Tech-oriented commited on
Commit
500bcc1
1 Parent(s): f30dc80

Training in progress, epoch 2

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5516f568d9584132a4d0dae9f8f5d0773515aabc3ae2fe414cd662ff0000540c
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021e86c88dc67430e1e5c6d76dd0fc0c913c6aa802914511cccb0803a00af50c
3
  size 437958648
run-3/checkpoint-33676/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.4,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.4,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-3/checkpoint-33676/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021e86c88dc67430e1e5c6d76dd0fc0c913c6aa802914511cccb0803a00af50c
3
+ size 437958648
run-3/checkpoint-33676/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7fa85a5db4dc31e27ef3ab60cf48b7cf852476da155399f6cb89c5451077a4
3
+ size 876038394
run-3/checkpoint-33676/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b6820a4917708a5679709800e4ec332195ca8d655a478d18751676df5fe33a
3
+ size 14244
run-3/checkpoint-33676/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52781f6cb217173993e0c4bf84ad71d5dc090611670a82d9e48a08e324ce7a9
3
+ size 1064
run-3/checkpoint-33676/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-3/checkpoint-33676/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-33676/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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-3/checkpoint-33676/trainer_state.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9220183486238532,
3
+ "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-3/checkpoint-33676",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 33676,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 295.93414306640625,
14
+ "learning_rate": 9.536827410046812e-06,
15
+ "loss": 0.6121,
16
+ "step": 4209
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 0.9155740141868591,
21
+ "learning_rate": 8.669955440089204e-06,
22
+ "loss": 0.573,
23
+ "step": 8418
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 162.3487091064453,
28
+ "learning_rate": 7.803083470131597e-06,
29
+ "loss": 0.5403,
30
+ "step": 12627
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 0.1670043170452118,
35
+ "learning_rate": 6.936211500173989e-06,
36
+ "loss": 0.4884,
37
+ "step": 16836
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_accuracy": 0.9013761467889908,
42
+ "eval_loss": 0.4918152391910553,
43
+ "eval_runtime": 2.4623,
44
+ "eval_samples_per_second": 354.144,
45
+ "eval_steps_per_second": 22.337,
46
+ "step": 16838
47
+ },
48
+ {
49
+ "epoch": 1.25,
50
+ "grad_norm": 33.91927719116211,
51
+ "learning_rate": 6.069339530216381e-06,
52
+ "loss": 0.4458,
53
+ "step": 21045
54
+ },
55
+ {
56
+ "epoch": 1.5,
57
+ "grad_norm": 2.4961254596710205,
58
+ "learning_rate": 5.202467560258773e-06,
59
+ "loss": 0.4301,
60
+ "step": 25254
61
+ },
62
+ {
63
+ "epoch": 1.75,
64
+ "grad_norm": 0.07560272514820099,
65
+ "learning_rate": 4.335595590301165e-06,
66
+ "loss": 0.4057,
67
+ "step": 29463
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "grad_norm": 0.6363665461540222,
72
+ "learning_rate": 3.4687236203435575e-06,
73
+ "loss": 0.3992,
74
+ "step": 33672
75
+ },
76
+ {
77
+ "epoch": 2.0,
78
+ "eval_accuracy": 0.9220183486238532,
79
+ "eval_loss": 0.4500230848789215,
80
+ "eval_runtime": 2.4396,
81
+ "eval_samples_per_second": 357.431,
82
+ "eval_steps_per_second": 22.544,
83
+ "step": 33676
84
+ }
85
+ ],
86
+ "logging_steps": 4209,
87
+ "max_steps": 50514,
88
+ "num_input_tokens_seen": 0,
89
+ "num_train_epochs": 3,
90
+ "save_steps": 500,
91
+ "total_flos": 1655389413125220.0,
92
+ "train_batch_size": 4,
93
+ "trial_name": null,
94
+ "trial_params": {
95
+ "learning_rate": 1.040369938000442e-05,
96
+ "num_train_epochs": 3,
97
+ "per_device_train_batch_size": 4,
98
+ "seed": 7,
99
+ "weight_decay": 0.2933024618852218
100
+ }
101
+ }
run-3/checkpoint-33676/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9482bfd78493d3a93f61bdac0b3e0c266bc6feb1b9eeb8b0e705574041a082e
3
+ size 4984
run-3/checkpoint-33676/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709757360.e017d622c671.539.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b715918f088f87c8d6920528ea4f7d62f6163fbfa10f600da255bc17f200079d
3
- size 5925
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45912ed147d899c4835d233c4595ca5865535280d2acf6623a5c8f35e5e21875
3
+ size 7114