Hugging Face's logo

obudzecie
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
obudzecie commited on
Commit
9d49645
•
1 Parent(s): d396424

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. model.safetensors +1 -1
  2. run-7/checkpoint-27/config.json +25 -0
  3. run-7/checkpoint-27/model.safetensors +3 -0
  4. run-7/checkpoint-27/optimizer.pt +3 -0
  5. run-7/checkpoint-27/rng_state.pth +3 -0
  6. run-7/checkpoint-27/scheduler.pt +3 -0
  7. run-7/checkpoint-27/special_tokens_map.json +7 -0
  8. run-7/checkpoint-27/tokenizer.json +0 -0
  9. run-7/checkpoint-27/tokenizer_config.json +55 -0
  10. run-7/checkpoint-27/trainer_state.json +35 -0
  11. run-7/checkpoint-27/training_args.bin +3 -0
  12. run-7/checkpoint-27/vocab.txt +0 -0
  13. run-8/checkpoint-27/config.json +25 -0
  14. run-8/checkpoint-27/model.safetensors +3 -0
  15. run-8/checkpoint-27/optimizer.pt +3 -0
  16. run-8/checkpoint-27/rng_state.pth +3 -0
  17. run-8/checkpoint-27/scheduler.pt +3 -0
  18. run-8/checkpoint-27/special_tokens_map.json +7 -0
  19. run-8/checkpoint-27/tokenizer.json +0 -0
  20. run-8/checkpoint-27/tokenizer_config.json +55 -0
  21. run-8/checkpoint-27/trainer_state.json +35 -0
  22. run-8/checkpoint-27/training_args.bin +3 -0
  23. run-8/checkpoint-27/vocab.txt +0 -0
  24. runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709062634.d3d09c0dfc16.836.18 +3 -0
  25. runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709062645.d3d09c0dfc16.836.19 +3 -0
  26. runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709062657.d3d09c0dfc16.836.20 +3 -0
  27. training_args.bin +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86a3a35334741fdbbf9f170e6a6a9530e2812fa8eccd04aca2cff02a06beedb4
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90af82b0097bc3fef61fd70c5aef866ba4fd4f704a0ffd9b614fd809ff2d5304
3
  size 267832560
run-7/checkpoint-27/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7564a94901fc9a19da15d34195d2536a0f4f3cc28329f82ac7589075408b980b
3
+ size 267832560
run-7/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd97ff09f244918c3e40a73d1db51a4fcfcfa7546f31b4285786ca4898daa20
3
+ size 535727290
run-7/checkpoint-27/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bf186c412d31936ba67e8e7661925718ec57ded5ebbd5389e67c8f65be6782
3
+ size 14244
run-7/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11fd38c7eabd116a82d09f6e88dfe3d7d2621c155f77c8b3b5cfb7198bfd0780
3
+ size 1064
run-7/checkpoint-27/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-7/checkpoint-27/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-27/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-7/checkpoint-27/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-27",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 27,
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_loss": 0.6485143899917603,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.4156,
16
+ "eval_samples_per_second": 736.801,
17
+ "eval_steps_per_second": 92.542,
18
+ "step": 27
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 81,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 3.6417971123005782e-06,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 27
34
+ }
35
+ }
run-7/checkpoint-27/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc9ab575082fc68efa351c47c15c3e6c732ccddb3c6b565ed370798882678ea0
3
+ size 4984
run-7/checkpoint-27/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-27/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8388610dfe42b3cbe61dd3f2e6f4a1d45914daa6ab2b89f0713994928316f019
3
+ size 267832560
run-8/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1d2ef18c2b7fe25d35414ad201329ddc57be5ce83919b05730497e763352c3
3
+ size 535727290
run-8/checkpoint-27/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8e486b82d9e5a71534855b4989950ca0b17177948b4eda3745bac0c1777272
3
+ size 14308
run-8/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76901d64ac5b2058f56523f407623a26f6fc30c45391aa486b2cc24c09ad0f2
3
+ size 1064
run-8/checkpoint-27/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-8/checkpoint-27/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-27/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-8/checkpoint-27/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-27",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 27,
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_loss": 0.6407399773597717,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.7011,
16
+ "eval_samples_per_second": 613.141,
17
+ "eval_steps_per_second": 77.01,
18
+ "step": 27
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 108,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 2.5037826580378036e-06,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 20
34
+ }
35
+ }
run-8/checkpoint-27/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a026e30c86ae6d404b4049748787112737fc14d9965eaa4ef17fab9e0f57ed0
3
+ size 4984
run-8/checkpoint-27/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709062634.d3d09c0dfc16.836.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b9b9a4ec1cc14a8375dedbbb85fedcd0d88eb723ee86f7f66d4ccc134e7ac2
3
+ size 5199
runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709062645.d3d09c0dfc16.836.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831fb636c3c6c88e291fbe205c57b17b9fc0deead1c5840e974f0c89c42ee9e8
3
+ size 5199
runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709062657.d3d09c0dfc16.836.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f43bff2bd2556d3fff44cf03fa63cbb436253a6f46210faa27f49f5c667bc6a
3
+ size 4870
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdd2de70007beb3d786052d08ae440a81b61d56e903d49a0367833e0af2b61f9
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55531ad0ca2e5236e3c2cf5a3b58985e9dc7e3f96c0a89eb5afb5657e37c51d1
3
+ size 4920