Hugging Face's logo

Slava
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Slava commited on
Commit
e99107c
·
verified ·
1 Parent(s): 7f14c98

Training in progress, epoch 2

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. logs/events.out.tfevents.1706213692.A-FVFFG2C4Q05P.18450.12 +2 -2
  2. logs/events.out.tfevents.1706219148.A-FVFFG2C4Q05P.18450.13 +3 -0
  3. logs/events.out.tfevents.1706220282.A-FVFFG2C4Q05P.18450.14 +3 -0
  4. logs/events.out.tfevents.1706225688.A-FVFFG2C4Q05P.18450.15 +3 -0
  5. logs/events.out.tfevents.1706235148.A-FVFFG2C4Q05P.18450.16 +3 -0
  6. logs/events.out.tfevents.1706238477.A-FVFFG2C4Q05P.18450.17 +3 -0
  7. logs/events.out.tfevents.1706248274.A-FVFFG2C4Q05P.18450.18 +3 -0
  8. logs/events.out.tfevents.1706249191.A-FVFFG2C4Q05P.18450.19 +3 -0
  9. model.safetensors +1 -1
  10. run-11/checkpoint-1054/config.json +34 -0
  11. run-11/checkpoint-1054/model.safetensors +3 -0
  12. run-11/checkpoint-1054/optimizer.pt +3 -0
  13. run-11/checkpoint-1054/rng_state.pth +3 -0
  14. run-11/checkpoint-1054/scheduler.pt +3 -0
  15. run-11/checkpoint-1054/special_tokens_map.json +7 -0
  16. run-11/checkpoint-1054/tokenizer.json +0 -0
  17. run-11/checkpoint-1054/tokenizer_config.json +57 -0
  18. run-11/checkpoint-1054/trainer_state.json +56 -0
  19. run-11/checkpoint-1054/training_args.bin +3 -0
  20. run-11/checkpoint-1054/vocab.txt +0 -0
  21. run-11/checkpoint-3689/config.json +34 -0
  22. run-11/checkpoint-3689/model.safetensors +3 -0
  23. run-11/checkpoint-3689/optimizer.pt +3 -0
  24. run-11/checkpoint-3689/rng_state.pth +3 -0
  25. run-11/checkpoint-3689/scheduler.pt +3 -0
  26. run-11/checkpoint-3689/special_tokens_map.json +7 -0
  27. run-11/checkpoint-3689/tokenizer.json +0 -0
  28. run-11/checkpoint-3689/tokenizer_config.json +57 -0
  29. run-11/checkpoint-3689/trainer_state.json +131 -0
  30. run-11/checkpoint-3689/training_args.bin +3 -0
  31. run-11/checkpoint-3689/vocab.txt +0 -0
  32. run-14/checkpoint-527/config.json +34 -0
  33. run-14/checkpoint-527/model.safetensors +3 -0
  34. run-14/checkpoint-527/optimizer.pt +3 -0
  35. run-14/checkpoint-527/rng_state.pth +3 -0
  36. run-14/checkpoint-527/scheduler.pt +3 -0
  37. run-14/checkpoint-527/special_tokens_map.json +7 -0
  38. run-14/checkpoint-527/tokenizer.json +0 -0
  39. run-14/checkpoint-527/tokenizer_config.json +57 -0
  40. run-14/checkpoint-527/trainer_state.json +41 -0
  41. run-14/checkpoint-527/training_args.bin +3 -0
  42. run-14/checkpoint-527/vocab.txt +0 -0
  43. run-16/checkpoint-1581/config.json +34 -0
  44. run-16/checkpoint-1581/model.safetensors +3 -0
  45. run-16/checkpoint-1581/optimizer.pt +3 -0
  46. run-16/checkpoint-1581/rng_state.pth +3 -0
  47. run-16/checkpoint-1581/scheduler.pt +3 -0
  48. run-16/checkpoint-1581/special_tokens_map.json +7 -0
  49. run-16/checkpoint-1581/tokenizer.json +0 -0
  50. run-16/checkpoint-1581/tokenizer_config.json +57 -0
logs/events.out.tfevents.1706213692.A-FVFFG2C4Q05P.18450.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62cc5bae5643e76f5fe7132152762e60f7c56f8a1f4dd8974ac1be3b8f3804b9
3
- size 4915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb62a9dd9f6430bc1eda0081efeb8aadd7c1c72a5da4ee45f1be86337d023dc
3
+ size 8149
logs/events.out.tfevents.1706219148.A-FVFFG2C4Q05P.18450.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffaf393c526a120288d3f5148beef1cc5b65198d4f7bce83170e04725b8816f
3
+ size 4916
logs/events.out.tfevents.1706220282.A-FVFFG2C4Q05P.18450.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb280db1879dc86e3d917f2544ce588ef981bcfbd8a4c39827399c9872e95dd
3
+ size 4915
logs/events.out.tfevents.1706225688.A-FVFFG2C4Q05P.18450.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14304845751cc508cd7826cfe49a1345788c5dfbb13f65869d8c976eea306d14
3
+ size 5396
logs/events.out.tfevents.1706235148.A-FVFFG2C4Q05P.18450.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50b65e51e0946b0e37e5f4f8cdcf2479100ce4dc9664a3d81723a1b52fc78f1
3
+ size 4916
logs/events.out.tfevents.1706238477.A-FVFFG2C4Q05P.18450.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248b91f61c18e4c8821676ed6fba1d03969f36ac6b8813731ca22ed8e32be6bb
3
+ size 6356
logs/events.out.tfevents.1706248274.A-FVFFG2C4Q05P.18450.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561be7125c6f8eab9f747bb3fe5cac3461393ae59dd2ce00308980f8966a0196
3
+ size 4915
logs/events.out.tfevents.1706249191.A-FVFFG2C4Q05P.18450.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e9193e605eef0fb5bd220ade658b78f062ba5fc8ea0e20ca53918eb38d1998
3
+ size 5396
