xuancoblab2023
commited on
Commit
•
c4e5b51
1
Parent(s):
ed03abe
Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1721963780.98acc6742512.15262.12 +2 -2
- logs/events.out.tfevents.1721964033.98acc6742512.15262.13 +3 -0
- model.safetensors +1 -1
- run-11/checkpoint-1204/config.json +34 -0
- run-11/checkpoint-1204/model.safetensors +3 -0
- run-11/checkpoint-1204/optimizer.pt +3 -0
- run-11/checkpoint-1204/rng_state.pth +3 -0
- run-11/checkpoint-1204/scheduler.pt +3 -0
- run-11/checkpoint-1204/special_tokens_map.json +7 -0
- run-11/checkpoint-1204/tokenizer.json +0 -0
- run-11/checkpoint-1204/tokenizer_config.json +55 -0
- run-11/checkpoint-1204/trainer_state.json +178 -0
- run-11/checkpoint-1204/training_args.bin +3 -0
- run-11/checkpoint-1204/vocab.txt +0 -0
- run-11/checkpoint-1376/config.json +34 -0
- run-11/checkpoint-1376/model.safetensors +3 -0
- run-11/checkpoint-1376/optimizer.pt +3 -0
- run-11/checkpoint-1376/rng_state.pth +3 -0
- run-11/checkpoint-1376/scheduler.pt +3 -0
- run-11/checkpoint-1376/special_tokens_map.json +7 -0
- run-11/checkpoint-1376/tokenizer.json +0 -0
- run-11/checkpoint-1376/tokenizer_config.json +55 -0
- run-11/checkpoint-1376/trainer_state.json +198 -0
- run-11/checkpoint-1376/training_args.bin +3 -0
- run-11/checkpoint-1376/vocab.txt +0 -0
- run-12/checkpoint-172/config.json +34 -0
- run-12/checkpoint-172/model.safetensors +3 -0
- run-12/checkpoint-172/optimizer.pt +3 -0
- run-12/checkpoint-172/rng_state.pth +3 -0
- run-12/checkpoint-172/scheduler.pt +3 -0
- run-12/checkpoint-172/special_tokens_map.json +7 -0
- run-12/checkpoint-172/tokenizer.json +0 -0
- run-12/checkpoint-172/tokenizer_config.json +55 -0
- run-12/checkpoint-172/trainer_state.json +58 -0
- run-12/checkpoint-172/training_args.bin +3 -0
- run-12/checkpoint-172/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1721963780.98acc6742512.15262.12
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:ac968270ab0b3253904bf2cf5bc4b1d1f044326b26c490a2b9e1ea79a20d9a7d
|
3 |
+
size 11137
|
logs/events.out.tfevents.1721964033.98acc6742512.15262.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ecbe9df3a52c0c08856ff050181ca4544e71072e3a038564edc349883f645c9
|
3 |
+
size 5707
|
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 sha256:14fdfcfe9061a09edda20b60e554d6b0c5ba3388e70cd83e25b1dfc70581121d
|
3 |
size 17549312
|
run-11/checkpoint-1204/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-11/checkpoint-1204/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bbf1fa380484480004f69a37e8a6ae198ad5837967aab480c39ec0c1113efcd
|
3 |
+
size 17549312
|
run-11/checkpoint-1204/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35fd99c8c6868fcb79cf8ef08a908b9be520d8a3c67e92b1152f90c4cdf4ef66
|
3 |
+
size 35123898
|
run-11/checkpoint-1204/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4404160742a334aa27fbb21c3241578919c1efefcab10b400b543b1d691ccc6d
|
3 |
+
size 14308
|
run-11/checkpoint-1204/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b822515287f90b218d3a10f32a5156f4bc0a524ede8a86ca5445761d191a50b5
|
3 |
+
size 1064
|
run-11/checkpoint-1204/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-11/checkpoint-1204/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-11/checkpoint-1204/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-11/checkpoint-1204/trainer_state.json
ADDED
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.818,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-11/checkpoint-1204",
|
4 |
+
"epoch": 7.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1204,
|
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": 1.173068881034851,
|
14 |
+
"learning_rate": 0.00024337376165851695,
|
15 |
+
"loss": 0.6049,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8273706666666667,
