xuancoblab2023
commited on
Commit
•
8f25fac
1
Parent(s):
4bb3232
Training in progress, epoch 7
Browse files- logs/events.out.tfevents.1721966710.98acc6742512.15262.35 +2 -2
- model.safetensors +1 -1
- run-34/checkpoint-1204/config.json +34 -0
- run-34/checkpoint-1204/model.safetensors +3 -0
- run-34/checkpoint-1204/optimizer.pt +3 -0
- run-34/checkpoint-1204/rng_state.pth +3 -0
- run-34/checkpoint-1204/scheduler.pt +3 -0
- run-34/checkpoint-1204/special_tokens_map.json +7 -0
- run-34/checkpoint-1204/tokenizer.json +0 -0
- run-34/checkpoint-1204/tokenizer_config.json +55 -0
- run-34/checkpoint-1204/trainer_state.json +178 -0
- run-34/checkpoint-1204/training_args.bin +3 -0
- run-34/checkpoint-1204/vocab.txt +0 -0
logs/events.out.tfevents.1721966710.98acc6742512.15262.35
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 sha256:3859bdf37e10fbda51664abd3d87491ea73752f3aac593606f86d36670ce6694
|
3 |
+
size 10057
|
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:e05b276bac02c701f99aa85e61f73e1bbda989de395f6197f3e2e91d311f1ff5
|
3 |
size 17549312
|
run-34/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-34/checkpoint-1204/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e05b276bac02c701f99aa85e61f73e1bbda989de395f6197f3e2e91d311f1ff5
|
3 |
+
size 17549312
|
run-34/checkpoint-1204/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c542ebae4fea8c5f829153c2269ed3a20d4c46cf2561f04a1c7855f09498fb1e
|
3 |
+
size 35123898
|
run-34/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-34/checkpoint-1204/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:753bb6af8cf5950c8406cf628e7e1c3554e8b8639369eac47e6d0cb7a4b69a51
|
3 |
+
size 1064
|
run-34/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-34/checkpoint-1204/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-34/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-34/checkpoint-1204/trainer_state.json
ADDED
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8213333333333334,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-34/checkpoint-860",
|
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": 1.2015043497085571,
|
14 |
+
"learning_rate": 0.00027537877162579386,
|
15 |
+
"loss": 0.5903,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8227715555555557,
|
21 |
+
"eval_BAC": 0.7293333333333334,
|
22 |
+
"eval_MCC": 0.462798882269463,
|
23 |
+
"eval_PR_AUC": 0.7817423653297785,
|
24 |
+
"eval_accuracy": 0.7293333333333333,
|
25 |
+
"eval_loss": 0.524067223072052,
|
26 |
+
"eval_runtime": 6.2657,
|
27 |
+
"eval_samples_per_second": 239.398,
|
28 |
+
"eval_steps_per_second": 7.501,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 2.673234224319458,
|
34 |
+
"learning_rate": 0.00024095642517256964,
|
35 |
+
"loss": 0.5391,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.8590240000000001,
|
41 |
+
"eval_BAC": 0.7893333333333333,
|
42 |
+
"eval_MCC": 0.6018126794174047,
|
43 |
+
"eval_PR_AUC": 0.8177888157143621,
|
44 |
+
"eval_accuracy": 0.7893333333333333,
|
45 |
+
"eval_loss": 0.48427751660346985,
|
46 |
+
"eval_runtime": 6.2417,
|
47 |
+
"eval_samples_per_second": 240.319,
|
48 |
+
"eval_steps_per_second": 7.53,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 2.158290147781372,
|
54 |
+
"learning_rate": 0.00020653407871934538,
|
55 |
+
"loss": 0.5144,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.874496,
|
61 |
+
"eval_BAC": 0.8166666666666667,
|
62 |
+
"eval_MCC": 0.6357253352621931,
|
63 |
+
