xuancoblab2023
commited on
Commit
•
b6709ee
1
Parent(s):
62eb8e0
Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1721965439.98acc6742512.15262.25 +2 -2
- logs/events.out.tfevents.1721965588.98acc6742512.15262.26 +3 -0
- model.safetensors +1 -1
- run-24/checkpoint-516/config.json +34 -0
- run-24/checkpoint-516/model.safetensors +3 -0
- run-24/checkpoint-516/optimizer.pt +3 -0
- run-24/checkpoint-516/rng_state.pth +3 -0
- run-24/checkpoint-516/scheduler.pt +3 -0
- run-24/checkpoint-516/special_tokens_map.json +7 -0
- run-24/checkpoint-516/tokenizer.json +0 -0
- run-24/checkpoint-516/tokenizer_config.json +55 -0
- run-24/checkpoint-516/trainer_state.json +98 -0
- run-24/checkpoint-516/training_args.bin +3 -0
- run-24/checkpoint-516/vocab.txt +0 -0
- run-24/checkpoint-688/config.json +34 -0
- run-24/checkpoint-688/model.safetensors +3 -0
- run-24/checkpoint-688/optimizer.pt +3 -0
- run-24/checkpoint-688/rng_state.pth +3 -0
- run-24/checkpoint-688/scheduler.pt +3 -0
- run-24/checkpoint-688/special_tokens_map.json +7 -0
- run-24/checkpoint-688/tokenizer.json +0 -0
- run-24/checkpoint-688/tokenizer_config.json +55 -0
- run-24/checkpoint-688/trainer_state.json +118 -0
- run-24/checkpoint-688/training_args.bin +3 -0
- run-24/checkpoint-688/vocab.txt +0 -0
- run-25/checkpoint-172/config.json +34 -0
- run-25/checkpoint-172/model.safetensors +3 -0
- run-25/checkpoint-172/optimizer.pt +3 -0
- run-25/checkpoint-172/rng_state.pth +3 -0
- run-25/checkpoint-172/scheduler.pt +3 -0
- run-25/checkpoint-172/special_tokens_map.json +7 -0
- run-25/checkpoint-172/tokenizer.json +0 -0
- run-25/checkpoint-172/tokenizer_config.json +55 -0
- run-25/checkpoint-172/trainer_state.json +58 -0
- run-25/checkpoint-172/training_args.bin +3 -0
- run-25/checkpoint-172/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1721965439.98acc6742512.15262.25
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 sha256:4c9937e1d573c304efe45d9d1736f4436a7b5f9797e4fd4b890fd06c2d6ee51d
|
3 |
+
size 8609
|
logs/events.out.tfevents.1721965588.98acc6742512.15262.26
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37ad6698a68647e75f4a0ae679fabd88a9fa06ce936470c667d33cf07bc196d9
|
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 sha256:8213352dae50cc3d57ccecacdd43708a479e7c2a90ef60b2d454c41f70088f34
|
3 |
size 17549312
|
run-24/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-24/checkpoint-516/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:487b3e2faa13fa88b9035fdb66b34aae3900483994b43e87c1e3c63f8a5eeaba
|
3 |
+
size 17549312
|
run-24/checkpoint-516/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ab166851499e567368aff902ead1bcc14a527bd4e9b4b4c4ec2ea8469eb5a50
|
3 |
+
size 35123898
|
run-24/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-24/checkpoint-516/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75538528aad8bbe80fa7cbd01a9fd872acdcce4c9c529222c28ac5b2e9afc68f
|
3 |
+
size 1064
|
run-24/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-24/checkpoint-516/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-24/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-24/checkpoint-516/trainer_state.json
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.804,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-24/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": 0.6114831566810608,
|
14 |
+
"learning_rate": 0.00012438553278352026,
|
15 |
+
"loss": 0.4032,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.812864,
|
21 |
+
"eval_BAC": 0.736,
|
22 |
+
"eval_MCC": 0.47260700716368276,
|
23 |
+
"eval_PR_AUC": 0.7744742146180674,
|
24 |
+
"eval_accuracy": 0.736,
|
25 |
+
"eval_loss": 0.3765888214111328,
|
26 |
+
"eval_runtime": 6.2583,
|
27 |
+
"eval_samples_per_second": 239.681,
|
28 |
+
"eval_steps_per_second": 7.51,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 0.8825994729995728,
|
34 |
+
