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
86bb489
·
verified ·
1 Parent(s): bf0f6bd

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. logs/events.out.tfevents.1713506689.persepolis.29644.7 +2 -2
  2. logs/events.out.tfevents.1713507751.persepolis.29644.8 +3 -0
  3. logs/events.out.tfevents.1713507864.persepolis.29644.9 +3 -0
  4. model.safetensors +1 -1
  5. run-6/checkpoint-4743/config.json +39 -0
  6. run-6/checkpoint-4743/model.safetensors +3 -0
  7. run-6/checkpoint-4743/optimizer.pt +3 -0
  8. run-6/checkpoint-4743/rng_state.pth +3 -0
  9. run-6/checkpoint-4743/scheduler.pt +3 -0
  10. run-6/checkpoint-4743/special_tokens_map.json +37 -0
  11. run-6/checkpoint-4743/tokenizer.json +0 -0
  12. run-6/checkpoint-4743/tokenizer_config.json +62 -0
  13. run-6/checkpoint-4743/trainer_state.json +170 -0
  14. run-6/checkpoint-4743/training_args.bin +3 -0
  15. run-6/checkpoint-4743/vocab.txt +0 -0
  16. run-8/checkpoint-527/config.json +39 -0
  17. run-8/checkpoint-527/model.safetensors +3 -0
  18. run-8/checkpoint-527/optimizer.pt +3 -0
  19. run-8/checkpoint-527/rng_state.pth +3 -0
  20. run-8/checkpoint-527/scheduler.pt +3 -0
  21. run-8/checkpoint-527/special_tokens_map.json +37 -0
  22. run-8/checkpoint-527/tokenizer.json +0 -0
  23. run-8/checkpoint-527/tokenizer_config.json +62 -0
  24. run-8/checkpoint-527/trainer_state.json +42 -0
  25. run-8/checkpoint-527/training_args.bin +3 -0
  26. run-8/checkpoint-527/vocab.txt +0 -0
  27. training_args.bin +1 -1
logs/events.out.tfevents.1713506689.persepolis.29644.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a23a67d15c1aec8e3f4ce9fbec8bef0fcb80571dc4656a2a15b7733c6f97d3ca
3
- size 9216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a296745615caef372673b28e9e5ab72036f79a56cce08b3e62b85b2f2028c2
3
+ size 10104
logs/events.out.tfevents.1713507751.persepolis.29644.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e77d24ec0d8a318df88ebf9e15b678ad1a178a5f345c3452cb8cf19ffc3feb6d
3
+ size 5479
logs/events.out.tfevents.1713507864.persepolis.29644.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d79d72c7f46f0323b5d0401c2ed23b123740b1e3802cd433b05ada22f3269e
3
+ size 5479
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f090faca1d4edfb9e855cfdd0cc87ecc27fe6da086a4d9bb087c9d2dccf9c5ff
3
  size 54221200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1a0ff6583a43373e8dbfa5adc88891eec1cc5e7f350297b04b7bd1f9f23e78
3
  size 54221200
run-6/checkpoint-4743/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-6/checkpoint-4743/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:066d51dc785c5d0fd13181791a8ecf07645565918c9073fd7b3ed41290ea3403
3
+ size 54221200
run-6/checkpoint-4743/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18fabbd7cd0315782fabca0182c2970b364f111e0964621a4d262e01d47e4ee6
3
+ size 108564282
run-6/checkpoint-4743/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c152397842beab1796a552c55738a07bc58ecbe3a3243c1ede246aea0e445640
3
+ size 14308
run-6/checkpoint-4743/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f36665a9884cbce1ada0bc3cfca0e48f666dd5ce8d47b49bb4f8d0d663dc7b
3
+ size 1064
run-6/checkpoint-4743/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-6/checkpoint-4743/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-4743/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-6/checkpoint-4743/trainer_state.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.926605504587156,
3
+ "best_model_checkpoint": "electra-distilled-sst\\run-6\\checkpoint-2108",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4743,
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": 17.92670440673828,
14
+ "learning_rate": 2.010330074098376e-05,
15
+ "loss": 1.6952,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8910550458715596,
21
+ "eval_loss": 0.9234904050827026,
22
+ "eval_runtime": 1.446,
23
+ "eval_samples_per_second": 603.052,
24
+ "eval_steps_per_second": 4.841,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 43.87211990356445,
30
+ "learning_rate": 1.759575125325375e-05,
31
+ "loss": 0.8731,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.9059633027522935,
37
+ "eval_loss": 0.770187258720398,
38
+ "eval_runtime": 1.4489,
39
+ "eval_samples_per_second": 601.851,
40
+ "eval_steps_per_second": 4.831,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 13.310898780822754,
46
+ "learning_rate": 1.508343456117444e-05,
47
+ "loss": 0.6622,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.9139908256880734,
53
+ "eval_loss": 0.7737818956375122,
54
+ "eval_runtime": 1.4497,
55
+ "eval_samples_per_second": 601.516,
56
