Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
4e75df1
·
verified ·
1 Parent(s): 4ceba60

Training in progress, epoch 7

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1713589040.1376c752d37a.9760.24 +2 -2
  2. model.safetensors +1 -1
  3. run-24/checkpoint-1284/config.json +34 -0
  4. run-24/checkpoint-1284/model.safetensors +3 -0
  5. run-24/checkpoint-1284/optimizer.pt +3 -0
  6. run-24/checkpoint-1284/rng_state.pth +3 -0
  7. run-24/checkpoint-1284/scheduler.pt +3 -0
  8. run-24/checkpoint-1284/special_tokens_map.json +7 -0
  9. run-24/checkpoint-1284/tokenizer.json +0 -0
  10. run-24/checkpoint-1284/tokenizer_config.json +57 -0
  11. run-24/checkpoint-1284/trainer_state.json +146 -0
  12. run-24/checkpoint-1284/training_args.bin +3 -0
  13. run-24/checkpoint-1284/vocab.txt +0 -0
  14. run-24/checkpoint-1498/config.json +34 -0
  15. run-24/checkpoint-1498/model.safetensors +3 -0
  16. run-24/checkpoint-1498/optimizer.pt +3 -0
  17. run-24/checkpoint-1498/rng_state.pth +3 -0
  18. run-24/checkpoint-1498/scheduler.pt +3 -0
  19. run-24/checkpoint-1498/special_tokens_map.json +7 -0
  20. run-24/checkpoint-1498/tokenizer.json +0 -0
  21. run-24/checkpoint-1498/tokenizer_config.json +57 -0
  22. run-24/checkpoint-1498/trainer_state.json +166 -0
  23. run-24/checkpoint-1498/training_args.bin +3 -0
  24. run-24/checkpoint-1498/vocab.txt +0 -0
logs/events.out.tfevents.1713589040.1376c752d37a.9760.24 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d60de3a08b6bd218b54854730f93b1bb77cb13f21821eba4d0e51516de35c6ea
3
- size 8402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3548a7462a514b6572d24de8510b65bdda0188a431e25253cf14e57e48752c
3
+ size 9862
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c55063ec3f26eb95890216125a933f616ef2414e289477fd3bc5c7d12a9bfd5
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ef49825a5969a0eeb028ab443fe74268e2aca9f24b5d4598c982abe29c77fb
3
  size 17549312
run-24/checkpoint-1284/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
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": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-24/checkpoint-1284/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6120755b282f714c95af9d9607d08e6aecbd517d68857c91d3172e2f48d07e86
3
+ size 17549312
run-24/checkpoint-1284/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c237dce2b549bb583950270d71ad6dad2554846775dc54a08002414b96c664a
3
+ size 35123898
run-24/checkpoint-1284/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa74fb48b8739c352726086ee20186281632dbf682ba20839e3522db3e3b091
3
+ size 14308
run-24/checkpoint-1284/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ab30c9d396127c0de9c572779bf267d391fe96e5a653b623f7b5e6b0c041e66
3
+ size 1064
run-24/checkpoint-1284/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-24/checkpoint-1284/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-1284/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-24/checkpoint-1284/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7697715289982425,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-1284",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1284,
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
+ "grad_norm": 7.816347122192383,
14
+ "learning_rate": 0.0002514027907655722,
15
+ "loss": 0.603,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.705916813122437,
21
+ "eval_f1": 0.4670912951167728,
22
+ "eval_loss": 0.5544006824493408,
23
+ "eval_mcc": 0.2876964932013613,
24
+ "eval_precision": 0.5898123324396782,
25
+ "eval_recall": 0.3866432337434095,
26
+ "eval_runtime": 3.1616,
27
+ "eval_samples_per_second": 539.92,
28
+ "eval_steps_per_second": 17.08,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.7939634323120117,
34
+ "learning_rate": 0.00021997744191987566,
35
+ "loss": 0.531,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7352079671939075,
41
+ "eval_f1": 0.5368852459016393,
42
+ "eval_loss": 0.5183561444282532,
43
+ "eval_mcc": 0.3684302929196794,
44
+ "eval_precision": 0.6437346437346437,
45
+ "eval_recall": 0.46045694200351495,
46
+ "eval_runtime": 3.2232,
47
+ "eval_samples_per_second": 529.598,
48
