xuancoblab2023 commited on
Commit
ba380b9
·
verified ·
1 Parent(s): b2f29cb

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1711292011.73e3a81c01ef.4225.21 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6138364bb5f8deeea50f2cd1334ed831298a54f5a4a1dd0532ce836109f37604
3
- size 5406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22823a4f12ab032eae8d7b7b2d1dafb781632bd507a244283116662e87af214
3
+ size 6136
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f23031178abf4018a18bbf9c66d1da8ebda44c7847e8df5aa5496daaf1104fc
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f357ad34619bf81b66a71a8d67bdd38507c3fb9009d913839642728869deead4
3
  size 17549312
run-21/checkpoint-384/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": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-21/checkpoint-384/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f357ad34619bf81b66a71a8d67bdd38507c3fb9009d913839642728869deead4
3
+ size 17549312
run-21/checkpoint-384/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a63b60022645ac808452af076904fd96109e66bcdc1129b83ac4a7f445faf442
3
+ size 35122746
run-21/checkpoint-384/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2558f72cda987826e5e7caf54cc6282fe335ebecbddfed7bb83f0184d1f54cc
3
+ size 14054
run-21/checkpoint-384/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3c9436dd5101b31ccee16e63c1540cdf951638c07819ef5edd23a469ccf320
3
+ size 1064
run-21/checkpoint-384/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-21/checkpoint-384/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-384/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-21/checkpoint-384/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8082191780821918,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-384",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 384,
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": 5.036266803741455,
14
+ "learning_rate": 7.741005485591573e-05,
15
+ "loss": 0.556,
16
+ "step": 192
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.786692759295499,
21
+ "eval_f1": 0.8080985915492958,
22
+ "eval_loss": 0.4501095712184906,
23
+ "eval_mcc": 0.5882099387037968,
24
+ "eval_precision": 0.7344,
25
+ "eval_recall": 0.898238747553816,
26
+ "eval_runtime": 67.0331,
27
+ "eval_samples_per_second": 15.246,
28
+ "eval_steps_per_second": 0.477,
29
+ "step": 192
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 7.937936305999756,
34
+ "learning_rate": 5.8057541141936786e-05,
35
+ "loss": 0.4586,
36
+ "step": 384
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8082191780821918,
41
+ "eval_f1": 0.8161350844277674,
42
+ "eval_loss": 0.42737704515457153,
43
+ "eval_mcc": 0.6187363370477468,
44
+ "eval_precision": 0.7837837837837838,
45
+ "eval_recall": 0.8512720156555773,
46
+ "eval_runtime": 66.4748,
47
+ "eval_samples_per_second": 15.374,
48
+ "eval_steps_per_second": 0.481,
49
+ "step": 384
50
+ }
51
+ ],
52
+ "logging_steps": 500,
53
+ "max_steps": 960,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 5,
56
+ "save_steps": 500,
57
+ "total_flos": 471390394560.0,
58
+ "train_batch_size": 16,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "alpha": 0.8653499588119579,
62
+ "learning_rate": 9.676256856989465e-05,
63
+ "num_train_epochs": 5,
64
+ "per_device_train_batch_size": 16,
65
+ "temperature": 45
66
+ }
67
+ }
run-21/checkpoint-384/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b9a69c0a84f1792b2d6d65795033f526e96e3e74b93dead0b939d20001f112
3
+ size 4984
run-21/checkpoint-384/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 sha256:3f62d580257060cdaf08ca2f6bebff447fe36fd6a4ed09c360f3a936d71824ec
3
- size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b9a69c0a84f1792b2d6d65795033f526e96e3e74b93dead0b939d20001f112
3
+ size 4984