|
21 |
+
"eval_BAC": 0.7413333333333333,
|
22 |
+
"eval_MCC": 0.4850333676414723,
|
23 |
+
"eval_PR_AUC": 0.7881657633117372,
|
24 |
+
"eval_accuracy": 0.7413333333333333,
|
25 |
+
"eval_loss": 0.5346564650535583,
|
26 |
+
"eval_runtime": 6.256,
|
27 |
+
"eval_samples_per_second": 239.768,
|
28 |
+
"eval_steps_per_second": 7.513,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 2.4093000888824463,
|
34 |
+
"learning_rate": 0.00020860608142158596,
|
35 |
+
"loss": 0.5475,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.8532853333333333,
|
41 |
+
"eval_BAC": 0.7966666666666666,
|
42 |
+
"eval_MCC": 0.6114050721892912,
|
43 |
+
"eval_PR_AUC": 0.7888869116793986,
|
44 |
+
"eval_accuracy": 0.7966666666666666,
|
45 |
+
"eval_loss": 0.48248833417892456,
|
46 |
+
"eval_runtime": 6.2583,
|
47 |
+
"eval_samples_per_second": 239.682,
|
48 |
+
"eval_steps_per_second": 7.51,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 3.5168275833129883,
|
54 |
+
"learning_rate": 0.00017383840118465497,
|
55 |
+
"loss": 0.521,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.8562666666666667,
|
61 |
+
"eval_BAC": 0.798,
|
62 |
+
"eval_MCC": 0.5978527601704366,
|
63 |
+
"eval_PR_AUC": 0.8147153641772997,
|
64 |
+
"eval_accuracy": 0.798,
|
65 |
+
"eval_loss": 0.4632047414779663,
|
66 |
+
"eval_runtime": 6.2642,
|
67 |
+
"eval_samples_per_second": 239.455,
|
68 |
+
"eval_steps_per_second": 7.503,
|
69 |
+
"step": 516
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.0,
|
73 |
+
"grad_norm": 3.0364439487457275,
|
74 |
+
"learning_rate": 0.00013907072094772397,
|
75 |
+
"loss": 0.5067,
|
76 |
+
"step": 688
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_AUC": 0.8710017777777778,
|
81 |
+
"eval_BAC": 0.8026666666666666,
|
82 |
+
"eval_MCC": 0.6086337734330317,
|
83 |
+
"eval_PR_AUC": 0.8431966996463283,
|
84 |
+
"eval_accuracy": 0.8026666666666666,
|
85 |
+
"eval_loss": 0.4548323452472687,
|
86 |
+
"eval_runtime": 6.2602,
|
87 |
+
"eval_samples_per_second": 239.609,
|
88 |
+
"eval_steps_per_second": 7.508,
|
89 |
+
"step": 688
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 5.0,
|
93 |
+
"grad_norm": 4.948005199432373,
|
94 |
+
"learning_rate": 0.00010430304071079298,
|
95 |
+
"loss": 0.496,
|
96 |
+
"step": 860
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 5.0,
|
100 |
+
"eval_AUC": 0.8774115555555555,
|
101 |
+
"eval_BAC": 0.8133333333333332,
|
102 |
+
"eval_MCC": 0.6399469848044845,
|
103 |
+
"eval_PR_AUC": 0.8344867532038169,
|
104 |
+
"eval_accuracy": 0.8133333333333334,
|
105 |
+
"eval_loss": 0.45315295457839966,
|
106 |
+
"eval_runtime": 6.257,
|
107 |
+
"eval_samples_per_second": 239.731,
|
108 |
+
"eval_steps_per_second": 7.512,
|
109 |
+
"step": 860
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 6.0,
|
113 |
+
"grad_norm": 7.4915666580200195,
|
114 |
+
"learning_rate": 6.953536047386199e-05,
|
115 |
+
"loss": 0.4845,
|
116 |
+
"step": 1032
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 6.0,
|
120 |
+
"eval_AUC": 0.8858737777777778,
|
121 |
+
"eval_BAC": 0.8113333333333332,
|
122 |
+
"eval_MCC": 0.6275096493938598,
|
123 |
+
"eval_PR_AUC": 0.8524215878184646,
|
124 |
+
"eval_accuracy": 0.8113333333333334,
|
125 |
+
"eval_loss": 0.44440844655036926,
|
126 |
+
"eval_runtime": 6.2656,
|
127 |
+
"eval_samples_per_second": 239.403,
|
128 |
+
"eval_steps_per_second": 7.501,
|
129 |
+
"step": 1032
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 7.0,
|
133 |
+
"grad_norm": 3.649087905883789,
|
134 |
+
"learning_rate": 3.476768023693099e-05,
|
135 |
+
"loss": 0.4771,
|
136 |
+
"step": 1204
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 7.0,
|
140 |
+
"eval_AUC": 0.8873937777777777,
|
141 |
+
"eval_BAC": 0.8180000000000001,
|
142 |
+