+ "eval_steps_per_second": 16.754,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.888092279434204,
54
+ "learning_rate": 0.00018855209307417915,
55
+ "loss": 0.502,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7451669595782073,
61
+ "eval_f1": 0.48520710059171596,
62
+ "eval_loss": 0.5155817270278931,
63
+ "eval_mcc": 0.3814260429877007,
64
+ "eval_precision": 0.7427536231884058,
65
+ "eval_recall": 0.3602811950790861,
66
+ "eval_runtime": 3.1891,
67
+ "eval_samples_per_second": 535.256,
68
+ "eval_steps_per_second": 16.933,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 3.3760223388671875,
74
+ "learning_rate": 0.00015712674422848263,
75
+ "loss": 0.4897,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7422378441710603,
81
+ "eval_f1": 0.45812807881773393,
82
+ "eval_loss": 0.5075758695602417,
83
+ "eval_mcc": 0.37344089980427997,
84
+ "eval_precision": 0.7654320987654321,
85
+ "eval_recall": 0.3268892794376098,
86
+ "eval_runtime": 3.1359,
87
+ "eval_samples_per_second": 544.344,
88
+ "eval_steps_per_second": 17.22,
89
+ "step": 856
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 11.075637817382812,
94
+ "learning_rate": 0.0001257013953827861,
95
+ "loss": 0.4761,
96
+ "step": 1070
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7568834212067955,
101
+ "eval_f1": 0.5870646766169154,
102
+ "eval_loss": 0.49240508675575256,
103
+ "eval_mcc": 0.42649635439740835,
104
+ "eval_precision": 0.676605504587156,
105
+ "eval_recall": 0.5184534270650264,
106
+ "eval_runtime": 3.1156,
107
+ "eval_samples_per_second": 547.891,
108
+ "eval_steps_per_second": 17.332,
109
+ "step": 1070
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 6.270783424377441,
114
+ "learning_rate": 9.427604653708957e-05,
115
+ "loss": 0.4671,
116
+ "step": 1284
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7697715289982425,
121
+ "eval_f1": 0.6288951841359773,
122
+ "eval_loss": 0.48595207929611206,
123
+ "eval_mcc": 0.4660789140327505,
124
+ "eval_precision": 0.6795918367346939,
125
+ "eval_recall": 0.5852372583479789,
126
+ "eval_runtime": 3.1299,
127
+ "eval_samples_per_second": 545.38,
128
+ "eval_steps_per_second": 17.253,
129
+ "step": 1284
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 1926,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 9,
136
+ "save_steps": 500,
137
+ "total_flos": 3148653986640.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.9932022812512611,
142
+ "learning_rate": 0.0002828281396112687,
143
+ "num_train_epochs": 9,
144
+ "temperature": 23
145
+ }
146
+ }
run-24/checkpoint-1284/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056a4a07ea3eb275e3c290638752eb45bcffa89ead6519b5845088d41a30cf92
3
+ size 5048
run-24/checkpoint-1284/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-1498/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
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": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-24/checkpoint-1498/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ef49825a5969a0eeb028ab443fe74268e2aca9f24b5d4598c982abe29c77fb
3
+ size 17549312
run-24/checkpoint-1498/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df6b5e7f4dd5194cc7ff19de32246f6ec429c44124562fd7d11a3ce62a1d306a
3
+ size 35123898
run-24/checkpoint-1498/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec7baa77763623ab6f5c0a3afb24b20f15950a2841a41419e9c31b1269a80a7
3
+ size 14308
run-24/checkpoint-1498/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5053a0bf47542db805887977ba98881f4cd355af7a9f4fb18ba3458edc4bdd60
3
+ size 1064
run-24/checkpoint-1498/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-24/checkpoint-1498/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-1498/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-24/checkpoint-1498/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7697715289982425,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-1284",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1498,
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
+ "grad_norm": 7.816347122192383,
14
+ "learning_rate": 0.0002514027907655722,
15
+ "loss": 0.603,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.705916813122437,
