sibstrider commited on
Commit
f9c7a4d
1 Parent(s): 6db0403

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:dc9d1735e03593e326e1e528895da92b01589e1a2f64e413b4662eddc1d66131
3
  size 116795404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a662254a9bd9189f215541b7a62820144d6786928f15ae2de7f755f01c5828
3
  size 116795404
run-3/checkpoint-1650/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-3/checkpoint-1650/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a662254a9bd9189f215541b7a62820144d6786928f15ae2de7f755f01c5828
3
+ size 116795404
run-3/checkpoint-1650/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be5d5046bd18d02831886a2ca4ce380850936fc5d24f1cf627c971ca435bd10
3
+ size 233621882
run-3/checkpoint-1650/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989e0de2cbf91e1f074906d2b83814b66827c8558181a9e5c07f660052e422ec
3
+ size 13990
run-3/checkpoint-1650/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a14bf2ce9f6e05ed349d9057c685478492cdf05f37594ddaa3f216426168c4
3
+ size 1064
run-3/checkpoint-1650/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-3/checkpoint-1650/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1650/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-3/checkpoint-1650/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3877551020408163,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-3\\checkpoint-550",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1650,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.91,
13
+ "learning_rate": 1.3662899505209146e-06,
14
+ "loss": 2.35,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.3877551020408163,
20
+ "eval_loss": 2.2825658321380615,
21
+ "eval_runtime": 1.1797,
22
+ "eval_samples_per_second": 207.683,
23
+ "eval_steps_per_second": 13.563,
24
+ "step": 550
25
+ },
26
+ {
27
+ "epoch": 1.82,
28
+ "learning_rate": 7.722508415987777e-07,
29
+ "loss": 2.2529,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.3795918367346939,
35
+ "eval_loss": 2.1926839351654053,
36
+ "eval_runtime": 1.103,
37
+ "eval_samples_per_second": 222.122,
38
+ "eval_steps_per_second": 14.506,
39
+ "step": 1100
40
+ },
41
+ {
42
+ "epoch": 2.73,
43
+ "learning_rate": 1.7821173267664104e-07,
44
+ "loss": 2.1925,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.37551020408163266,
50
+ "eval_loss": 2.160534143447876,
51
+ "eval_runtime": 1.431,
52
+ "eval_samples_per_second": 171.209,
53
+ "eval_steps_per_second": 11.181,
54
+ "step": 1650
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 1650,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 3,
61
+ "save_steps": 500,
62
+ "total_flos": 2885602679400.0,
63
+ "train_batch_size": 4,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 1.9603290594430513e-06,
67
+ "num_train_epochs": 3,
68
+ "per_device_train_batch_size": 4,
69
+ "seed": 40
70
+ }
71
+ }
run-3/checkpoint-1650/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e267ca63c53f31d703414854821a4189b7f58d9ce572859ccd38579e71acb732
3
+ size 4728
run-3/checkpoint-1650/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.1705260668.DESKTOP-RFEED41.20976.9 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2d9fa85fa96d592886a14e286787c3cc78dbeb83859ca4758437fc3a187945c
3
- size 5912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a370ef6c93ad0457d5f90e34e76925fc88e4c13ba22dc9b90b5dc2292076f0df
3
+ size 6746