "eval_loss": 0.2902683913707733,
81
+ "eval_runtime": 125.6067,
82
+ "eval_samples_per_second": 57.29,
83
+ "eval_steps_per_second": 0.454,
84
+ "step": 985
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 6.093442170653356e-07,
89
+ "loss": 0.2964,
90
+ "step": 1182
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.7722345747637577,
95
+ "eval_loss": 0.2897145748138428,
96
+ "eval_runtime": 125.7458,
97
+ "eval_samples_per_second": 57.227,
98
+ "eval_steps_per_second": 0.453,
99
+ "step": 1182
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 3.046721085326678e-07,
104
+ "loss": 0.2959,
105
+ "step": 1379
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.7718176764869372,
110
+ "eval_loss": 0.28957682847976685,
111
+ "eval_runtime": 125.8315,
112
+ "eval_samples_per_second": 57.188,
113
+ "eval_steps_per_second": 0.453,
114
+ "step": 1379
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 0.0,
119
+ "loss": 0.2961,
120
+ "step": 1576
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.7722345747637577,
125
+ "eval_loss": 0.2894397974014282,
126
+ "eval_runtime": 125.7279,
127
+ "eval_samples_per_second": 57.235,
128
+ "eval_steps_per_second": 0.453,
129
+ "step": 1576
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 1576,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 8,
136
+ "save_steps": 500,
137
+ "total_flos": 353904216589332.0,
138
+ "trial_name": null,
139
+ "trial_params": {
140
+ "alpha": 0.4889425582875847,
141
+ "learning_rate": 2.4373768682613424e-06,
142
+ "num_train_epochs": 8,
143
+ "temperature": 30
144
+ }
145
+ }
run-4/checkpoint-1576/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981a91f79573183152619d189d97ff4841d075d34b88f159d3995abce38af003
3
+ size 4792
run-4/checkpoint-1576/vocab.txt ADDED
The diff for this file is too large to render. See raw diff