21
+ "eval_f1": 0.4670912951167728,
22
+ "eval_loss": 0.5544006824493408,
23
+ "eval_mcc": 0.2876964932013613,
24
+ "eval_precision": 0.5898123324396782,
25
+ "eval_recall": 0.3866432337434095,
26
+ "eval_runtime": 3.1616,
27
+ "eval_samples_per_second": 539.92,
28
+ "eval_steps_per_second": 17.08,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.7939634323120117,
34
+ "learning_rate": 0.00021997744191987566,
35
+ "loss": 0.531,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7352079671939075,
41
+ "eval_f1": 0.5368852459016393,
42
+ "eval_loss": 0.5183561444282532,
43
+ "eval_mcc": 0.3684302929196794,
44
+ "eval_precision": 0.6437346437346437,
45
+ "eval_recall": 0.46045694200351495,
46
+ "eval_runtime": 3.2232,
47
+ "eval_samples_per_second": 529.598,
48
+ "eval_steps_per_second": 16.754,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.888092279434204,
54
+ "learning_rate": 0.00018855209307417915,
55
+ "loss": 0.502,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7451669595782073,
61
+ "eval_f1": 0.48520710059171596,
62
+ "eval_loss": 0.5155817270278931,
63
+ "eval_mcc": 0.3814260429877007,
64
+ "eval_precision": 0.7427536231884058,
65
+ "eval_recall": 0.3602811950790861,
66
+ "eval_runtime": 3.1891,
67
+ "eval_samples_per_second": 535.256,
68
+ "eval_steps_per_second": 16.933,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 3.3760223388671875,
74
+ "learning_rate": 0.00015712674422848263,
75
+ "loss": 0.4897,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7422378441710603,
81
+ "eval_f1": 0.45812807881773393,
82
+ "eval_loss": 0.5075758695602417,
83
+ "eval_mcc": 0.37344089980427997,
84
+ "eval_precision": 0.7654320987654321,
85
+ "eval_recall": 0.3268892794376098,
86
+ "eval_runtime": 3.1359,
87
+ "eval_samples_per_second": 544.344,
88
+ "eval_steps_per_second": 17.22,
89
+ "step": 856
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 11.075637817382812,
94
+ "learning_rate": 0.0001257013953827861,
95
+ "loss": 0.4761,
96
+ "step": 1070
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7568834212067955,
101
+ "eval_f1": 0.5870646766169154,
102
+ "eval_loss": 0.49240508675575256,
103
+ "eval_mcc": 0.42649635439740835,
104
+ "eval_precision": 0.676605504587156,
105
+ "eval_recall": 0.5184534270650264,
106
+ "eval_runtime": 3.1156,
107
+ "eval_samples_per_second": 547.891,
108
+ "eval_steps_per_second": 17.332,
109
+ "step": 1070
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 6.270783424377441,
114
+ "learning_rate": 9.427604653708957e-05,
115
+ "loss": 0.4671,
116
+ "step": 1284
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7697715289982425,
121
+ "eval_f1": 0.6288951841359773,
122
+ "eval_loss": 0.48595207929611206,
123
+ "eval_mcc": 0.4660789140327505,
124
+ "eval_precision": 0.6795918367346939,
125
+ "eval_recall": 0.5852372583479789,
126
+ "eval_runtime": 3.1299,
127
+ "eval_samples_per_second": 545.38,
128
+ "eval_steps_per_second": 17.253,
129
+ "step": 1284
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 6.990926742553711,
134
+ "learning_rate": 6.285069769139304e-05,
135
+ "loss": 0.4567,
136
+ "step": 1498
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7633274751025191,
141
+ "eval_f1": 0.5692963752665245,
142
+ "eval_loss": 0.48252516984939575,
143
+ "eval_mcc": 0.43473790600905954,
144
+ "eval_precision": 0.7235772357723578,
145
+ "eval_recall": 0.46924428822495606,
146
+ "eval_runtime": 3.1545,
147
+ "eval_samples_per_second": 541.124,
148
+ "eval_steps_per_second": 17.118,
149
+ "step": 1498
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 1926,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 9,
156
+ "save_steps": 500,
157
+ "total_flos": 3673429651080.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.9932022812512611,
162
+ "learning_rate": 0.0002828281396112687,
163
+ "num_train_epochs": 9,
164
+ "temperature": 23
165
+ }
166
+ }
run-24/checkpoint-1498/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056a4a07ea3eb275e3c290638752eb45bcffa89ead6519b5845088d41a30cf92
3
+ size 5048
run-24/checkpoint-1498/vocab.txt ADDED
The diff for this file is too large to render. See raw diff