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
b2fd267
·
verified ·
1 Parent(s): 9be54ca

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713504727.persepolis.29644.2 +2 -2
  2. logs/events.out.tfevents.1713505330.persepolis.29644.3 +3 -0
  3. model.safetensors +1 -1
  4. run-1/checkpoint-2635/config.json +39 -0
  5. run-1/checkpoint-2635/model.safetensors +3 -0
  6. run-1/checkpoint-2635/optimizer.pt +3 -0
  7. run-1/checkpoint-2635/rng_state.pth +3 -0
  8. run-1/checkpoint-2635/scheduler.pt +3 -0
  9. run-1/checkpoint-2635/special_tokens_map.json +37 -0
  10. run-1/checkpoint-2635/tokenizer.json +0 -0
  11. run-1/checkpoint-2635/tokenizer_config.json +62 -0
  12. run-1/checkpoint-2635/trainer_state.json +106 -0
  13. run-1/checkpoint-2635/training_args.bin +3 -0
  14. run-1/checkpoint-2635/vocab.txt +0 -0
  15. run-2/checkpoint-527/config.json +39 -0
  16. run-2/checkpoint-527/model.safetensors +3 -0
  17. run-2/checkpoint-527/optimizer.pt +3 -0
  18. run-2/checkpoint-527/rng_state.pth +3 -0
  19. run-2/checkpoint-527/scheduler.pt +3 -0
  20. run-2/checkpoint-527/special_tokens_map.json +37 -0
  21. run-2/checkpoint-527/tokenizer.json +0 -0
  22. run-2/checkpoint-527/tokenizer_config.json +62 -0
  23. run-2/checkpoint-527/trainer_state.json +42 -0
  24. run-2/checkpoint-527/training_args.bin +3 -0
  25. run-2/checkpoint-527/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713504727.persepolis.29644.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e960bbf085646c78ab614ff05fc354dc83390b6308fdd47a9f2c59d7cfedbd2
3
- size 7080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4b1e19ab2e923a3c6a3f00dac46d537d6d9aaa49e916019b5091a14f8723b97
3
+ size 7968
logs/events.out.tfevents.1713505330.persepolis.29644.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1ccecd1141e2600b2e6899065e71772bbfd533d08c2024c0d233c32c387921
3
+ size 5478
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0597f644323ecdbe033d7f4c13d9e0cfeadf57356cd4296c7cf431491e72c9f4
3
  size 54221200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79298628d80bd34d4d819943a7ecd5dd64cf95f45e0aba0854d2bc21f6e712af
3
  size 54221200
run-1/checkpoint-2635/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-1/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef160dce6b88a82dc51924d898241a9db660a306e304e91d7ef4d01279bb4b11
3
+ size 54221200
run-1/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff7b3de7d1e898a742b1e184b2586d1cf709fe4221d1e7ed780c0aab489731c
3
+ size 108564282
run-1/checkpoint-2635/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f663bdb15d062023c1cf28c57849d73a5f427a71fc4ff8bd8995ab52fb854b16
3
+ size 14308
run-1/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7a9d5a9926a777cdb1b8b848c0778335d348b9b7f7b2a69ab4d626d1982538
3
+ size 1064
run-1/checkpoint-2635/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-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-2635/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-1/checkpoint-2635/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8910550458715596,
3
+ "best_model_checkpoint": "electra-distilled-sst\\run-1\\checkpoint-1054",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2635,
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": 66.74252319335938,
14
+ "learning_rate": 0.0002000029100592468,
15
+ "loss": 2.5183,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.875,
21
+ "eval_loss": 2.3820443153381348,
22
+ "eval_runtime": 1.4493,
23
+ "eval_samples_per_second": 601.689,
24
+ "eval_steps_per_second": 4.83,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 67.3247299194336,
30
+ "learning_rate": 0.00015007323994971434,
31
+ "loss": 1.237,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8910550458715596,
37
+ "eval_loss": 2.0578901767730713,
38
+ "eval_runtime": 1.4579,
39
+ "eval_samples_per_second": 598.133,
40
+ "eval_steps_per_second": 4.802,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 9.862482070922852,
46
+ "learning_rate": 0.00010014356984018184,
47
+ "loss": 0.8517,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8841743119266054,
53
+ "eval_loss": 2.112179756164551,
54
+ "eval_runtime": 1.4398,
55
+ "eval_samples_per_second": 605.639,
56
+ "eval_steps_per_second": 4.862,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 9.713326454162598,
62
+ "learning_rate": 5.021389973064936e-05,
63
+ "loss": 0.62,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8784403669724771,
69
+ "eval_loss": 2.1044843196868896,
70
+ "eval_runtime": 1.4493,
71
+ "eval_samples_per_second": 601.685,
72
+ "eval_steps_per_second": 4.83,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 34.83477020263672,
78
+ "learning_rate": 2.842296211168832e-07,
79
+ "loss": 0.4638,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.8910550458715596,
85
+ "eval_loss": 2.0922484397888184,
86
+ "eval_runtime": 1.4483,
87
+ "eval_samples_per_second": 602.09,
88
+ "eval_steps_per_second": 4.833,
89
+ "step": 2635
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 2635,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 5,
96
+ "save_steps": 500,
97
+ "total_flos": 936602651243304.0,
98
+ "train_batch_size": 128,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.15523880635662113,
102
+ "learning_rate": 0.0002496483505476624,
103
+ "num_train_epochs": 5,
104
+ "temperature": 16
105
+ }
106
+ }
run-1/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ae5bfb8dc04e1587c99a811e9f5c8e620e9e0c3708ec65e7504205f51d366f
3
+ size 5048
run-1/checkpoint-2635/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79298628d80bd34d4d819943a7ecd5dd64cf95f45e0aba0854d2bc21f6e712af
3
+ size 54221200
run-2/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2a2252df6a68d4c84816c7dbf83968507df758720b11584cb484cad977b20e6
3
+ size 108564282
run-2/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-2/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05fc8ef8651196407a72ff9594037bed79ea1e9e99d1fd98853cd6e8a6331283
3
+ size 1064
run-2/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-2/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5091743119266054,
3
+ "best_model_checkpoint": "electra-distilled-sst\\run-2\\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": 3.510751485824585,
14
+ "learning_rate": 0.0007235764985208607,
15
+ "loss": 4.9041,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5091743119266054,
21
+ "eval_loss": 4.841418266296387,
22
+ "eval_runtime": 1.4537,
23
+ "eval_samples_per_second": 599.861,
24
+ "eval_steps_per_second": 4.815,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 3162,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 6,
32
+ "save_steps": 500,
33
+ "total_flos": 186587234208876.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.2011698337552854,
38
+ "learning_rate": 0.0008679624007294999,
39
+ "num_train_epochs": 6,
40
+ "temperature": 5
41
+ }
42
+ }
run-2/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abd3ad0420c43f4a6dc3c7f59acb9782deb90e9d7937e2e6b0b2fe954e1152f
3
+ size 5048
run-2/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:a0ae5bfb8dc04e1587c99a811e9f5c8e620e9e0c3708ec65e7504205f51d366f
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abd3ad0420c43f4a6dc3c7f59acb9782deb90e9d7937e2e6b0b2fe954e1152f
3
  size 5048