"learning_rate": 0.00011056491802979578,
|
35 |
+
"loss": 0.3836,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.834104888888889,
|
41 |
+
"eval_BAC": 0.7606666666666666,
|
42 |
+
"eval_MCC": 0.5584922194756476,
|
43 |
+
"eval_PR_AUC": 0.7802314251570694,
|
44 |
+
"eval_accuracy": 0.7606666666666667,
|
45 |
+
"eval_loss": 0.36870983242988586,
|
46 |
+
"eval_runtime": 6.277,
|
47 |
+
"eval_samples_per_second": 238.968,
|
48 |
+
"eval_steps_per_second": 7.488,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 1.0203838348388672,
|
54 |
+
"learning_rate": 9.67443032760713e-05,
|
55 |
+
"loss": 0.3769,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.8587253333333335,
|
61 |
+
"eval_BAC": 0.804,
|
62 |
+
"eval_MCC": 0.6132578536355836,
|
63 |
+
"eval_PR_AUC": 0.8153312043691034,
|
64 |
+
"eval_accuracy": 0.804,
|
65 |
+
"eval_loss": 0.35289254784584045,
|
66 |
+
"eval_runtime": 6.2324,
|
67 |
+
"eval_samples_per_second": 240.677,
|
68 |
+
"eval_steps_per_second": 7.541,
|
69 |
+
"step": 516
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 500,
|
73 |
+
"max_steps": 1720,
|
74 |
+
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 10,
|
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": 0.605164320881552,
|
94 |
+
"learning_rate": 0.00013820614753724472,
|
95 |
+
"num_train_epochs": 10,
|
96 |
+
"temperature": 9
|
97 |
+
}
|
98 |
+
}
|
run-24/checkpoint-516/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db080950555f1448b25c4e51afe1a086f8b409b2841b40874bfcb82bde4dd4fe
|
3 |
+
size 5240
|
run-24/checkpoint-516/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-24/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-24/checkpoint-688/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cd88e55a4ad598aeedf3f4280a390f9784cf880a857c6e4d81f9cf21b4aa022
|
3 |
+
size 17549312
|
run-24/checkpoint-688/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c044b32ef437069b4b6b2b1d1e757646e944ccb01a280067d98dbff9a83653fd
|
3 |
+
size 35123898
|
run-24/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-24/checkpoint-688/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30b2b90006e3a2c253a37647a01130cb18ff999440ac3da1261bd3f1029cb923
|
3 |
+
size 1064
|
run-24/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-24/checkpoint-688/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-24/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-24/checkpoint-688/trainer_state.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.81,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-24/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": 0.6114831566810608,
|
14 |
+
"learning_rate": 0.00012438553278352026,
|
15 |
+
"loss": 0.4032,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.812864,
|
21 |
+
"eval_BAC": 0.736,
|
22 |
+
"eval_MCC": 0.47260700716368276,
|
23 |
+
"eval_PR_AUC": 0.7744742146180674,
|
24 |
+
"eval_accuracy": 0.736,
|
25 |
+
"eval_loss": 0.3765888214111328,
|
26 |
+
"eval_runtime": 6.2583,
|
27 |
+
"eval_samples_per_second": 239.681,
|
28 |
+
"eval_steps_per_second": 7.51,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 0.8825994729995728,
|
34 |
+
"learning_rate": 0.00011056491802979578,
|
35 |
+
"loss": 0.3836,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.834104888888889,
|
41 |
+
"eval_BAC": 0.7606666666666666,
|
42 |
+
"eval_MCC": 0.5584922194756476,
|
43 |
+
"eval_PR_AUC": 0.7802314251570694,
|
44 |
+
"eval_accuracy": 0.7606666666666667,
|
45 |
+
"eval_loss": 0.36870983242988586,
|
46 |
+
"eval_runtime": 6.277,
|
47 |
+
"eval_samples_per_second": 238.968,
|
48 |
+
"eval_steps_per_second": 7.488,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 1.0203838348388672,
|
54 |
+
"learning_rate": 9.67443032760713e-05,
|
55 |
+
"loss": 0.3769,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.8587253333333335,
|
61 |
+
"eval_BAC": 0.804,
|
62 |
+
