datht commited on
Commit
42edcc1
1 Parent(s): 48d6e32

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65d7da0d006186443d46ae59773b7e1cd81d3e1fe5f655e360149d689d877335
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05fccb75155fd3e76595b9fab6d6c7a85335077fdfb78802cbf4f876d9b8c257
3
  size 267835644
run-2/checkpoint-147/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.38.1",
34
+ "vocab_size": 30522
35
+ }
run-2/checkpoint-147/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05fccb75155fd3e76595b9fab6d6c7a85335077fdfb78802cbf4f876d9b8c257
3
+ size 267835644
run-2/checkpoint-147/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20f6bb62058ef22a592097bd9ac6c3d5fa20339aaae90e2e2fb31a53f54ce0d
3
+ size 535733434
run-2/checkpoint-147/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42fa5c93040569c02dea752d65807fe216a2d352ba2d9120b699e619eba0f991
3
+ size 14308
run-2/checkpoint-147/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232c27118f267b1e8ae4e2efb47e83ef19c02f660794a64933c5c2a80e40e663
3
+ size 1064
run-2/checkpoint-147/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-2/checkpoint-147/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-147/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-2/checkpoint-147/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6643835616438356,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-2/checkpoint-147",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 147,
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
+ "eval_accuracy": 0.6643835616438356,
14
+ "eval_loss": 0.7592821717262268,
15
+ "eval_runtime": 3.589,
16
+ "eval_samples_per_second": 162.72,
17
+ "eval_steps_per_second": 10.309,
18
+ "step": 147
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 735,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 6.031594833830981e-06,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 20
34
+ }
35
+ }
run-2/checkpoint-147/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36120bb4b2d0b720eac4a646b1e2a8af896ce0926f8d47d5e1fdf1d13dfce58c
3
+ size 4984
run-2/checkpoint-147/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711979017.c7a746a4e968.35.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be0a5dc2f5aa05ef179181ce45044395f80b253d815dc0951064a92998638c4
3
+ size 4980
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d668cda970f0e7b58198421b94cd9a12080cecdba47e0c64a8024f78de6495a3
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36120bb4b2d0b720eac4a646b1e2a8af896ce0926f8d47d5e1fdf1d13dfce58c
3
  size 4984