apetulante commited on
Commit
543d3d5
·
1 Parent(s): a462ce5

end of training 3 epochs

Browse files
last-checkpoint/config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_name_or_path": "distilbert-base-cased",
3
- "activation": "gelu",
4
- "architectures": [
5
- "DistilBertForSequenceClassification"
6
- ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
11
- "id2label": {
12
- "0": "anger",
13
- "1": "joy",
14
- "2": "optimism",
15
- "3": "sadness"
16
- },
17
- "initializer_range": 0.02,
18
- "label2id": {
19
- "anger": 0,
20
- "joy": 1,
21
- "optimism": 2,
22
- "sadness": 3
23
- },
24
- "max_position_embeddings": 512,
25
- "model_type": "distilbert",
26
- "n_heads": 12,
27
- "n_layers": 6,
28
- "output_past": true,
29
- "pad_token_id": 0,
30
- "problem_type": "single_label_classification",
31
- "qa_dropout": 0.1,
32
- "seq_classif_dropout": 0.2,
33
- "sinusoidal_pos_embds": false,
34
- "tie_weights_": true,
35
- "torch_dtype": "float32",
36
- "transformers_version": "4.29.2",
37
- "vocab_size": 28996
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d55d7c26014a79d1621cfff040d5e36353973e497fe9c4972340807c24f07281
3
- size 526337605
 
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3449a3fe7f8eb91a4110c0d2d42c1948404f7f12555e6454d4a0ded4425fb697
3
- size 263173805
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:95121a03130c20cd42fca5a281b2c01f2beee94c8dcc417d49d1d329ac5c2e27
3
- size 14575
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b97cbb8612b487297195de021ea547749e32246db05d923833a6ff76e97b74d
3
- size 627
 
 
 
 
last-checkpoint/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
last-checkpoint/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": false,
5
- "mask_token": "[MASK]",
6
- "model_max_length": 512,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "DistilBertTokenizer",
12
- "unk_token": "[UNK]"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,67 +0,0 @@
1
- {
2
- "best_metric": 0.7026458905584507,
3
- "best_model_checkpoint": "bert-emotion/checkpoint-2445",
4
- "epoch": 3.0,
5
- "global_step": 2445,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 1.0,
12
- "learning_rate": 3.3333333333333335e-05,
13
- "loss": 0.877,
14
- "step": 815
15
- },
16
- {
17
- "epoch": 1.0,
18
- "eval_fscore": 0.6765085079349261,
19
- "eval_loss": 0.8045032620429993,
20
- "eval_precision": 0.744856968428397,
21
- "eval_recall": 0.6494702118945573,
22
- "eval_runtime": 0.7333,
23
- "eval_samples_per_second": 509.994,
24
- "eval_steps_per_second": 128.18,
25
- "step": 815
26
- },
27
- {
28
- "epoch": 2.0,
29
- "learning_rate": 1.6666666666666667e-05,
30
- "loss": 0.5462,
31
- "step": 1630
32
- },
33
- {
34
- "epoch": 2.0,
35
- "eval_fscore": 0.6773642519384729,
36
- "eval_loss": 1.0057429075241089,
37
- "eval_precision": 0.7147887424988623,
38
- "eval_recall": 0.6566177231056908,
39
- "eval_runtime": 0.7943,
40
- "eval_samples_per_second": 470.836,
41
- "eval_steps_per_second": 118.338,
42
- "step": 1630
43
- },
44
- {
45
- "epoch": 3.0,
46
- "learning_rate": 0.0,
47
- "loss": 0.2691,
48
- "step": 2445
49
- },
50
- {
51
- "epoch": 3.0,
52
- "eval_fscore": 0.7026458905584507,
53
- "eval_loss": 1.2736551761627197,
54
- "eval_precision": 0.6979544225842089,
55
- "eval_recall": 0.7110390879680959,
56
- "eval_runtime": 0.7665,
57
- "eval_samples_per_second": 487.904,
58
- "eval_steps_per_second": 122.628,
59
- "step": 2445
60
- }
61
- ],
62
- "max_steps": 2445,
63
- "num_train_epochs": 3,
64
- "total_flos": 94971645618192.0,
65
- "trial_name": null,
66
- "trial_params": null
67
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd1dee909cc7422222cfff046af208c539c554f6cf55fe861295423f1dd64bee
3
- size 3899
 
 
 
 
last-checkpoint/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
runs/May29_20-56-54_0eb21313a3aa/events.out.tfevents.1685393829.0eb21313a3aa.23532.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5042f2814e9ae0e876408400f75376b348c12c5fdcc3224e2d279e15aaeffc8a
3
- size 5773
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c84e4e5d637e04a9746bf8ad67b726cb34f1ac9eefb392e6f9b290da9dd95d
3
+ size 6127