xuancoblab2023
commited on
Commit
•
2c64b92
1
Parent(s):
a003ac8
Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1721962439.98acc6742512.15262.2 +2 -2
- logs/events.out.tfevents.1721962568.98acc6742512.15262.3 +3 -0
- model.safetensors +1 -1
- run-1/checkpoint-516/config.json +34 -0
- run-1/checkpoint-516/model.safetensors +3 -0
- run-1/checkpoint-516/optimizer.pt +3 -0
- run-1/checkpoint-516/rng_state.pth +3 -0
- run-1/checkpoint-516/scheduler.pt +3 -0
- run-1/checkpoint-516/special_tokens_map.json +7 -0
- run-1/checkpoint-516/tokenizer.json +0 -0
- run-1/checkpoint-516/tokenizer_config.json +55 -0
- run-1/checkpoint-516/trainer_state.json +98 -0
- run-1/checkpoint-516/training_args.bin +3 -0
- run-1/checkpoint-516/vocab.txt +0 -0
- run-1/checkpoint-688/config.json +34 -0
- run-1/checkpoint-688/model.safetensors +3 -0
- run-1/checkpoint-688/optimizer.pt +3 -0
- run-1/checkpoint-688/rng_state.pth +3 -0
- run-1/checkpoint-688/scheduler.pt +3 -0
- run-1/checkpoint-688/special_tokens_map.json +7 -0
- run-1/checkpoint-688/tokenizer.json +0 -0
- run-1/checkpoint-688/tokenizer_config.json +55 -0
- run-1/checkpoint-688/trainer_state.json +118 -0
- run-1/checkpoint-688/training_args.bin +3 -0
- run-1/checkpoint-688/vocab.txt +0 -0
- run-2/checkpoint-172/config.json +34 -0
- run-2/checkpoint-172/model.safetensors +3 -0
- run-2/checkpoint-172/optimizer.pt +3 -0
- run-2/checkpoint-172/rng_state.pth +3 -0
- run-2/checkpoint-172/scheduler.pt +3 -0
- run-2/checkpoint-172/special_tokens_map.json +7 -0
- run-2/checkpoint-172/tokenizer.json +0 -0
- run-2/checkpoint-172/tokenizer_config.json +55 -0
- run-2/checkpoint-172/trainer_state.json +58 -0
- run-2/checkpoint-172/training_args.bin +3 -0
- run-2/checkpoint-172/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1721962439.98acc6742512.15262.2
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 sha256:3024554ce80166e5a3aa67ccdb6c3d2bb4747fef8a0a86374faa2951b04a62a8
|
3 |
+
size 8236
|
logs/events.out.tfevents.1721962568.98acc6742512.15262.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e6cb732fec6b5056570aa54443129f3e03d3257ba9750ef74f7a4c6cbe44234
|
3 |
+
size 5708
|
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 sha256:1af612a7f664f810b37e8f8d7fe7ce92d45527d343d7b701c8085caded0fa603
|
3 |
size 17549312
|
run-1/checkpoint-516/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-1/checkpoint-516/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdd8af782175ee631b889f95e37381418065aa689d291323e07349506aa1b268
|
3 |
+
size 17549312
|
run-1/checkpoint-516/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:749ebfea1d5609c34b035032762726a3c2b2bd9ea5958b92ab3098b58af24339
|
3 |
+
size 35123898
|
run-1/checkpoint-516/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e559bd010dfad806644ec9950fc1246348c344f69faad3d9fcd91973ca8dae1e
|
3 |
+
size 14308
|
run-1/checkpoint-516/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55c2128f9137c1f9de6173f0232dceb1bd4fb80938a5f625e5ff881d01b31fbc
|
3 |
+
size 1064
|
run-1/checkpoint-516/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-1/checkpoint-516/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-516/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-1/checkpoint-516/trainer_state.json
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7086666666666667,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-1/checkpoint-516",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 516,
|
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": 0.10513057559728622,
|
14 |
+
"learning_rate": 0.0004697676642472769,
|
15 |
+
"loss": 0.0495,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8095893333333333,
|
21 |
+
"eval_BAC": 0.5,
|
22 |
+
"eval_MCC": 0.0,
|
23 |
+
"eval_PR_AUC": 0.7634102804324954,
|
24 |
+
"eval_accuracy": 0.5,
|
25 |
+
"eval_loss": 0.04859978333115578,
|
26 |
+
"eval_runtime": 6.131,
|
27 |
+
"eval_samples_per_second": 244.658,