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23893f7224a7bc69c792d25073f9d6a6b006ae31c0a78b378e8e817d49d4fafc
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7361cc641172e4d433d9122fa85e9b1eda716c64127b2b928ad93b520ec046
3
  size 17549312
run-11/checkpoint-1054/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-11/checkpoint-1054/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6a486e060246d3adb48bcaf435087c55b67c7ad776bb37ee9dac07cfc37448
3
+ size 17549312
run-11/checkpoint-1054/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb1d68212ad1095e55c03b80d1c02b1997fc76709ed40a67ed563aba54ea8b3
3
+ size 35122373
run-11/checkpoint-1054/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:260bdbb59b5e150f75450cd4e9defbf6deeda9a4e5690f5284bcc9395a60f0af
3
+ size 13617
run-11/checkpoint-1054/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0de76751247d87b58d90a1b730f62a7a21a6ee787542ae9cdac66f463930db
3
+ size 627
run-11/checkpoint-1054/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-11/checkpoint-1054/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-1054/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-11/checkpoint-1054/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8337155963302753,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/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
+ "learning_rate": 0.00010911592510991879,
14
+ "loss": 1.2248,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8130733944954128,
20
+ "eval_loss": 1.0815833806991577,
21
+ "eval_runtime": 19.1179,
22
+ "eval_samples_per_second": 45.612,
23
+ "eval_steps_per_second": 0.366,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 9.0929937591599e-05,
29
+ "loss": 0.6152,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8337155963302753,
35
+ "eval_loss": 1.116389513015747,
36
+ "eval_runtime": 6.3065,
37
+ "eval_samples_per_second": 138.271,
38
+ "eval_steps_per_second": 1.11,
39
+ "step": 1054
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 3689,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 7,
46
+ "save_steps": 500,
47
+ "total_flos": 16162868129520.0,
48
+ "train_batch_size": 128,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "alpha": 0.6271968482895725,
52
+ "learning_rate": 0.0001273019126282386,
53
+ "num_train_epochs": 7,
54
+ "temperature": 11
55
+ }
56
+ }
run-11/checkpoint-1054/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff57408053b19dbf32dbe4dd4af251a79a2c99bea6a376004e876c375e910b86
3
+ size 4283
run-11/checkpoint-1054/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-3689/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-11/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8693a63cbf06ce0d856ba6668fec281315b4d53102598dabade6f27926391b5
3
+ size 17549312
run-11/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0721eecf6bc93448597411fc82e51cac8198955d973c0e489f03a0155c35d5b1
3
+ size 35122373
run-11/checkpoint-3689/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1944a0f816099340e1dbf1a93e033a5a3a4bb0c92f096d7559d0edb8afc135de
3
+ size 13617
run-11/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b32bcfe0ed82d05530a69569db3776f28ee7f8cd9eab70ce1f1cb8da68b200
3
+ size 627
run-11/checkpoint-3689/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-11/checkpoint-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-3689/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-11/checkpoint-3689/trainer_state.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8337155963302753,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-1054",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3689,
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
+ "learning_rate": 0.00010911592510991879,
14
+ "loss": 1.2248,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8130733944954128,
20
+ "eval_loss": 1.0815833806991577,
21
+ "eval_runtime": 19.1179,
22
+ "eval_samples_per_second": 45.612,
23
+ "eval_steps_per_second": 0.366,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 9.0929937591599e-05,
29
+ "loss": 0.6152,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8337155963302753,
35
+ "eval_loss": 1.116389513015747,
36
+ "eval_runtime": 6.3065,
37
+ "eval_samples_per_second": 138.271,
38
+ "eval_steps_per_second": 1.11,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 7.27439500732792e-05,
44
+ "loss": 0.471,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.823394495412844,
50
+ "eval_loss": 1.144020438194275,
51
+ "eval_runtime": 6.8066,
52
+ "eval_samples_per_second": 128.11,
53
+ "eval_steps_per_second": 1.028,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 5.4557962554959397e-05,