"eval_MCC": 0.6132578536355836,
|
63 |
+
"eval_PR_AUC": 0.8153312043691034,
|
64 |
+
"eval_accuracy": 0.804,
|
65 |
+
"eval_loss": 0.35289254784584045,
|
66 |
+
"eval_runtime": 6.2324,
|
67 |
+
"eval_samples_per_second": 240.677,
|
68 |
+
"eval_steps_per_second": 7.541,
|
69 |
+
"step": 516
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.0,
|
73 |
+
"grad_norm": 2.1677234172821045,
|
74 |
+
"learning_rate": 8.292368852234684e-05,
|
75 |
+
"loss": 0.3677,
|
76 |
+
"step": 688
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_AUC": 0.8672444444444444,
|
81 |
+
"eval_BAC": 0.81,
|
82 |
+
"eval_MCC": 0.6290847145741534,
|
83 |
+
"eval_PR_AUC": 0.8293327638808494,
|
84 |
+
"eval_accuracy": 0.81,
|
85 |
+
"eval_loss": 0.3481285870075226,
|
86 |
+
"eval_runtime": 6.2093,
|
87 |
+
"eval_samples_per_second": 241.573,
|
88 |
+
"eval_steps_per_second": 7.569,
|
89 |
+
"step": 688
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"logging_steps": 500,
|
93 |
+
"max_steps": 1720,
|
94 |
+
"num_input_tokens_seen": 0,
|
95 |
+
"num_train_epochs": 10,
|
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": false
|
105 |
+
},
|
106 |
+
"attributes": {}
|
107 |
+
}
|
108 |
+
},
|
109 |
+
"total_flos": 1801510920000.0,
|
110 |
+
"train_batch_size": 32,
|
111 |
+
"trial_name": null,
|
112 |
+
"trial_params": {
|
113 |
+
"alpha": 0.605164320881552,
|
114 |
+
"learning_rate": 0.00013820614753724472,
|
115 |
+
"num_train_epochs": 10,
|
116 |
+
"temperature": 9
|
117 |
+
}
|
118 |
+
}
|
run-24/checkpoint-688/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db080950555f1448b25c4e51afe1a086f8b409b2841b40874bfcb82bde4dd4fe
|
3 |
+
size 5240
|
run-24/checkpoint-688/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-25/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-25/checkpoint-172/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8213352dae50cc3d57ccecacdd43708a479e7c2a90ef60b2d454c41f70088f34
|
3 |
+
size 17549312
|
run-25/checkpoint-172/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e0e9c065f0b95e48906d4d640da8a2723ca4a00e40b2e8f468aae67984dcfa0
|
3 |
+
size 35123898
|
run-25/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-25/checkpoint-172/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc1cbbc90dd196a984a862d2e56b8e356ce5cb2b72c88db207315d8f1d36e14b
|
3 |
+
size 1064
|
run-25/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-25/checkpoint-172/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-25/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-25/checkpoint-172/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7413333333333333,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-25/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": 0.8690188527107239,
|
14 |
+
"learning_rate": 0.0001732793884765621,
|
15 |
+
"loss": 0.484,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8223413333333331,
|
21 |
+
"eval_BAC": 0.7413333333333333,
|
22 |
+
"eval_MCC": 0.48280573474696187,
|
23 |
+
"eval_PR_AUC": 0.7777897109751378,
|
24 |
+
"eval_accuracy": 0.7413333333333333,
|
25 |
+
"eval_loss": 0.43229565024375916,
|
26 |
+
"eval_runtime": 6.2362,
|
27 |
+
"eval_samples_per_second": 240.531,
|
28 |
+
"eval_steps_per_second": 7.537,
|
29 |
+
"step": 172
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 344,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 2,
|
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": 0.7425109383729434,
|
54 |
+
"learning_rate": 0.0003465587769531242,
|
55 |
+
"num_train_epochs": 2,
|
56 |
+
"temperature": 5
|
57 |
+
}
|
58 |
+
}
|
run-25/checkpoint-172/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55a7265c224cfadd9cbeae7323bf17185f780b87c258a3ceb7edb6382228834d
|
3 |
+
size 5240
|
run-25/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 sha256:55a7265c224cfadd9cbeae7323bf17185f780b87c258a3ceb7edb6382228834d
|
3 |
size 5240
|