|
28 |
+
"eval_steps_per_second": 7.666,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 0.061181988567113876,
|
34 |
+
"learning_rate": 0.00031317844283151793,
|
35 |
+
"loss": 0.0486,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.8169422222222222,
|
41 |
+
"eval_BAC": 0.6066666666666667,
|
42 |
+
"eval_MCC": 0.34181792192366234,
|
43 |
+
"eval_PR_AUC": 0.7733898212292494,
|
44 |
+
"eval_accuracy": 0.6066666666666667,
|
45 |
+
"eval_loss": 0.04842817783355713,
|
46 |
+
"eval_runtime": 6.2071,
|
47 |
+
"eval_samples_per_second": 241.657,
|
48 |
+
"eval_steps_per_second": 7.572,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 0.035214055329561234,
|
54 |
+
"learning_rate": 0.00015658922141575897,
|
55 |
+
"loss": 0.0484,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.7751502222222222,
|
61 |
+
"eval_BAC": 0.7086666666666667,
|
62 |
+
"eval_MCC": 0.47074801855813936,
|
63 |
+
"eval_PR_AUC": 0.718076635825553,
|
64 |
+
"eval_accuracy": 0.7086666666666667,
|
65 |
+
"eval_loss": 0.048104096204042435,
|
66 |
+
"eval_runtime": 6.2731,
|
67 |
+
"eval_samples_per_second": 239.115,
|
68 |
+
"eval_steps_per_second": 7.492,
|
69 |
+
"step": 516
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 500,
|
73 |
+
"max_steps": 688,
|
74 |
+
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 4,
|
76 |
+
"save_steps": 500,
|
77 |
+
"stateful_callbacks": {
|
78 |
+
"TrainerControl": {
|
79 |
+
"args": {
|
80 |
+
"should_epoch_stop": false,
|
81 |
+
"should_evaluate": false,
|
82 |
+
"should_log": false,
|
83 |
+
"should_save": true,
|
84 |
+
"should_training_stop": false
|
85 |
+
},
|
86 |
+
"attributes": {}
|
87 |
+
}
|
88 |
+
},
|
89 |
+
"total_flos": 1351133190000.0,
|
90 |
+
"train_batch_size": 32,
|
91 |
+
"trial_name": null,
|
92 |
+
"trial_params": {
|
93 |
+
"alpha": 0.06190377563487581,
|
94 |
+
"learning_rate": 0.0006263568856630359,
|
95 |
+
"num_train_epochs": 4,
|
96 |
+
"temperature": 15
|
97 |
+
}
|
98 |
+
}
|
run-1/checkpoint-516/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fa2a37044ef6ce8c62252f894198b0ff65c98d3ddcbefc318c73358bb5c9023
|
3 |
+
size 5240
|
run-1/checkpoint-516/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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-1/checkpoint-688/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05f2e53cca223b521271e54b265d0f50be12bbcc30b495fd472d3680aab7d798
|
3 |
+
size 17549312
|
run-1/checkpoint-688/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8695e21af44c9b0d4d3b0dfa84bcdc92de443023bba347ec8f0901643dd66956
|
3 |
+
size 35123898
|
run-1/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-1/checkpoint-688/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bed76c770e34ec7ed846c66d1d97ef39c9e6544624cff7fe4ff4557af799276
|
3 |
+
size 1064
|
run-1/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-1/checkpoint-688/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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-1/checkpoint-688/trainer_state.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7086666666666667,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-1/checkpoint-516",
|
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": 0.10513057559728622,
|
14 |
+
"learning_rate": 0.0004697676642472769,
|
15 |
+
"loss": 0.0495,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8095893333333333,
|
21 |
+
"eval_BAC": 0.5,
|
22 |
+
"eval_MCC": 0.0,
|
23 |
+
"eval_PR_AUC": 0.7634102804324954,
|
24 |
+
"eval_accuracy": 0.5,
|
25 |
+
"eval_loss": 0.04859978333115578,
|
26 |
+
"eval_runtime": 6.131,
|
27 |
+
"eval_samples_per_second": 244.658,
|
28 |
+
"eval_steps_per_second": 7.666,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 0.061181988567113876,
|
34 |
+
"learning_rate": 0.00031317844283151793,
|
35 |
+
"loss": 0.0486,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.8169422222222222,
|
41 |
+
