xuancoblab2023 commited on
Commit
9e0ce72
·
verified ·
1 Parent(s): e481c99

Training in progress, epoch 1

Browse files
logs/events.out.tfevents.1713441879.ec9626078864.14834.44 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecd37eb526ffd4ea94610e02a5035a7209bd6a3cb91d8ecd2d4badd757100e00
3
- size 9057
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f403a962407466dc1776ce5d01eb95d773273efb300e676066c51e788121c827
3
+ size 9787
logs/events.out.tfevents.1713442247.ec9626078864.14834.45 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3340f1716a5b11cb7820ffc3227d8579ae1fa678db26e7d1129bf5241659c0ff
3
+ size 5407
logs/events.out.tfevents.1713442299.ec9626078864.14834.46 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a4950ec746a4e3f6281944d11f164ef933f98692e3fab60274abafaf421cb76
3
+ size 5407
logs/events.out.tfevents.1713442352.ec9626078864.14834.47 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f66a8ca1e4f2398b2917b1dc769392d98c16ec36f280845a440709780f7a2e
3
+ size 5405
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9dc2d5f6ef880b55cf1bb572263a0d7b637feff9bfb9659dd3245a1a8eb388b
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb3f905dfbb1b52d6479e9fcb56b4738c52dab5f5501007d1aabae623688354
3
  size 17549312
run-46/checkpoint-645/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-46/checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb3f905dfbb1b52d6479e9fcb56b4738c52dab5f5501007d1aabae623688354
3
+ size 17549312
run-46/checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06085e5231b606e0a71f9248bc343a0ecbe769c7f2820c8590c708148663187c
3
+ size 35123898
run-46/checkpoint-645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64cda8af0c2d214cf65bdf171fde38f18025a5a08f9a451c61fdf726867d7c2
3
+ size 14308
run-46/checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5be26437fc187e8808202866790ef5a1d059e7d1bc44e96e9b52e90e12e921ad
3
+ size 1064
run-46/checkpoint-645/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-46/checkpoint-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-46/checkpoint-645/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-46/checkpoint-645/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8933695230709577,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-46/checkpoint-645",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 645,
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": 1.6987380981445312,
14
+ "learning_rate": 0.00010984250364302024,
15
+ "loss": 0.3231,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8933695230709577,
21
+ "eval_f1": 0.23822714681440443,
22
+ "eval_loss": 0.3004969358444214,
23
+ "eval_mcc": 0.2521357214538019,
24
+ "eval_precision": 0.5620915032679739,
25
+ "eval_recall": 0.15114235500878734,
26
+ "eval_runtime": 9.9202,
27
+ "eval_samples_per_second": 519.949,
28
+ "eval_steps_per_second": 16.33,
29
+ "step": 645
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 2580,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 4,
36
+ "save_steps": 500,
37
+ "total_flos": 1586942532600.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.946912541258565,
42
+ "learning_rate": 0.000146456671524027,
43
+ "num_train_epochs": 4,
44
+ "temperature": 16
45
+ }
46
+ }
run-46/checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867920cc2fb71bfa041ac618264cc58420597c2e407df7768d84770b1009618e
3
+ size 4984
run-46/checkpoint-645/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 sha256:08828bcd5b32baf8358042cd0b0d31aa8b726101d471f32c4aacac638c8d4236
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867920cc2fb71bfa041ac618264cc58420597c2e407df7768d84770b1009618e
3
  size 4984