"eval_MCC": 0.6409466868541137,
|
143 |
+
"eval_PR_AUC": 0.8535373088628392,
|
144 |
+
"eval_accuracy": 0.818,
|
145 |
+
"eval_loss": 0.43640071153640747,
|
146 |
+
"eval_runtime": 6.2505,
|
147 |
+
"eval_samples_per_second": 239.982,
|
148 |
+
"eval_steps_per_second": 7.519,
|
149 |
+
"step": 1204
|
150 |
+
}
|
151 |
+
],
|
152 |
+
"logging_steps": 500,
|
153 |
+
"max_steps": 1376,
|
154 |
+
"num_input_tokens_seen": 0,
|
155 |
+
"num_train_epochs": 8,
|
156 |
+
"save_steps": 500,
|
157 |
+
"stateful_callbacks": {
|
158 |
+
"TrainerControl": {
|
159 |
+
"args": {
|
160 |
+
"should_epoch_stop": false,
|
161 |
+
"should_evaluate": false,
|
162 |
+
"should_log": false,
|
163 |
+
"should_save": true,
|
164 |
+
"should_training_stop": false
|
165 |
+
},
|
166 |
+
"attributes": {}
|
167 |
+
}
|
168 |
+
},
|
169 |
+
"total_flos": 3152644110000.0,
|
170 |
+
"train_batch_size": 32,
|
171 |
+
"trial_name": null,
|
172 |
+
"trial_params": {
|
173 |
+
"alpha": 0.9508242983728342,
|
174 |
+
"learning_rate": 0.00027814144189544795,
|
175 |
+
"num_train_epochs": 8,
|
176 |
+
"temperature": 2
|
177 |
+
}
|
178 |
+
}
|
run-11/checkpoint-1204/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00c34daadb74657e0250649c99c809ed0c04f4fb815b36eb44644c8403fdf072
|
3 |
+
size 5240
|
run-11/checkpoint-1204/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-11/checkpoint-1376/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-11/checkpoint-1376/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce58bc99dcbd91e647d3b6b43a35473226e013935977d6667387f3f13b02b35d
|
3 |
+
size 17549312
|
run-11/checkpoint-1376/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97c7860c5f9bc1c05615e5a8d43a3a058b3855b79a7b338438b17a158c4667f4
|
3 |
+
size 35123898
|
run-11/checkpoint-1376/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edaf180ca6adccc71bbccb352ad77ce0fa3542e9d87badbbada21fe981422321
|
3 |
+
size 14308
|
run-11/checkpoint-1376/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d47b980b0c8a7546fee8320406f9109930106684894695f32a7c9368b45850a
|
3 |
+
size 1064
|
run-11/checkpoint-1376/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-11/checkpoint-1376/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-11/checkpoint-1376/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-11/checkpoint-1376/trainer_state.json
ADDED
@@ -0,0 +1,198 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.824,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-11/checkpoint-1376",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1376,
|
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": 1.173068881034851,
|
14 |
+
"learning_rate": 0.00024337376165851695,
|
15 |
+
"loss": 0.6049,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8273706666666667,
|
21 |
+
"eval_BAC": 0.7413333333333333,
|
22 |
+
"eval_MCC": 0.4850333676414723,
|
23 |
+
"eval_PR_AUC": 0.7881657633117372,
|
24 |
+
"eval_accuracy": 0.7413333333333333,
|
25 |
+
"eval_loss": 0.5346564650535583,
|
26 |
+
"eval_runtime": 6.256,
|
27 |
+
"eval_samples_per_second": 239.768,
|
28 |
+
"eval_steps_per_second": 7.513,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 2.4093000888824463,
|
34 |
+
"learning_rate": 0.00020860608142158596,
|
35 |
+
"loss": 0.5475,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.8532853333333333,
|
41 |
+
"eval_BAC": 0.7966666666666666,
|
42 |
+
"eval_MCC": 0.6114050721892912,
|
43 |
+
"eval_PR_AUC": 0.7888869116793986,
|
44 |
+
"eval_accuracy": 0.7966666666666666,
|
45 |
+
"eval_loss": 0.48248833417892456,
|
46 |
+
"eval_runtime": 6.2583,
|
47 |
+
"eval_samples_per_second": 239.682,
|
48 |
+
"eval_steps_per_second": 7.51,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 3.5168275833129883,
|
54 |
+
"learning_rate": 0.00017383840118465497,