"eval_BAC": 0.6066666666666667,
|
42 |
+
"eval_MCC": 0.34181792192366234,
|
43 |
+
"eval_PR_AUC": 0.7733898212292494,
|
44 |
+
"eval_accuracy": 0.6066666666666667,
|
45 |
+
"eval_loss": 0.04842817783355713,
|
46 |
+
"eval_runtime": 6.2071,
|
47 |
+
"eval_samples_per_second": 241.657,
|
48 |
+
"eval_steps_per_second": 7.572,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 0.035214055329561234,
|
54 |
+
"learning_rate": 0.00015658922141575897,
|
55 |
+
"loss": 0.0484,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.7751502222222222,
|
61 |
+
"eval_BAC": 0.7086666666666667,
|
62 |
+
"eval_MCC": 0.47074801855813936,
|
63 |
+
"eval_PR_AUC": 0.718076635825553,
|
64 |
+
"eval_accuracy": 0.7086666666666667,
|
65 |
+
"eval_loss": 0.048104096204042435,
|
66 |
+
"eval_runtime": 6.2731,
|
67 |
+
"eval_samples_per_second": 239.115,
|
68 |
+
"eval_steps_per_second": 7.492,
|
69 |
+
"step": 516
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.0,
|
73 |
+
"grad_norm": 0.08540869504213333,
|
74 |
+
"learning_rate": 0.0,
|
75 |
+
"loss": 0.0483,
|
76 |
+
"step": 688
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_AUC": 0.7888142222222222,
|
81 |
+
"eval_BAC": 0.6553333333333333,
|
82 |
+
"eval_MCC": 0.41482262338943016,
|
83 |
+
"eval_PR_AUC": 0.7243356288592278,
|
84 |
+
"eval_accuracy": 0.6553333333333333,
|
85 |
+
"eval_loss": 0.04813617467880249,
|
86 |
+
"eval_runtime": 6.2684,
|
87 |
+
"eval_samples_per_second": 239.295,
|
88 |
+
"eval_steps_per_second": 7.498,
|
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": 0.06190377563487581,
|
114 |
+
"learning_rate": 0.0006263568856630359,
|
115 |
+
"num_train_epochs": 4,
|
116 |
+
"temperature": 15
|
117 |
+
}
|
118 |
+
}
|
run-1/checkpoint-688/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fa2a37044ef6ce8c62252f894198b0ff65c98d3ddcbefc318c73358bb5c9023
|
3 |
+
size 5240
|
run-1/checkpoint-688/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-172/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1af612a7f664f810b37e8f8d7fe7ce92d45527d343d7b701c8085caded0fa603
|
3 |
+
size 17549312
|
run-2/checkpoint-172/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef2a75fb52625dacf9421df2e7486e69640896586a8f6c38c2387af02cb4f13
|
3 |
+
size 35123898
|
run-2/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-2/checkpoint-172/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b928f62439a633e541dcdfc2797ab5c91ac1d9bfd5ed6bc37aeb26ec367112d
|
3 |
+
size 1064
|
run-2/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-2/checkpoint-172/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-172/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6966666666666667,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-2/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": 0.39246517419815063,
|
14 |
+
"learning_rate": 4.639522353304605e-05,
|
15 |
+
"loss": 0.2489,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.786481777777778,
|
21 |
+
"eval_BAC": 0.6966666666666667,
|
22 |
+
"eval_MCC": 0.4004741770824115,
|
23 |
+
"eval_PR_AUC": 0.7486102682312443,
|
24 |
+
"eval_accuracy": 0.6966666666666667,
|
25 |
+
"eval_loss": 0.23812349140644073,
|
26 |
+
"eval_runtime": 6.2157,
|
27 |
+
"eval_samples_per_second": 241.324,
|
28 |
+
"eval_steps_per_second": 7.561,
|
29 |
+
"step": 172
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 1720,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 10,
|
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": 0.3558486326039224,
|
54 |
+
"learning_rate": 5.155024837005116e-05,
|
55 |
+
"num_train_epochs": 10,
|
56 |
+
"temperature": 4
|
57 |
+
}
|
58 |
+
}
|
run-2/checkpoint-172/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9bd69b3929a44bec8f4cb67348238146f431e97b360ab6f0d8fff3cfab94f36
|
3 |
+
size 5240
|
run-2/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:e9bd69b3929a44bec8f4cb67348238146f431e97b360ab6f0d8fff3cfab94f36
|
3 |
size 5240
|