JeukHwang commited on
Commit
ae1fa58
·
1 Parent(s): 977fa3f

Training in progress, epoch 4

Browse files
logs/events.out.tfevents.1699911268.b18f42e49ba4.3021.25 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63088544fb117d44e34a70675d861d46374fc395690ff58d044db04e43f32a62
3
- size 5254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b1f177f3cb3d25dfd04fd3e83ae8c2e08e783aa247f2e3951a3614088e735d
3
+ size 6214
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95ed964cbc4b24c807d4fa8f86bf536bf22efe5eb051fc5a90f0697a068ae445
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b21520346822035eb05ba85e2b02b007e9280415e6960664cb00f38a14cbed
3
  size 17549312
run-24/checkpoint-2108/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-24/checkpoint-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b21520346822035eb05ba85e2b02b007e9280415e6960664cb00f38a14cbed
3
+ size 17549312
run-24/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d160c5cd7446a5c759234043bb995be7099ac141a48fa9171aa7a838fb81f6f
3
+ size 35123898
run-24/checkpoint-2108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5380d7490ac96d7f61709bde5d4086c1114991ed50d41459765b29873c758add
3
+ size 14308
run-24/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a638d47ebda73259f7f05768ea93172e5582f7c7870c51a65954caaacc7c9e7
3
+ size 1064
run-24/checkpoint-2108/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-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-2108/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-24/checkpoint-2108/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8302752293577982,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-1054",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2108,
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
+ "learning_rate": 9.264654582488016e-05,
14
+ "loss": 1.9014,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8107798165137615,
20
+ "eval_loss": 1.552759051322937,
21
+ "eval_runtime": 0.8371,
22
+ "eval_samples_per_second": 1041.732,
23
+ "eval_steps_per_second": 8.363,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 7.412426598811543e-05,
29
+ "loss": 0.9481,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8302752293577982,
35
+ "eval_loss": 1.4989248514175415,
36
+ "eval_runtime": 0.8428,
37
+ "eval_samples_per_second": 1034.644,
38
+ "eval_steps_per_second": 8.306,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 5.5601986151350695e-05,
44
+ "loss": 0.716,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8256880733944955,
50
+ "eval_loss": 1.504542350769043,
51
+ "eval_runtime": 0.9321,
52
+ "eval_samples_per_second": 935.536,
53
+ "eval_steps_per_second": 7.51,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 3.7079706314585956e-05,
59
+ "loss": 0.6102,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8188073394495413,
65
+ "eval_loss": 1.5119519233703613,
66
+ "eval_runtime": 0.8521,
67
+ "eval_samples_per_second": 1023.392,
68
+ "eval_steps_per_second": 8.215,
69
+ "step": 2108
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 3162,
74
+ "num_train_epochs": 6,
75
+ "save_steps": 500,
76
+ "total_flos": 32320254802260.0,
77
+ "trial_name": null,
78
+ "trial_params": {
79
+ "alpha": 0.32712078965773406,
80
+ "learning_rate": 0.00011113367902058842,
81
+ "num_train_epochs": 6,
82
+ "temperature": 24
83
+ }
84
+ }
run-24/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a8249c53933e918f28c304299ffcb113fd2a092e048e706c58ab31b2064ca9
3
+ size 4600
run-24/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff