xuancoblab2023
commited on
Commit
•
ecfaad3
1
Parent(s):
bbb0918
Training in progress, epoch 5
Browse files- logs/events.out.tfevents.1721966078.98acc6742512.15262.32 +2 -2
- model.safetensors +1 -1
- run-31/checkpoint-860/config.json +34 -0
- run-31/checkpoint-860/model.safetensors +3 -0
- run-31/checkpoint-860/optimizer.pt +3 -0
- run-31/checkpoint-860/rng_state.pth +3 -0
- run-31/checkpoint-860/scheduler.pt +3 -0
- run-31/checkpoint-860/special_tokens_map.json +7 -0
- run-31/checkpoint-860/tokenizer.json +0 -0
- run-31/checkpoint-860/tokenizer_config.json +55 -0
- run-31/checkpoint-860/trainer_state.json +138 -0
- run-31/checkpoint-860/training_args.bin +3 -0
- run-31/checkpoint-860/vocab.txt +0 -0
logs/events.out.tfevents.1721966078.98acc6742512.15262.32
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3c59a9704885e2de2f8856ef96e0f16e93e83dd2d420e039e6579aac4f052bc
|
3 |
+
size 8607
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17549312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e5f81295e21c8a3e84293dedf31ff666a38f63d863d8fe0e1c052c746f7dffa
|
3 |
size 17549312
|
run-31/checkpoint-860/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": "4.43.2",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
run-31/checkpoint-860/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e5f81295e21c8a3e84293dedf31ff666a38f63d863d8fe0e1c052c746f7dffa
|
3 |
+
size 17549312
|
run-31/checkpoint-860/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35c8295d82d9d807ca2ea207ffc787f7ee4d7b861c5c44b983378766b54315bf
|
3 |
+
size 35123898
|
run-31/checkpoint-860/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac9f0bc35f961ba3eec992b81bac90971267fe149efd92cea3c10af23980c570
|
3 |
+
size 14308
|
run-31/checkpoint-860/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b5b475decdacf684895bcf05bf8aaaaab57cc14c9462d832a58c3609efacc27
|
3 |
+
size 1064
|
run-31/checkpoint-860/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-31/checkpoint-860/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-31/checkpoint-860/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": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-31/checkpoint-860/trainer_state.json
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8173333333333334,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-31/checkpoint-688",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 860,
|
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": 0.9708962440490723,
|
14 |
+
"learning_rate": 0.00018007353154788933,
|
15 |
+
"loss": 0.5186,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8338702222222223,
|
21 |
+
"eval_BAC": 0.758,
|
22 |
+
"eval_MCC": 0.5164413442563544,
|
23 |
+
"eval_PR_AUC": 0.7903470719520844,
|
24 |
+
"eval_accuracy": 0.758,
|
25 |
+
"eval_loss": 0.45808151364326477,
|
26 |
+
"eval_runtime": 6.2856,
|
27 |
+
"eval_samples_per_second": 238.642,
|
28 |
+
"eval_steps_per_second": 7.477,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 1.5569114685058594,
|
34 |
+
"learning_rate": 0.0001543487413267623,
|
35 |
+
"loss": 0.4771,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.8571271111111111,
|
41 |
+
"eval_BAC": 0.7793333333333333,
|
42 |
+
"eval_MCC": 0.591094330111451,
|
43 |
+
"eval_PR_AUC": 0.8037547287750328,
|
44 |
+
"eval_accuracy": 0.7793333333333333,
|
45 |
+
"eval_loss": 0.4492648243904114,
|
46 |
+
"eval_runtime": 6.2364,
|
47 |
+
"eval_samples_per_second": 240.525,
|
48 |
+
"eval_steps_per_second": 7.536,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 2.398871898651123,
|
54 |
+
"learning_rate": 0.00012862395110563524,
|
55 |
+
"loss": 0.4628,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.8642417777777778,
|
61 |
+
"eval_BAC": 0.7986666666666666,
|
62 |
+
"eval_MCC": 0.5973864367101849,
|
63 |
+
"eval_PR_AUC": 0.8284732954100074,
|
64 |
+
"eval_accuracy": 0.7986666666666666,
|
65 |
+
"eval_loss": 0.425106942653656,
|
66 |
+
"eval_runtime": 6.229,
|
67 |
+
"eval_samples_per_second": 240.809,
|
68 |
+
"eval_steps_per_second": 7.545,
|
69 |
+
"step": 516
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.0,
|
73 |
+
"grad_norm": 2.736416816711426,
|
74 |
+
"learning_rate": 0.0001028991608845082,
|
75 |
+
"loss": 0.453,
|
76 |
+
"step": 688
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_AUC": 0.8754026666666667,
|
81 |
+
"eval_BAC": 0.8173333333333332,
|
82 |
+
"eval_MCC": 0.6381270399870552,
|
83 |
+
"eval_PR_AUC": 0.8391884252076478,
|
84 |
+
"eval_accuracy": 0.8173333333333334,
|
85 |
+
"eval_loss": 0.4091016352176666,
|
86 |
+
"eval_runtime": 6.2348,
|
87 |
+
"eval_samples_per_second": 240.585,
|
88 |
+
"eval_steps_per_second": 7.538,
|
89 |
+
"step": 688
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 5.0,
|
93 |
+
"grad_norm": 2.7166924476623535,
|
94 |
+
"learning_rate": 7.717437066338115e-05,
|
95 |
+
"loss": 0.4436,
|
96 |
+
"step": 860
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 5.0,
|
100 |
+
"eval_AUC": 0.8772906666666666,
|
101 |
+
"eval_BAC": 0.8113333333333334,
|
102 |
+
"eval_MCC": 0.6330057971036138,
|
103 |
+
"eval_PR_AUC": 0.8365753409728844,
|
104 |
+
"eval_accuracy": 0.8113333333333334,
|
105 |
+
"eval_loss": 0.4114744961261749,
|
106 |
+
"eval_runtime": 6.2226,
|
107 |
+
"eval_samples_per_second": 241.056,
|
108 |
+
"eval_steps_per_second": 7.553,
|
109 |
+
"step": 860
|
110 |
+
}
|
111 |
+
],
|
112 |
+
"logging_steps": 500,
|
113 |
+
"max_steps": 1376,
|
114 |
+
"num_input_tokens_seen": 0,
|
115 |
+
"num_train_epochs": 8,
|
116 |
+
"save_steps": 500,
|
117 |
+
"stateful_callbacks": {
|
118 |
+
"TrainerControl": {
|
119 |
+
"args": {
|
120 |
+
"should_epoch_stop": false,
|
121 |
+
"should_evaluate": false,
|
122 |
+
"should_log": false,
|
123 |
+
"should_save": true,
|
124 |
+
"should_training_stop": false
|
125 |
+
},
|
126 |
+
"attributes": {}
|
127 |
+
}
|
128 |
+
},
|
129 |
+
"total_flos": 2251888650000.0,
|
130 |
+
"train_batch_size": 32,
|
131 |
+
"trial_name": null,
|
132 |
+
"trial_params": {
|
133 |
+
"alpha": 0.8022374115576867,
|
134 |
+
"learning_rate": 0.0002057983217690164,
|
135 |
+
"num_train_epochs": 8,
|
136 |
+
"temperature": 4
|
137 |
+
}
|
138 |
+
}
|
run-31/checkpoint-860/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78fd7203d5f23c69c697c8238f9f591b290847593ab65c957256295adf31d75f
|
3 |
+
size 5240
|
run-31/checkpoint-860/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|