Hugging Face's logo

kasohrab
/
electra-distilled-sst

Text Classification
Transformers
TensorBoard
Safetensors
electra
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kasohrab commited on
Commit
6d28c16
•
1 Parent(s): 25b386a

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713506046.persepolis.29644.4 +2 -2
  2. logs/events.out.tfevents.1713506311.persepolis.29644.5 +3 -0
  3. model.safetensors +1 -1
  4. run-3/checkpoint-1054/config.json +39 -0
  5. run-3/checkpoint-1054/model.safetensors +3 -0
  6. run-3/checkpoint-1054/optimizer.pt +3 -0
  7. run-3/checkpoint-1054/rng_state.pth +3 -0
  8. run-3/checkpoint-1054/scheduler.pt +3 -0
  9. run-3/checkpoint-1054/special_tokens_map.json +37 -0
  10. run-3/checkpoint-1054/tokenizer.json +0 -0
  11. run-3/checkpoint-1054/tokenizer_config.json +62 -0
  12. run-3/checkpoint-1054/trainer_state.json +58 -0
  13. run-3/checkpoint-1054/training_args.bin +3 -0
  14. run-3/checkpoint-1054/vocab.txt +0 -0
  15. run-4/checkpoint-527/config.json +39 -0
  16. run-4/checkpoint-527/model.safetensors +3 -0
  17. run-4/checkpoint-527/optimizer.pt +3 -0
  18. run-4/checkpoint-527/rng_state.pth +3 -0
  19. run-4/checkpoint-527/scheduler.pt +3 -0
  20. run-4/checkpoint-527/special_tokens_map.json +37 -0
  21. run-4/checkpoint-527/tokenizer.json +0 -0
  22. run-4/checkpoint-527/tokenizer_config.json +62 -0
  23. run-4/checkpoint-527/trainer_state.json +42 -0
  24. run-4/checkpoint-527/training_args.bin +3 -0
  25. run-4/checkpoint-527/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713506046.persepolis.29644.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c08b3ff72fd8562113b283679075123bd0d63821fc52b37ca4673b4dd4abb3f3
3
- size 5479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36847913ec5bc699bb7adf2d6e432af71f4e23e48290000336b369402ad7ef35
3
+ size 6367
logs/events.out.tfevents.1713506311.persepolis.29644.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45bd4f53621ee93825c17a8555958fa2c5f91d8b1345756a84523f31675e7e01
3
+ size 5478
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0235f33576132397312ada05940fd0357d9698462ad10e4f5619204286e81eff
3
  size 54221200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f97a3f493fae23b1b5cd2a457039293f3aab7ea0e16575deee3b9446630456
3
  size 54221200
run-3/checkpoint-1054/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/electra-small-discriminator",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 128,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 256,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1024,
18
+ "label2id": {
19
+ "negative": "0",
20
+ "positive": "1"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "electra",
25
+ "num_attention_heads": 4,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "summary_activation": "gelu",
31
+ "summary_last_dropout": 0.1,
32
+ "summary_type": "first",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.40.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 30522
39
+ }
run-3/checkpoint-1054/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac33823532e51308447571cc8d477055f14b95069a2bfa867f455c514c228f4
3
+ size 54221200
run-3/checkpoint-1054/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653847f181b4fdd8403b792f25b187f34eabd8bb39438edf1ec5b4046e1fe894
3
+ size 108564282
run-3/checkpoint-1054/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:085ca35ec4dc671993a68ae04b5c8903d6f41b040217020fac4d4514df1e6c6e
3
+ size 14308
run-3/checkpoint-1054/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07185af642e6eb705acceca57de76e098a18262ea7a57df8fd3e0b1ea831b06
3
+ size 1064
run-3/checkpoint-1054/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-1054/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1054/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 128,
49
+ "model_max_length": 512,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "ElectraTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
run-3/checkpoint-1054/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9013761467889908,
3
+ "best_model_checkpoint": "electra-distilled-sst\\run-3\\checkpoint-1054",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1054,
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
+ "grad_norm": 20.69542694091797,
14
+ "learning_rate": 1.4084477147380312e-05,
15
+ "loss": 1.4419,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8704128440366973,
21
+ "eval_loss": 0.8999464511871338,
22
+ "eval_runtime": 1.4417,
23
+ "eval_samples_per_second": 604.854,
24
+ "eval_steps_per_second": 4.855,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": Infinity,
30
+ "learning_rate": 5.335029222492542e-08,
31
+ "loss": 0.8235,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.9013761467889908,
37
+ "eval_loss": 0.7633256912231445,
38
+ "eval_runtime": 1.4453,
39
+ "eval_samples_per_second": 603.342,
40
+ "eval_steps_per_second": 4.843,
41
+ "step": 1054
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 1054,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 2,
48
+ "save_steps": 500,
49
+ "total_flos": 373776249469380.0,
50
+ "train_batch_size": 128,
51
+ "trial_name": null,
52
+ "trial_params": {
53
+ "alpha": 0.7273510251657795,
54
+ "learning_rate": 2.8115604002535698e-05,
55
+ "num_train_epochs": 2,
56
+ "temperature": 7
57
+ }
58
+ }
run-3/checkpoint-1054/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff6a73b0274d51d0230d65160acf1da02acf6cc8fc7e82070ef6d105deddf34c
3
+ size 5048
run-3/checkpoint-1054/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-527/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/electra-small-discriminator",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 128,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 256,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1024,
18
+ "label2id": {
19
+ "negative": "0",
20
+ "positive": "1"
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "electra",
25
+ "num_attention_heads": 4,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "summary_activation": "gelu",
31
+ "summary_last_dropout": 0.1,
32
+ "summary_type": "first",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.40.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 30522
39
+ }
run-4/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f97a3f493fae23b1b5cd2a457039293f3aab7ea0e16575deee3b9446630456
3
+ size 54221200
run-4/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a446067c0df7bec304183f376b8069ccd0fb2f62c7bb31b08d5a5270e6d60e22
3
+ size 108564282
run-4/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc9791cb55befa0c8b441bb05d4823eb646b6924ad858d6b339d592c0fbe5a2
3
+ size 14308
run-4/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3116ba6f13cad5622787da759fd43e050e23f71b01393506ac1b7053d7e65568
3
+ size 1064
run-4/checkpoint-527/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-4/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-527/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 128,
49
+ "model_max_length": 512,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "ElectraTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
run-4/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8922018348623854,
3
+ "best_model_checkpoint": "electra-distilled-sst\\run-4\\checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
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
+ "grad_norm": 26.105838775634766,
14
+ "learning_rate": 2.1019516058113692e-05,
15
+ "loss": 1.7548,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8922018348623854,
21
+ "eval_loss": 0.9411500692367554,
22
+ "eval_runtime": 1.4396,
23
+ "eval_samples_per_second": 605.724,
24
+ "eval_steps_per_second": 4.862,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 1054,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 2,
32
+ "save_steps": 500,
33
+ "total_flos": 186587234208876.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.4067254850025479,
38
+ "learning_rate": 4.195941273721938e-05,
39
+ "num_train_epochs": 2,
40
+ "temperature": 4
41
+ }
42
+ }
run-4/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54623c6f2e4fc53202fd30482607c234dd22e66d8ff08e6a11fec29b6f68cb4
3
+ size 5048
run-4/checkpoint-527/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff6a73b0274d51d0230d65160acf1da02acf6cc8fc7e82070ef6d105deddf34c
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54623c6f2e4fc53202fd30482607c234dd22e66d8ff08e6a11fec29b6f68cb4
3
  size 5048