|
55 |
+
"loss": 0.521,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.8562666666666667,
|
61 |
+
"eval_BAC": 0.798,
|
62 |
+
"eval_MCC": 0.5978527601704366,
|
63 |
+
"eval_PR_AUC": 0.8147153641772997,
|
64 |
+
"eval_accuracy": 0.798,
|
65 |
+
"eval_loss": 0.4632047414779663,
|
66 |
+
"eval_runtime": 6.2642,
|
67 |
+
"eval_samples_per_second": 239.455,
|
68 |
+
"eval_steps_per_second": 7.503,
|
69 |
+
"step": 516
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.0,
|
73 |
+
"grad_norm": 3.0364439487457275,
|
74 |
+
"learning_rate": 0.00013907072094772397,
|
75 |
+
"loss": 0.5067,
|
76 |
+
"step": 688
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_AUC": 0.8710017777777778,
|
81 |
+
"eval_BAC": 0.8026666666666666,
|
82 |
+
"eval_MCC": 0.6086337734330317,
|
83 |
+
"eval_PR_AUC": 0.8431966996463283,
|
84 |
+
"eval_accuracy": 0.8026666666666666,
|
85 |
+
"eval_loss": 0.4548323452472687,
|
86 |
+
"eval_runtime": 6.2602,
|
87 |
+
"eval_samples_per_second": 239.609,
|
88 |
+
"eval_steps_per_second": 7.508,
|
89 |
+
"step": 688
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 5.0,
|
93 |
+
"grad_norm": 4.948005199432373,
|
94 |
+
"learning_rate": 0.00010430304071079298,
|
95 |
+
"loss": 0.496,
|
96 |
+
"step": 860
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 5.0,
|
100 |
+
"eval_AUC": 0.8774115555555555,
|
101 |
+
"eval_BAC": 0.8133333333333332,
|
102 |
+
"eval_MCC": 0.6399469848044845,
|
103 |
+
"eval_PR_AUC": 0.8344867532038169,
|
104 |
+
"eval_accuracy": 0.8133333333333334,
|
105 |
+
"eval_loss": 0.45315295457839966,
|
106 |
+
"eval_runtime": 6.257,
|
107 |
+
"eval_samples_per_second": 239.731,
|
108 |
+
"eval_steps_per_second": 7.512,
|
109 |
+
"step": 860
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 6.0,
|
113 |
+
"grad_norm": 7.4915666580200195,
|
114 |
+
"learning_rate": 6.953536047386199e-05,
|
115 |
+
"loss": 0.4845,
|
116 |
+
"step": 1032
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 6.0,
|
120 |
+
"eval_AUC": 0.8858737777777778,
|
121 |
+
"eval_BAC": 0.8113333333333332,
|
122 |
+
"eval_MCC": 0.6275096493938598,
|
123 |
+
"eval_PR_AUC": 0.8524215878184646,
|
124 |
+
"eval_accuracy": 0.8113333333333334,
|
125 |
+
"eval_loss": 0.44440844655036926,
|
126 |
+
"eval_runtime": 6.2656,
|
127 |
+
"eval_samples_per_second": 239.403,
|
128 |
+
"eval_steps_per_second": 7.501,
|
129 |
+
"step": 1032
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 7.0,
|
133 |
+
"grad_norm": 3.649087905883789,
|
134 |
+
"learning_rate": 3.476768023693099e-05,
|
135 |
+
"loss": 0.4771,
|
136 |
+
"step": 1204
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 7.0,
|
140 |
+
"eval_AUC": 0.8873937777777777,
|
141 |
+
"eval_BAC": 0.8180000000000001,
|
142 |
+
"eval_MCC": 0.6409466868541137,
|
143 |
+
"eval_PR_AUC": 0.8535373088628392,
|
144 |
+
"eval_accuracy": 0.818,
|
145 |
+
"eval_loss": 0.43640071153640747,
|
146 |
+
"eval_runtime": 6.2505,
|
147 |
+
"eval_samples_per_second": 239.982,
|
148 |
+
"eval_steps_per_second": 7.519,
|
149 |
+
"step": 1204
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 8.0,
|
153 |
+
"grad_norm": 2.1959824562072754,
|
154 |
+
"learning_rate": 0.0,
|
155 |
+
"loss": 0.4739,
|
156 |
+
"step": 1376
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 8.0,
|
160 |
+
"eval_AUC": 0.8897351111111111,
|
161 |
+
"eval_BAC": 0.8240000000000001,
|
162 |
+
"eval_MCC": 0.651352819389177,
|
163 |
+
"eval_PR_AUC": 0.8590307681592729,
|
164 |
+
"eval_accuracy": 0.824,
|
165 |
+
"eval_loss": 0.4306699335575104,
|
166 |
+
"eval_runtime": 6.2445,
|
167 |
+
"eval_samples_per_second": 240.211,
|
168 |
+
"eval_steps_per_second": 7.527,
|
169 |
+
"step": 1376
|
170 |
+
}
|
171 |
+
],
|
172 |
+
"logging_steps": 500,
|
173 |
+
"max_steps": 1376,
|
174 |
