tcgyver commited on
Commit
10e1f37
1 Parent(s): 5e9b5c9

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:dfe832a8aebf9afd0057695779bcbf9ff98cdd9b155862a9901480f93951d187
3
- size 526337605
 
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aa9a09d6bd2426bd0eaa8a2810f471dc07e8f638a94fa1526856b3fac8bc578
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:a26e8e39bb51d8a7caed1830a870934f23f013aeeb7af5c748299e513ff1239c
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": 0.7358550612860959,
3
- "best_model_checkpoint": "bert-emotion/checkpoint-1630",
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": 0.8556,
14
- "step": 815
15
- },
16
- {
17
- "epoch": 1.0,
18
- "eval_fscore": 0.6088407481834592,
19
- "eval_loss": 0.7854498624801636,
20
- "eval_precision": 0.7460500863333636,
21
- "eval_recall": 0.5928805424781983,
22
- "eval_runtime": 0.6963,
23
- "eval_samples_per_second": 537.095,
24
- "eval_steps_per_second": 134.992,
25
- "step": 815
26
- },
27
- {
28
- "epoch": 2.0,
29
- "learning_rate": 1.6666666666666667e-05,
30
- "loss": 0.5369,
31
- "step": 1630
32
- },
33
- {
34
- "epoch": 2.0,
35
- "eval_fscore": 0.7358550612860959,
36
- "eval_loss": 0.9014220237731934,
37
- "eval_precision": 0.7548954614992351,
38
- "eval_recall": 0.7278147804934554,
39
- "eval_runtime": 0.6996,
40
- "eval_samples_per_second": 534.58,
41
- "eval_steps_per_second": 134.36,
42
- "step": 1630
43
- },
44
- {
45
- "epoch": 3.0,
46
- "learning_rate": 0.0,
47
- "loss": 0.2571,
48
- "step": 2445
49
- },
50
- {
51
- "epoch": 3.0,
52
- "eval_fscore": 0.7340137112297485,
53
- "eval_loss": 1.1412936449050903,
54
- "eval_precision": 0.7505623807659564,
55
- "eval_recall": 0.7243031825553111,
56
- "eval_runtime": 1.0289,
57
- "eval_samples_per_second": 363.493,
58
- "eval_steps_per_second": 91.359,
59
- "step": 2445
60
- }
61
- ],
62
- "max_steps": 2445,
63
- "num_train_epochs": 3,
64
- "total_flos": 95309811761304.0,
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 sha256:5c82dea0ca84efadda6d3ba4c7ef48b350f1d7322f2b4080e32fe28fbc8f6967
3
- size 3899
 
 
 
 
last-checkpoint/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aa9a09d6bd2426bd0eaa8a2810f471dc07e8f638a94fa1526856b3fac8bc578
3
  size 263173805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbf468791e262310b70e9b7e62c59bce1397f91ff65fd242a83ab52b1a750af
3
  size 263173805
runs/May30_16-11-47_69ba46e5071f/events.out.tfevents.1685463125.69ba46e5071f.267.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56d6411eae2f15a3298a05bfdfe130500d509fa95a06026761e91a3a75183199
3
- size 5773
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c12e356d46a6e97a365c5eadc76b5e4399ca944703594497333d01d0037d119
3
+ size 6127