+ "eval_steps_per_second": 4.829,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 12.57313060760498,
62
+ "learning_rate": 1.2571117869095134e-05,
63
+ "loss": 0.5443,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.926605504587156,
69
+ "eval_loss": 0.7234447598457336,
70
+ "eval_runtime": 1.451,
71
+ "eval_samples_per_second": 600.977,
72
+ "eval_steps_per_second": 4.824,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 28.64960289001465,
78
+ "learning_rate": 1.0058801177015824e-05,
79
+ "loss": 0.48,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.9174311926605505,
85
+ "eval_loss": 0.7743226289749146,
86
+ "eval_runtime": 1.4478,
87
+ "eval_samples_per_second": 602.308,
88
+ "eval_steps_per_second": 4.835,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 10.863966941833496,
94
+ "learning_rate": 7.546484484936517e-06,
95
+ "loss": 0.4283,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.9220183486238532,
101
+ "eval_loss": 0.7562010288238525,
102
+ "eval_runtime": 1.4492,
103
+ "eval_samples_per_second": 601.691,
104
+ "eval_steps_per_second": 4.83,
105
+ "step": 3162
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 25.16184425354004,
110
+ "learning_rate": 5.038934997206505e-06,
111
+ "loss": 0.3886,
112
+ "step": 3689
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.9197247706422018,
117
+ "eval_loss": 0.7708072662353516,
118
+ "eval_runtime": 1.4413,
119
+ "eval_samples_per_second": 604.999,
120
+ "eval_steps_per_second": 4.857,
121
+ "step": 3689
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": 19.518695831298828,
126
+ "learning_rate": 2.5266183051271976e-06,
127
+ "loss": 0.373,
128
+ "step": 4216
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_accuracy": 0.9185779816513762,
133
+ "eval_loss": 0.8256669640541077,
134
+ "eval_runtime": 1.4454,
135
+ "eval_samples_per_second": 603.301,
136
+ "eval_steps_per_second": 4.843,
137
+ "step": 4216
138
+ },
139
+ {
140
+ "epoch": 9.0,
141
+ "grad_norm": 73.0574951171875,
142
+ "learning_rate": 1.4301613047889797e-08,
143
+ "loss": 0.3533,
144
+ "step": 4743
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "eval_accuracy": 0.9162844036697247,
149
+ "eval_loss": 0.8148481845855713,
150
+ "eval_runtime": 1.4457,
151
+ "eval_samples_per_second": 603.149,
152
+ "eval_steps_per_second": 4.842,
153
+ "step": 4743
154
+ }
155
+ ],
156
+ "logging_steps": 500,
157
+ "max_steps": 4743,
158
+ "num_input_tokens_seen": 0,
159
+ "num_train_epochs": 9,
160
+ "save_steps": 500,
161
+ "total_flos": 1684816747339368.0,
162
+ "train_batch_size": 128,
163
+ "trial_name": null,
164
+ "trial_params": {
165
+ "alpha": 0.7277023096419001,
166
+ "learning_rate": 2.261085022871377e-05,
167
+ "num_train_epochs": 9,
168
+ "temperature": 29
169
+ }
170
+ }
run-6/checkpoint-4743/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7705e1bdc734df47d18bce4720d4d36365410d1105809f45fd9138e67693b9
3
+ size 5048
run-6/checkpoint-4743/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1a0ff6583a43373e8dbfa5adc88891eec1cc5e7f350297b04b7bd1f9f23e78
3
+ size 54221200
run-8/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0febfe15c0f8074ea6946aad48b7a0a002b8afb1f17c079f5ae14c54852b5bc3
3
+ size 108564282
run-8/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-8/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c5effb5247e0a1c97bc04c31462d47ed73872fc3ae7ac326a2b3e8e8951d6c
3
+ size 1064
run-8/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-8/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9036697247706422,
3
+ "best_model_checkpoint": "electra-distilled-sst\\run-8\\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": 25.336427688598633,
14
+ "learning_rate": 8.271664431386432e-05,
15
+ "loss": 0.94,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.9036697247706422,
21
+ "eval_loss": 0.6703569889068604,
22
+ "eval_runtime": 1.4486,
23
+ "eval_samples_per_second": 601.968,
24
+ "eval_steps_per_second": 4.832,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 5270,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 10,
32
+ "save_steps": 500,
33
+ "total_flos": 186587234208876.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.7393993567935025,
38
+ "learning_rate": 9.188800917665787e-05,
39
+ "num_train_epochs": 10,
40
+ "temperature": 6
41
+ }
42
+ }
run-8/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604fb470236be9b28d71629cd094f68d34075ab2ebf7a71e2d7fae152203ef0e
3
+ size 5048
run-8/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:fd7705e1bdc734df47d18bce4720d4d36365410d1105809f45fd9138e67693b9
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604fb470236be9b28d71629cd094f68d34075ab2ebf7a71e2d7fae152203ef0e
3
  size 5048