+
"num_input_tokens_seen": 0,
|
175 |
+
"num_train_epochs": 8,
|
176 |
+
"save_steps": 500,
|
177 |
+
"stateful_callbacks": {
|
178 |
+
"TrainerControl": {
|
179 |
+
"args": {
|
180 |
+
"should_epoch_stop": false,
|
181 |
+
"should_evaluate": false,
|
182 |
+
"should_log": false,
|
183 |
+
"should_save": true,
|
184 |
+
"should_training_stop": true
|
185 |
+
},
|
186 |
+
"attributes": {}
|
187 |
+
}
|
188 |
+
},
|
189 |
+
"total_flos": 3603021840000.0,
|
190 |
+
"train_batch_size": 32,
|
191 |
+
"trial_name": null,
|
192 |
+
"trial_params": {
|
193 |
+
"alpha": 0.9508242983728342,
|
194 |
+
"learning_rate": 0.00027814144189544795,
|
195 |
+
"num_train_epochs": 8,
|
196 |
+
"temperature": 2
|
197 |
+
}
|
198 |
+
}
|
run-11/checkpoint-1376/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00c34daadb74657e0250649c99c809ed0c04f4fb815b36eb44644c8403fdf072
|
3 |
+
size 5240
|
run-11/checkpoint-1376/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-12/checkpoint-172/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-12/checkpoint-172/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14fdfcfe9061a09edda20b60e554d6b0c5ba3388e70cd83e25b1dfc70581121d
|
3 |
+
size 17549312
|
run-12/checkpoint-172/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cd94b5122b763e8c6be7234547e47a50b0b840ce7389b11403e1ff133d4d8d2
|
3 |
+
size 35123898
|
run-12/checkpoint-172/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b99cb6263c36c5c191e9bbbef2d3167790018df547076ed69608752e2b4353d4
|
3 |
+
size 14308
|
run-12/checkpoint-172/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:142f817588faa52be4f42af2594882b843b702be715b40fc13fcb9869af39976
|
3 |
+
size 1064
|
run-12/checkpoint-172/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-12/checkpoint-172/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-12/checkpoint-172/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-12/checkpoint-172/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7453333333333333,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-12/checkpoint-172",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 172,
|
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": 1.1232905387878418,
|
14 |
+
"learning_rate": 0.00024417899038111995,
|
15 |
+
"loss": 0.6117,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8254151111111111,
|
21 |
+
"eval_BAC": 0.7453333333333334,
|
22 |
+
"eval_MCC": 0.4912976797633764,
|
23 |
+
"eval_PR_AUC": 0.786302392146851,
|
24 |
+
"eval_accuracy": 0.7453333333333333,
|
25 |
+
"eval_loss": 0.5350800156593323,
|
26 |
+
"eval_runtime": 6.3041,
|
27 |
+
"eval_samples_per_second": 237.94,
|
28 |
+
"eval_steps_per_second": 7.455,
|
29 |
+
"step": 172
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 1376,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 8,
|
36 |
+
"save_steps": 500,
|
37 |
+
"stateful_callbacks": {
|
38 |
+
"TrainerControl": {
|
39 |
+
"args": {
|
40 |
+
"should_epoch_stop": false,
|
41 |
+
"should_evaluate": false,
|
42 |
+
"should_log": false,
|
43 |
+
"should_save": true,
|
44 |
+
"should_training_stop": false
|
45 |
+
},
|
46 |
+
"attributes": {}
|
47 |
+
}
|
48 |
+
},
|
49 |
+
"total_flos": 450377730000.0,
|
50 |
+
"train_batch_size": 32,
|
51 |
+
"trial_name": null,
|
52 |
+
"trial_params": {
|
53 |
+
"alpha": 0.9633802106648812,
|
54 |
+
"learning_rate": 0.0002790617032927085,
|
55 |
+
"num_train_epochs": 8,
|
56 |
+
"temperature": 2
|
57 |
+
}
|
58 |
+
}
|
run-12/checkpoint-172/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d50e4f7ab6447df633273fe08e7e11f04b1d23b2e8a33c7570cd79f5951df51
|
3 |
+
size 5240
|
run-12/checkpoint-172/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d50e4f7ab6447df633273fe08e7e11f04b1d23b2e8a33c7570cd79f5951df51
|
3 |
size 5240
|