Hugging Face's logo

kasohrab
/
electra-distilled

Text Classification
Transformers
TensorBoard
Safetensors
electra
Model card Files
xet
Metrics Community
kasohrab commited on
Commit
ddc1c98
·
verified ·
1 Parent(s): 85caa38

Training in progress, epoch 1

Browse files
Files changed (17) hide show
  1. config.json +1 -1
  2. logs/events.out.tfevents.1713491533.persepolis.24356.7 +2 -2
  3. logs/events.out.tfevents.1713494701.persepolis.24356.8 +3 -0
  4. logs/events.out.tfevents.1713494873.persepolis.37460.0 +3 -0
  5. model.safetensors +1 -1
  6. run-0/checkpoint-527/config.json +39 -0
  7. run-0/checkpoint-527/model.safetensors +3 -0
  8. run-0/checkpoint-527/optimizer.pt +3 -0
  9. run-0/checkpoint-527/rng_state.pth +3 -0
  10. run-0/checkpoint-527/scheduler.pt +3 -0
  11. run-0/checkpoint-527/special_tokens_map.json +37 -0
  12. run-0/checkpoint-527/tokenizer.json +0 -0
  13. run-0/checkpoint-527/tokenizer_config.json +62 -0
  14. run-0/checkpoint-527/trainer_state.json +42 -0
  15. run-0/checkpoint-527/training_args.bin +3 -0
  16. run-0/checkpoint-527/vocab.txt +0 -0
  17. training_args.bin +2 -2
config.json CHANGED
@@ -32,7 +32,7 @@
32
  "summary_type": "first",
33
  "summary_use_proj": true,
34
  "torch_dtype": "float32",
35
- "transformers_version": "4.39.3",
36
  "type_vocab_size": 2,
37
  "use_cache": true,
38
  "vocab_size": 30522
 
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
logs/events.out.tfevents.1713491533.persepolis.24356.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1d34c45cdd71173c9aff7d33b36dc94f6719f620863d8c80e7ec97dcfb54e1c
3
- size 8040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5d9da919b46885026c604df522b9176212ed576b039992ef2718f453bcf88f
3
+ size 8928
logs/events.out.tfevents.1713494701.persepolis.24356.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a90a7bc21ba2aa4773c04ec49a04af791629aba32c1f14ed13b5f159d617fb2
3
+ size 4852
logs/events.out.tfevents.1713494873.persepolis.37460.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7081cf3e0e34da2807797ca9fdf4f45f3a32e755d4baa3649c70b77a7569339b
3
+ size 5462
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71f57863770d4538b621a5428c276d31e49e350232edd652f5aeb49ca379f037
3
  size 54221200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c9e4f39c0209a43ec9f211a8dd4f2d291ab2010ee25111f253f7063cedbf55
3
  size 54221200
run-0/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-0/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c9e4f39c0209a43ec9f211a8dd4f2d291ab2010ee25111f253f7063cedbf55
3
+ size 54221200
run-0/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8942b0565b663debd4bc4d08c9b9745828034b70ccbd98cc7fe9c8c3882764
3
+ size 108564282
run-0/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-0/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8328d9bc054d567aa96a5cfe1ec5e7ed578678f76110f6ef49ba3f2af4f434
3
+ size 1064
run-0/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-0/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8956422018348624,
3
+ "best_model_checkpoint": "electra-distilled\\run-0\\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": 32.339683532714844,
14
+ "learning_rate": 3.7858342547009837e-05,
15
+ "loss": 2.3212,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8956422018348624,
21
+ "eval_loss": 1.1868938207626343,
22
+ "eval_runtime": 1.4837,
23
+ "eval_samples_per_second": 587.721,
24
+ "eval_steps_per_second": 4.718,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 4216,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 8,
32
+ "save_steps": 500,
33
+ "total_flos": 186587234208876.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.46392361362069834,
38
+ "learning_rate": 4.324323277653575e-05,
39
+ "num_train_epochs": 8,
40
+ "temperature": 30
41
+ }
42
+ }
run-0/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5e145d0ddb156ac59ddc14f60dab1f45d9921eed04c2b7d09faa71c2681b9e
3
+ size 5048
run-0/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:d188b3e0c349e784d27bd2c2043d6eeafdc5fa20586e760d3ece4aae36696b91
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5e145d0ddb156ac59ddc14f60dab1f45d9921eed04c2b7d09faa71c2681b9e
3
+ size 5048