59
+ "loss": 0.3957,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8325688073394495,
65
+ "eval_loss": 1.1239169836044312,
66
+ "eval_runtime": 7.0266,
67
+ "eval_samples_per_second": 124.099,
68
+ "eval_steps_per_second": 0.996,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 3.63719750366396e-05,
74
+ "loss": 0.3467,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8256880733944955,
80
+ "eval_loss": 1.1871780157089233,
81
+ "eval_runtime": 6.99,
82
+ "eval_samples_per_second": 124.75,
83
+ "eval_steps_per_second": 1.001,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 1.81859875183198e-05,
89
+ "loss": 0.3159,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8256880733944955,
95
+ "eval_loss": 1.179205060005188,
96
+ "eval_runtime": 6.8143,
97
+ "eval_samples_per_second": 127.965,
98
+ "eval_steps_per_second": 1.027,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 0.0,
104
+ "loss": 0.2938,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8222477064220184,
110
+ "eval_loss": 1.2032159566879272,
111
+ "eval_runtime": 6.2259,
112
+ "eval_samples_per_second": 140.06,
113
+ "eval_steps_per_second": 1.124,
114
+ "step": 3689
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 3689,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 7,
121
+ "save_steps": 500,
122
+ "total_flos": 56642674579560.0,
123
+ "train_batch_size": 128,
124
+ "trial_name": null,
125
+ "trial_params": {
126
+ "alpha": 0.6271968482895725,
127
+ "learning_rate": 0.0001273019126282386,
128
+ "num_train_epochs": 7,
129
+ "temperature": 11
130
+ }
131
+ }
run-11/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff57408053b19dbf32dbe4dd4af251a79a2c99bea6a376004e876c375e910b86
3
+ size 4283
run-11/checkpoint-3689/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-527/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-14/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5122f009507ce8a1c7246b2d43e68757db9ae2094fc10ddd7bc9a8e5badf6621
3
+ size 17549312
run-14/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a2d184c6cb5a14cdea02045a9cafa91b9427d19a434ae77a268f09df5f4c0bd
3
+ size 35122373
run-14/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f943a8d8f93fea7f44cad3b9bfb2d2b97d65b141eb704b9cba669cf42e776b14
3
+ size 13617
run-14/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9ac9373cf08f38d4a64ae49915a4b6948356b919e0ee772a5d4172bdb4988f
3
+ size 627
run-14/checkpoint-527/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-14/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-527/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-14/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8245412844036697,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/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
+ "learning_rate": 0.00019474702690730714,
14
+ "loss": 0.9795,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8245412844036697,
20
+ "eval_loss": 0.915910542011261,
21
+ "eval_runtime": 6.2219,
22
+ "eval_samples_per_second": 140.15,
23
+ "eval_steps_per_second": 1.125,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 4216,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 8,
31
+ "save_steps": 500,
32
+ "total_flos": 8069051778960.0,
33
+ "train_batch_size": 128,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "alpha": 0.6859594090871681,
37
+ "learning_rate": 0.00022256803075120817,
38
+ "num_train_epochs": 8,
39
+ "temperature": 29
40
+ }
41
+ }
run-14/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b052a21f86b780f6d7f1d08ff09c042d1d2839789de2a6f00d32705987721a5b
3
+ size 4283
run-14/checkpoint-527/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-1581/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-16/checkpoint-1581/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f54dcc3139e2bb9fb9042c8ad52729b9f2c4e16b49db76e3dd37bb50c807af3
3
+ size 17549312
run-16/checkpoint-1581/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0435e5ec8a4c4e90acd399141fc5707298fcb3b49ec17f76dc90f87ec1fd8a2
3
+ size 35122373
run-16/checkpoint-1581/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f1004ae2205b2fd82b8662eddc31a84c64c086e45e25c12d4a402a3d6a6e4d
3
+ size 13617
run-16/checkpoint-1581/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceaf0c478b858de5bd3b20cc01e01e1ee9146ac6e467d4a79f2247d045da12a2
3
+ size 627
run-16/checkpoint-1581/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-16/checkpoint-1581/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-1581/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }