Hugging Face's logo

EmreAkgul
/
best-model-cls-token

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
EmreAkgul commited on
Commit
80170b1
·
verified ·
1 Parent(s): 209310d

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-14/checkpoint-39/config.json +24 -0
  3. run-14/checkpoint-39/model.safetensors +3 -0
  4. run-14/checkpoint-39/optimizer.pt +3 -0
  5. run-14/checkpoint-39/rng_state.pth +3 -0
  6. run-14/checkpoint-39/scheduler.pt +3 -0
  7. run-14/checkpoint-39/special_tokens_map.json +7 -0
  8. run-14/checkpoint-39/tokenizer.json +0 -0
  9. run-14/checkpoint-39/tokenizer_config.json +56 -0
  10. run-14/checkpoint-39/trainer_state.json +50 -0
  11. run-14/checkpoint-39/training_args.bin +3 -0
  12. run-14/checkpoint-39/vocab.txt +0 -0
  13. run-7/checkpoint-78/config.json +24 -0
  14. run-7/checkpoint-78/model.safetensors +3 -0
  15. run-7/checkpoint-78/optimizer.pt +3 -0
  16. run-7/checkpoint-78/rng_state.pth +3 -0
  17. run-7/checkpoint-78/scheduler.pt +3 -0
  18. run-7/checkpoint-78/special_tokens_map.json +7 -0
  19. run-7/checkpoint-78/tokenizer.json +0 -0
  20. run-7/checkpoint-78/tokenizer_config.json +56 -0
  21. run-7/checkpoint-78/trainer_state.json +59 -0
  22. run-7/checkpoint-78/training_args.bin +3 -0
  23. run-7/checkpoint-78/vocab.txt +0 -0
  24. run-9/checkpoint-39/config.json +24 -0
  25. run-9/checkpoint-39/model.safetensors +3 -0
  26. run-9/checkpoint-39/optimizer.pt +3 -0
  27. run-9/checkpoint-39/rng_state.pth +3 -0
  28. run-9/checkpoint-39/scheduler.pt +3 -0
  29. run-9/checkpoint-39/special_tokens_map.json +7 -0
  30. run-9/checkpoint-39/tokenizer.json +0 -0
  31. run-9/checkpoint-39/tokenizer_config.json +56 -0
  32. run-9/checkpoint-39/trainer_state.json +50 -0
  33. run-9/checkpoint-39/training_args.bin +3 -0
  34. run-9/checkpoint-39/vocab.txt +0 -0
  35. run-9/checkpoint-78/config.json +24 -0
  36. run-9/checkpoint-78/model.safetensors +3 -0
  37. run-9/checkpoint-78/optimizer.pt +3 -0
  38. run-9/checkpoint-78/rng_state.pth +3 -0
  39. run-9/checkpoint-78/scheduler.pt +3 -0
  40. run-9/checkpoint-78/special_tokens_map.json +7 -0
  41. run-9/checkpoint-78/tokenizer.json +0 -0
  42. run-9/checkpoint-78/tokenizer_config.json +56 -0
  43. run-9/checkpoint-78/trainer_state.json +59 -0
  44. run-9/checkpoint-78/training_args.bin +3 -0
  45. run-9/checkpoint-78/vocab.txt +0 -0
  46. runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744550804.328f3c59ed9c.174.18 +3 -0
  47. runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744550848.328f3c59ed9c.174.19 +3 -0
  48. runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744551048.328f3c59ed9c.174.20 +3 -0
  49. runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744551094.328f3c59ed9c.174.21 +3 -0
  50. runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744551138.328f3c59ed9c.174.22 +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:357033e4513f631cda7baab36f6603a1f6960338e1b47c695cb5414e3170b7e7
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241ef8da471fb80623dcdb3856d66bf30562de8db05eb5a4d49671d305f4f620
3
  size 267832560
run-14/checkpoint-39/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "distilbert",
13
+ "n_heads": 12,
14
+ "n_layers": 6,
15
+ "pad_token_id": 0,
16
+ "problem_type": "single_label_classification",
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.3",
23
+ "vocab_size": 30522
24
+ }
run-14/checkpoint-39/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241ef8da471fb80623dcdb3856d66bf30562de8db05eb5a4d49671d305f4f620
3
+ size 267832560
run-14/checkpoint-39/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c0eda7ed0b38dc4135fc9dfc9e92830c5aeb03ca1f2238b03290c81b129383a
3
+ size 535727290
run-14/checkpoint-39/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec26492c01f8533e964548678a9125c8479f466e501c830c64a60759451765d
3
+ size 14244
run-14/checkpoint-39/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4eaf56c63b91f9696b5b0bcd061ce33b73232f24f89be31808de8c403d7d4a
3
+ size 1064
run-14/checkpoint-39/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-39/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-39/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-14/checkpoint-39/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5667870036101083,
4
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-rte-run_3/run-14/checkpoint-39",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 39,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.5667870036101083,
15
+ "eval_loss": 0.6876252889633179,
16
