xuancoblab2023
commited on
Commit
•
cacf4d2
1
Parent(s):
a3f6af6
Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1721962879.98acc6742512.15262.4 +2 -2
- logs/events.out.tfevents.1721963007.98acc6742512.15262.5 +3 -0
- model.safetensors +1 -1
- run-3/checkpoint-688/config.json +34 -0
- run-3/checkpoint-688/model.safetensors +3 -0
- run-3/checkpoint-688/optimizer.pt +3 -0
- run-3/checkpoint-688/rng_state.pth +3 -0
- run-3/checkpoint-688/scheduler.pt +3 -0
- run-3/checkpoint-688/special_tokens_map.json +7 -0
- run-3/checkpoint-688/tokenizer.json +0 -0
- run-3/checkpoint-688/tokenizer_config.json +55 -0
- run-3/checkpoint-688/trainer_state.json +118 -0
- run-3/checkpoint-688/training_args.bin +3 -0
- run-3/checkpoint-688/vocab.txt +0 -0
- run-4/checkpoint-172/config.json +34 -0
- run-4/checkpoint-172/model.safetensors +3 -0
- run-4/checkpoint-172/optimizer.pt +3 -0
- run-4/checkpoint-172/rng_state.pth +3 -0
- run-4/checkpoint-172/scheduler.pt +3 -0
- run-4/checkpoint-172/special_tokens_map.json +7 -0
- run-4/checkpoint-172/tokenizer.json +0 -0
- run-4/checkpoint-172/tokenizer_config.json +55 -0
- run-4/checkpoint-172/trainer_state.json +58 -0
- run-4/checkpoint-172/training_args.bin +3 -0
- run-4/checkpoint-172/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1721962879.98acc6742512.15262.4
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 sha256:6a085f721b375c339921c5b0d70bfa539cdecea0ca92c32fcc6f1c21bbb8db9f
|
3 |
+
size 8236
|
logs/events.out.tfevents.1721963007.98acc6742512.15262.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b08262395687f09567ba99b8406ed22bf974ce956ec3283c7806ce465b9f205
|
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 sha256:253af992d0b5e4f5ef28901c40cd9afaaf0a488f67946ac1595fc5d0ba076271
|
3 |
size 17549312
|
run-3/checkpoint-688/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-3/checkpoint-688/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f492c804703cbc6f13c7eb3ec22a19233d6dcedafb7ca298c89204f346989d3
|
3 |
+
size 17549312
|
run-3/checkpoint-688/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b011eeb317602e65630fd2e63e2e3dc37505d04ed368266ce5c78e5cadcf0ab
|
3 |
+
size 35123898
|
run-3/checkpoint-688/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1b1fea9cda5ce8cfa36db49d92878d70e7ecc73c289b2b17c8c4949a715ba6e
|
3 |
+
size 14308
|
run-3/checkpoint-688/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e329956b7390b0a0d9d894c8fbe302d97ea89159873c9ac8bfce269c5511f547
|
3 |
+
size 1064
|
run-3/checkpoint-688/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-3/checkpoint-688/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-688/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-3/checkpoint-688/trainer_state.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5853333333333334,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-3/checkpoint-688",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 688,
|
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": 0.06025523692369461,
|
14 |
+
"learning_rate": 1.750045443660438e-05,
|
15 |
+
"loss": 0.0574,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.6860142222222222,
|
21 |
+
"eval_BAC": 0.5333333333333333,
|
22 |
+
"eval_MCC": 0.14834770727423166,
|
23 |
+
"eval_PR_AUC": 0.6557725052787473,
|
24 |
+
"eval_accuracy": 0.5333333333333333,
|
25 |
+
"eval_loss": 0.05601842328906059,
|
26 |
+
"eval_runtime": 6.3117,
|
27 |
+
"eval_samples_per_second": 237.654,
|
28 |
+
"eval_steps_per_second": 7.446,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 0.07936638593673706,
|
34 |
+
"learning_rate": 1.166696962440292e-05,
|
35 |
+
"loss": 0.0568,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.7200666666666666,
|
41 |
+
"eval_BAC": 0.5813333333333334,
|
42 |
+
"eval_MCC": 0.2649445737463828,
|
43 |
+
"eval_PR_AUC": 0.6792464061936596,
|
44 |
+
"eval_accuracy": 0.5813333333333334,
|
45 |
+
"eval_loss": 0.055815439671278,
|
46 |
+
"eval_runtime": 6.3074,
|
47 |
+
"eval_samples_per_second": 237.814,
|
48 |
+
"eval_steps_per_second": 7.452,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 0.04040193930268288,
