sibstrider commited on
Commit
6dec3b6
1 Parent(s): 1c8f3ce

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 sha256:41ad1bb5f5b9373e318b3dccf40fdcc1f68f700fb28ef9bae27e5e923d25f4a2
3
  size 116795404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9daae86a41f9456705a887c9ec83097613eb972e56056b29071529315176893c
3
  size 116795404
run-1/checkpoint-276/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 600,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 2048,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 3,
46
+ "pad_token_id": 0,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "single_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.36.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 83828
54
+ }
run-1/checkpoint-276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2afb060c00b26fd23d8c74cc23dcb07285dfdf2fa22886faed486615b85d92
3
+ size 116795404
run-1/checkpoint-276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69bcdd5369a3ec8f0c3e048e8478c179a04b9f1b0264f174f4a2e1aec9bf909c
3
+ size 233621882
run-1/checkpoint-276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3986f4f3884942759939b9ff0c822ab6a348586b0daabc465b5f94101eb24a5
3
+ size 13990
run-1/checkpoint-276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e489cccb5c0efe2168a398375f59693441e912ed5fc9f1b8ec38473edd2870d
3
+ size 1064
run-1/checkpoint-276/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-1/checkpoint-276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-276/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
run-1/checkpoint-276/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8163265306122449,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-1\\checkpoint-276",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 276,
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": 0.7714285714285715,
14
+ "eval_loss": 1.5001928806304932,
15
+ "eval_runtime": 1.124,
16
+ "eval_samples_per_second": 217.972,
17
+ "eval_steps_per_second": 14.235,
18
+ "step": 138
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8163265306122449,
23
+ "eval_loss": 1.0953413248062134,
24
+ "eval_runtime": 1.175,
25
+ "eval_samples_per_second": 208.511,
26
+ "eval_steps_per_second": 13.617,
27
+ "step": 276
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 414,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 16,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 3.266288376624928e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 16,
42
+ "seed": 36
43
+ }
44
+ }
run-1/checkpoint-276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ba06e4df241930f59a2cb2d75e387e78b0cbefe51f6381c073f2e08285e49e
3
+ size 4728
run-1/checkpoint-276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-414/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 600,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 2048,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 3,
46
+ "pad_token_id": 0,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "single_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.36.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 83828
54
+ }
run-1/checkpoint-414/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9daae86a41f9456705a887c9ec83097613eb972e56056b29071529315176893c
3
+ size 116795404
run-1/checkpoint-414/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45cbc906f4256461da64c713eb8189b316e96086fc44a836256e02be1d66f3c0
3
+ size 233621882
run-1/checkpoint-414/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06bc64fcdaf909c15cf079eb01bfd874a6075d685cae4cab210020fb190405b9
3
+ size 13990
run-1/checkpoint-414/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058d28cd60335683cb4d2d036a388008a9cd78ad32c8b8aadbf43253410157fa
3
+ size 1064
run-1/checkpoint-414/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-1/checkpoint-414/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-414/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
run-1/checkpoint-414/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8408163265306122,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-1\\checkpoint-414",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 414,
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": 0.7714285714285715,
14
+ "eval_loss": 1.5001928806304932,
15
+ "eval_runtime": 1.124,
16
+ "eval_samples_per_second": 217.972,
17
+ "eval_steps_per_second": 14.235,
18
+ "step": 138
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8163265306122449,
23
+ "eval_loss": 1.0953413248062134,
24
+ "eval_runtime": 1.175,
25
+ "eval_samples_per_second": 208.511,
26
+ "eval_steps_per_second": 13.617,
27
+ "step": 276
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.8408163265306122,
32
+ "eval_loss": 0.9892452359199524,
33
+ "eval_runtime": 1.119,
34
+ "eval_samples_per_second": 218.945,
35
+ "eval_steps_per_second": 14.298,
36
+ "step": 414
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 414,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 16,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 3.266288376624928e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 16,
51
+ "seed": 36
52
+ }
53
+ }
run-1/checkpoint-414/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ba06e4df241930f59a2cb2d75e387e78b0cbefe51f6381c073f2e08285e49e
3
+ size 4728
run-1/checkpoint-414/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705259491.DESKTOP-RFEED41.20976.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65999fa43787fef93e3f44a95bb23e1018965452ba9c2c42259dcf4278a1b0d5
3
- size 5275
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd97ae80fc829963962f39677ef7d027a471d9492149c1c4317cbbea7bdb065b
3
+ size 6275