+ "eval_runtime": 1.7048,
17
+ "eval_samples_per_second": 162.48,
18
+ "eval_steps_per_second": 2.933,
19
+ "step": 39
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 234,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 6,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 64,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "dropout_rate": 0.3994557877518572,
44
+ "learning_rate": 2.1686743677849786e-05,
45
+ "num_train_epochs": 6,
46
+ "per_device_train_batch_size": 64,
47
+ "warmup_steps": 43,
48
+ "weight_decay": 0.03886015775146907
49
+ }
50
+ }
run-14/checkpoint-39/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cf3e2688a47066a6179d8c03b9819776b74f37d7be7c152adb78bb2ef5fc54
3
+ size 5432
run-14/checkpoint-39/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-78/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "distilbert",
13
+ "n_heads": 12,
14
+ "n_layers": 6,
15
+ "pad_token_id": 0,
16
+ "problem_type": "single_label_classification",
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.3",
23
+ "vocab_size": 30522
24
+ }
run-7/checkpoint-78/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2616d9618b0435e5932cc462ae643d3bb774107c8aa99677c139f30fbd9e6b
3
+ size 267832560
run-7/checkpoint-78/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724d7a6e8d56becf5f4614ca49fdb4cd9d133dd47bd9d74cbc35f7db612fd7f4
3
+ size 535727290
run-7/checkpoint-78/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867b92593652105b5f08fe70d622012e55758c900eaf343351c736e7b1b4f3b7
3
+ size 14244
run-7/checkpoint-78/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de8c88fd3da805a3c3b535c02c4ff780dcebea00a6d2cbb882da54672e86704
3
+ size 1064
run-7/checkpoint-78/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-7/checkpoint-78/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-78/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-7/checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5667870036101083,
4
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-rte-run_3/run-7/checkpoint-39",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 78,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.5667870036101083,
15
+ "eval_loss": 0.68735671043396,
16
+ "eval_runtime": 1.6956,
17
+ "eval_samples_per_second": 163.366,
18
+ "eval_steps_per_second": 2.949,
19
+ "step": 39
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5415162454873647,
24
+ "eval_loss": 0.6868671178817749,
25
+ "eval_runtime": 1.7633,
26
+ "eval_samples_per_second": 157.089,
27
+ "eval_steps_per_second": 2.836,
28
+ "step": 78
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 234,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 6,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": false
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 0,
49
+ "train_batch_size": 64,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "dropout_rate": 0.486027646322682,
53
+ "learning_rate": 3.0317715843725247e-05,
54
+ "num_train_epochs": 6,
55
+ "per_device_train_batch_size": 64,
56
+ "warmup_steps": 54,
57
+ "weight_decay": 0.05725924593559384
58
+ }
59
+ }
run-7/checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e67d1595f4374923ffd44d9ebd27f5c37a33918ad57c8a7b0279cdefac2bb25
3
+ size 5432
run-7/checkpoint-78/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-39/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "distilbert",
13
+ "n_heads": 12,
14
+ "n_layers": 6,
15
+ "pad_token_id": 0,
16
+ "problem_type": "single_label_classification",
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.3",
23
+ "vocab_size": 30522
24
+ }
run-9/checkpoint-39/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3e19d7cf37a47fd314b6ba12992c5ab23fd977139bc29dd13c5d769d830804b
3
+ size 267832560
run-9/checkpoint-39/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:912b7cb9c4633944e6a2407bfeaeb33935a8a46207f8176b68f16218a898c30e
3
+ size 535727290
run-9/checkpoint-39/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec26492c01f8533e964548678a9125c8479f466e501c830c64a60759451765d
3
+ size 14244
run-9/checkpoint-39/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c6d7dce42212b60c6b8e4226740b984d251651de1483f4e69f21da1cb2a03f
3
+ size 1064
run-9/checkpoint-39/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-9/checkpoint-39/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-39/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-9/checkpoint-39/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5631768953068592,
4
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-rte-run_3/run-9/checkpoint-39",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 39,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.5631768953068592,
15
+ "eval_loss": 0.6878404021263123,
16
+ "eval_runtime": 1.7195,
17
+ "eval_samples_per_second": 161.098,
18
+ "eval_steps_per_second": 2.908,
19
+ "step": 39
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 156,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 4,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 64,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "dropout_rate": 0.15335993564953984,
44
+ "learning_rate": 3.8464176314997903e-05,
45
+ "num_train_epochs": 4,
46
+ "per_device_train_batch_size": 64,
47
+ "warmup_steps": 83,
48
+ "weight_decay": 0.053701794143885775
49
+ }
50
+ }
run-9/checkpoint-39/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8170728cb7bf0227594a4ad811e4ddfb952c8ac28fac1775b22e49efb87c2d6d
3
+ size 5432
run-9/checkpoint-39/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-78/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "distilbert",
13
+ "n_heads": 12,
14
+ "n_layers": 6,
15
+ "pad_token_id": 0,
16
+ "problem_type": "single_label_classification",
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.3",
23
+ "vocab_size": 30522
24
+ }
run-9/checkpoint-78/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1b1b6b1a936ce308740678012d49ba5273f72ebce1c724458bd547a005b748
3
+ size 267832560
run-9/checkpoint-78/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f62dc262b685e9ad289b5cabffc0167e173d68b1357cd4e23d80e3301eec04
3
+ size 535727290
run-9/checkpoint-78/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867b92593652105b5f08fe70d622012e55758c900eaf343351c736e7b1b4f3b7
3
+ size 14244
run-9/checkpoint-78/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65c8d71a9ad78f954b64e4973dbe9ac0f91c97c1fd8bf81d454fdf8a71c5e5f1
3
+ size 1064
run-9/checkpoint-78/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-9/checkpoint-78/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-78/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-9/checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5631768953068592,
4
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-rte-run_3/run-9/checkpoint-39",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 78,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.5631768953068592,
15
+ "eval_loss": 0.6878404021263123,
16
+ "eval_runtime": 1.7195,
17
+ "eval_samples_per_second": 161.098,
18
+ "eval_steps_per_second": 2.908,
19
+ "step": 39
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5451263537906137,
24
+ "eval_loss": 0.698254406452179,
25
+ "eval_runtime": 1.6991,
26
+ "eval_samples_per_second": 163.023,
27
+ "eval_steps_per_second": 2.943,
28
+ "step": 78
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 156,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 4,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": false
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 0,
49
+ "train_batch_size": 64,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "dropout_rate": 0.15335993564953984,
53
+ "learning_rate": 3.8464176314997903e-05,
54
+ "num_train_epochs": 4,
55
+ "per_device_train_batch_size": 64,
56
+ "warmup_steps": 83,
57
+ "weight_decay": 0.053701794143885775
58
+ }
59
+ }
run-9/checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8170728cb7bf0227594a4ad811e4ddfb952c8ac28fac1775b22e49efb87c2d6d
3
+ size 5432
run-9/checkpoint-78/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744550804.328f3c59ed9c.174.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:263f6b1fc6509e3200abf334b0896379f5176741ade6c267f461e3aadb26aeb4
3
+ size 5335
runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744550848.328f3c59ed9c.174.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c3237a246a9836ea0d3413a831865a490a753a4a6f71a7b94a7e671f4eec7c7
3
+ size 5964
runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744551048.328f3c59ed9c.174.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727e69cc573980f1da24087c730b37839ef14cd40316180014f49b3c8e548d1a
3
+ size 5332
runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744551094.328f3c59ed9c.174.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d063b6fc5ba1957239365530c2427cc15a775a438598d6d1823346206cd09c
3
+ size 5330
runs/Apr13_12-17-18_328f3c59ed9c/events.out.tfevents.1744551138.328f3c59ed9c.174.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60eabc98b3f27025c8fe3fb8a4ef253176bbb82c8f82ffb5d9a64dd8765bb432
3
+ size 5329