|
54 |
+
"learning_rate": 5.83348481220146e-06,
|
55 |
+
"loss": 0.0566,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.7501155555555555,
|
61 |
+
"eval_BAC": 0.5459999999999999,
|
62 |
+
"eval_MCC": 0.20593895569506218,
|
63 |
+
"eval_PR_AUC": 0.7066874964455367,
|
64 |
+
"eval_accuracy": 0.546,
|
65 |
+
"eval_loss": 0.05583466589450836,
|
66 |
+
"eval_runtime": 6.177,
|
67 |
+
"eval_samples_per_second": 242.837,
|
68 |
+
"eval_steps_per_second": 7.609,
|
69 |
+
"step": 516
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.0,
|
73 |
+
"grad_norm": 0.08884396404027939,
|
74 |
+
"learning_rate": 0.0,
|
75 |
+
"loss": 0.0565,
|
76 |
+
"step": 688
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_AUC": 0.755400888888889,
|
81 |
+
"eval_BAC": 0.5853333333333333,
|
82 |
+
"eval_MCC": 0.28444444444444444,
|
83 |
+
"eval_PR_AUC": 0.7101770336776432,
|
84 |
+
"eval_accuracy": 0.5853333333333334,
|
85 |
+
"eval_loss": 0.05574020370841026,
|
86 |
+
"eval_runtime": 6.2726,
|
87 |
+
"eval_samples_per_second": 239.137,
|
88 |
+
"eval_steps_per_second": 7.493,
|
89 |
+
"step": 688
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"logging_steps": 500,
|
93 |
+
"max_steps": 688,
|
94 |
+
"num_input_tokens_seen": 0,
|
95 |
+
"num_train_epochs": 4,
|
96 |
+
"save_steps": 500,
|
97 |
+
"stateful_callbacks": {
|
98 |
+
"TrainerControl": {
|
99 |
+
"args": {
|
100 |
+
"should_epoch_stop": false,
|
101 |
+
"should_evaluate": false,
|
102 |
+
"should_log": false,
|
103 |
+
"should_save": true,
|
104 |
+
"should_training_stop": true
|
105 |
+
},
|
106 |
+
"attributes": {}
|
107 |
+
}
|
108 |
+
},
|
109 |
+
"total_flos": 1801510920000.0,
|
110 |
+
"train_batch_size": 32,
|
111 |
+
"trial_name": null,
|
112 |
+
"trial_params": {
|
113 |
+
"alpha": 0.07282268127135982,
|
114 |
+
"learning_rate": 2.333393924880584e-05,
|
115 |
+
"num_train_epochs": 4,
|
116 |
+
"temperature": 19
|
117 |
+
}
|
118 |
+
}
|
run-3/checkpoint-688/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ac229c98c6bdd9f587e559a419af2e54959e4f4e987fa74451dc16869d3838c
|
3 |
+
size 5240
|
run-3/checkpoint-688/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/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-4/checkpoint-172/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:253af992d0b5e4f5ef28901c40cd9afaaf0a488f67946ac1595fc5d0ba076271
|
3 |
+
size 17549312
|
run-4/checkpoint-172/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d72bb42e0e2436d65012b29ce9e906d173fce23653abf3e6e269c8f1be33dc90
|
3 |
+
size 35123898
|
run-4/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-4/checkpoint-172/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1939777f5def065f8fe7328a1e5c3d8834c7c4fd24c93823964b83fcb082e29
|
3 |
+
size 1064
|
run-4/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-4/checkpoint-172/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/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-4/checkpoint-172/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.73,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-4/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": 1.065812110900879,
|
14 |
+
"learning_rate": 8.050072712118835e-05,
|
15 |
+
"loss": 0.5092,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8145119999999999,
|
21 |
+
"eval_BAC": 0.73,
|
22 |
+
"eval_MCC": 0.4608302423279951,
|
23 |
+
"eval_PR_AUC": 0.7678112276484446,
|
24 |
+
"eval_accuracy": 0.73,
|
25 |
+
"eval_loss": 0.4519721269607544,
|
26 |
+
"eval_runtime": 6.3105,
|
27 |
+
"eval_samples_per_second": 237.697,
|
28 |
+
"eval_steps_per_second": 7.448,
|
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": 0.7709874476999774,
|
54 |
+
"learning_rate": 9.200083099564382e-05,
|
55 |
+
"num_train_epochs": 8,
|
56 |
+
"temperature": 3
|
57 |
+
}
|
58 |
+
}
|
run-4/checkpoint-172/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e822dd3e5d511c55cbe15ff5f987d7e223bc685f4a2426244b24b30556862387
|
3 |
+
size 5240
|
run-4/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:e822dd3e5d511c55cbe15ff5f987d7e223bc685f4a2426244b24b30556862387
|
3 |
size 5240
|