"eval_PR_AUC": 0.8445948803832817,
|
64 |
+
"eval_accuracy": 0.8166666666666667,
|
65 |
+
"eval_loss": 0.45355746150016785,
|
66 |
+
"eval_runtime": 6.2253,
|
67 |
+
"eval_samples_per_second": 240.953,
|
68 |
+
"eval_steps_per_second": 7.55,
|
69 |
+
"step": 516
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.0,
|
73 |
+
"grad_norm": 3.349181890487671,
|
74 |
+
"learning_rate": 0.00017211173226612116,
|
75 |
+
"loss": 0.4983,
|
76 |
+
"step": 688
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_AUC": 0.8846435555555555,
|
81 |
+
"eval_BAC": 0.8160000000000001,
|
82 |
+
"eval_MCC": 0.6361963355504687,
|
83 |
+
"eval_PR_AUC": 0.8646294269782169,
|
84 |
+
"eval_accuracy": 0.816,
|
85 |
+
"eval_loss": 0.43939444422721863,
|
86 |
+
"eval_runtime": 6.2032,
|
87 |
+
"eval_samples_per_second": 241.81,
|
88 |
+
"eval_steps_per_second": 7.577,
|
89 |
+
"step": 688
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 5.0,
|
93 |
+
"grad_norm": 3.5103800296783447,
|
94 |
+
"learning_rate": 0.00013768938581289693,
|
95 |
+
"loss": 0.4834,
|
96 |
+
"step": 860
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 5.0,
|
100 |
+
"eval_AUC": 0.8878346666666667,
|
101 |
+
"eval_BAC": 0.8213333333333334,
|
102 |
+
"eval_MCC": 0.6458179094010764,
|
103 |
+
"eval_PR_AUC": 0.8644689328040056,
|
104 |
+
"eval_accuracy": 0.8213333333333334,
|
105 |
+
"eval_loss": 0.4339253008365631,
|
106 |
+
"eval_runtime": 6.2328,
|
107 |
+
"eval_samples_per_second": 240.664,
|
108 |
+
"eval_steps_per_second": 7.541,
|
109 |
+
"step": 860
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 6.0,
|
113 |
+
"grad_norm": 5.336594581604004,
|
114 |
+
"learning_rate": 0.00010326703935967269,
|
115 |
+
"loss": 0.4746,
|
116 |
+
"step": 1032
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 6.0,
|
120 |
+
"eval_AUC": 0.8907893333333334,
|
121 |
+
"eval_BAC": 0.8106666666666666,
|
122 |
+
"eval_MCC": 0.6252673865062606,
|
123 |
+
"eval_PR_AUC": 0.878022223565124,
|
124 |
+
"eval_accuracy": 0.8106666666666666,
|
125 |
+
"eval_loss": 0.4312085807323456,
|
126 |
+
"eval_runtime": 6.2382,
|
127 |
+
"eval_samples_per_second": 240.453,
|
128 |
+
"eval_steps_per_second": 7.534,
|
129 |
+
"step": 1032
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 7.0,
|
133 |
+
"grad_norm": 4.427212715148926,
|
134 |
+
"learning_rate": 6.884469290644847e-05,
|
135 |
+
"loss": 0.4628,
|
136 |
+
"step": 1204
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 7.0,
|
140 |
+
"eval_AUC": 0.8948551111111112,
|
141 |
+
"eval_BAC": 0.8200000000000001,
|
142 |
+
"eval_MCC": 0.64296966214199,
|
143 |
+
"eval_PR_AUC": 0.8703491534724792,
|
144 |
+
"eval_accuracy": 0.82,
|
145 |
+
"eval_loss": 0.4243921637535095,
|
146 |
+
"eval_runtime": 6.2243,
|
147 |
+
"eval_samples_per_second": 240.991,
|
148 |
+
"eval_steps_per_second": 7.551,
|
149 |
+
"step": 1204
|
150 |
+
}
|
151 |
+
],
|
152 |
+
"logging_steps": 500,
|
153 |
+
"max_steps": 1548,
|
154 |
+
"num_input_tokens_seen": 0,
|
155 |
+
"num_train_epochs": 9,
|
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": 0.9233020385816241,
|
174 |
+
"learning_rate": 0.0003098011180790181,
|
175 |
+
"num_train_epochs": 9,
|
176 |
+
"temperature": 6
|
177 |
+
}
|
178 |
+
}
|
run-34/checkpoint-1204/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d877c1dfe97f2e408bebc774c8e31f32af08cd31e93d90cb40f8126e5d0bc9a5
|
3 |
+
size 5240
|
run-34/checkpoint-1204/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|