Ethan615 commited on
Commit
68b5beb
·
verified ·
1 Parent(s): 0c7a166

Training in progress, epoch 3

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9218d92639523b66107f5a8deb3d28fc571cd11316f9588aa4ec91cedf0930f8
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6233d9428b0c85753a5fb4ab9b84f2cfd125c240ba5ce59f40036dc1cfa110dc
3
  size 267832560
run-1/checkpoint-3207/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.39.3",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-3207/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6233d9428b0c85753a5fb4ab9b84f2cfd125c240ba5ce59f40036dc1cfa110dc
3
+ size 267832560
run-1/checkpoint-3207/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9add28fbe5b02f75490b6f93c6079727a18735d9192ba3d5b27353da3ffb7c0b
3
+ size 535727290
run-1/checkpoint-3207/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd83b62bf6a556c1ef38f6cdaa20d97ae6f41e71ccb1f2f81645d01d1bbb19c1
3
+ size 14244
run-1/checkpoint-3207/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b22797d1589f6b56aa471443393afd14d617137ce860e3821196fbaf393b92
3
+ size 1064
run-1/checkpoint-3207/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-1/checkpoint-3207/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-3207/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-1/checkpoint-3207/trainer_state.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4915876892254164,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3207,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "grad_norm": 8.518925666809082,
14
+ "learning_rate": 8.972995831812351e-06,
15
+ "loss": 0.5555,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.94,
20
+ "grad_norm": 15.430549621582031,
21
+ "learning_rate": 8.046990070015412e-06,
22
+ "loss": 0.509,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.5366330146789551,
28
+ "eval_matthews_correlation": 0.4025454740592728,
29
+ "eval_runtime": 0.8238,
30
+ "eval_samples_per_second": 1266.155,
31
+ "eval_steps_per_second": 80.121,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4,
36
+ "grad_norm": 22.634355545043945,
37
+ "learning_rate": 7.120984308218471e-06,
38
+ "loss": 0.3856,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 1.87,
43
+ "grad_norm": 40.38935089111328,
44
+ "learning_rate": 6.194978546421531e-06,
45
+ "loss": 0.3925,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.6002808213233948,
51
+ "eval_matthews_correlation": 0.4915876892254164,
52
+ "eval_runtime": 0.7672,
53
+ "eval_samples_per_second": 1359.42,
54
+ "eval_steps_per_second": 86.023,
55
+ "step": 2138
56
+ },
57
+ {
58
+ "epoch": 2.34,
59
+ "grad_norm": 33.39309310913086,
60
+ "learning_rate": 5.2689727846245905e-06,
61
+ "loss": 0.3121,
62
+ "step": 2500
63
+ },
64
+ {
65
+ "epoch": 2.81,
66
+ "grad_norm": 28.698448181152344,
67
+ "learning_rate": 4.34296702282765e-06,
68
+ "loss": 0.2998,
69
+ "step": 3000
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "eval_loss": 0.6921499371528625,
74
+ "eval_matthews_correlation": 0.48652176899433314,
75
+ "eval_runtime": 0.7643,
76
+ "eval_samples_per_second": 1364.583,
77
+ "eval_steps_per_second": 86.349,
78
+ "step": 3207
79
+ }
80
+ ],
81
+ "logging_steps": 500,
82
+ "max_steps": 5345,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 5,
85
+ "save_steps": 500,
86
+ "total_flos": 112981496058780.0,
87
+ "train_batch_size": 8,
88
+ "trial_name": null,
89
+ "trial_params": {
90
+ "learning_rate": 9.899001593609293e-06,
91
+ "num_train_epochs": 5,
92
+ "per_device_train_batch_size": 8,
93
+ "seed": 30
94
+ }
95
+ }
run-1/checkpoint-3207/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700e5a8d2a7a3275e73e65bff8334235b4a5dc3f98246bcca9062835dce46dee
3
+ size 4984
run-1/checkpoint-3207/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr05_13-35-05_48c5213de69d/events.out.tfevents.1712325014.48c5213de69d.790.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfd08490cda8e21d2b6990fa631eeb90deab6709bf2586f8d8bd75a522edf780
3
- size 6106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a90ff17d7a91621839d84d3b7a51db484966a51aff28b3b91f7dc0c6b51b97
3
+ size 7074