Hugging Face's logo

inflaton
/
cs605-nlp-assignment-2-bert-large-uncased-v2

Multiple Choice
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
inflaton commited on
Commit
e2d803d
•
1 Parent(s): ec77f25

Training in progress, step 3500

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-19/checkpoint-1000/config.json +26 -0
  3. run-19/checkpoint-1000/model.safetensors +3 -0
  4. run-19/checkpoint-1000/optimizer.pt +3 -0
  5. run-19/checkpoint-1000/rng_state.pth +3 -0
  6. run-19/checkpoint-1000/scheduler.pt +3 -0
  7. run-19/checkpoint-1000/special_tokens_map.json +7 -0
  8. run-19/checkpoint-1000/tokenizer.json +0 -0
  9. run-19/checkpoint-1000/tokenizer_config.json +55 -0
  10. run-19/checkpoint-1000/trainer_state.json +47 -0
  11. run-19/checkpoint-1000/training_args.bin +3 -0
  12. run-19/checkpoint-1000/vocab.txt +0 -0
  13. run-19/checkpoint-1500/config.json +26 -0
  14. run-19/checkpoint-1500/model.safetensors +3 -0
  15. run-19/checkpoint-1500/optimizer.pt +3 -0
  16. run-19/checkpoint-1500/rng_state.pth +3 -0
  17. run-19/checkpoint-1500/scheduler.pt +3 -0
  18. run-19/checkpoint-1500/special_tokens_map.json +7 -0
  19. run-19/checkpoint-1500/tokenizer.json +0 -0
  20. run-19/checkpoint-1500/tokenizer_config.json +55 -0
  21. run-19/checkpoint-1500/trainer_state.json +63 -0
  22. run-19/checkpoint-1500/training_args.bin +3 -0
  23. run-19/checkpoint-1500/vocab.txt +0 -0
  24. run-19/checkpoint-2000/config.json +26 -0
  25. run-19/checkpoint-2000/model.safetensors +3 -0
  26. run-19/checkpoint-2000/optimizer.pt +3 -0
  27. run-19/checkpoint-2000/rng_state.pth +3 -0
  28. run-19/checkpoint-2000/scheduler.pt +3 -0
  29. run-19/checkpoint-2000/special_tokens_map.json +7 -0
  30. run-19/checkpoint-2000/tokenizer.json +0 -0
  31. run-19/checkpoint-2000/tokenizer_config.json +55 -0
  32. run-19/checkpoint-2000/trainer_state.json +70 -0
  33. run-19/checkpoint-2000/training_args.bin +3 -0
  34. run-19/checkpoint-2000/vocab.txt +0 -0
  35. run-19/checkpoint-2500/config.json +26 -0
  36. run-19/checkpoint-2500/model.safetensors +3 -0
  37. run-19/checkpoint-2500/optimizer.pt +3 -0
  38. run-19/checkpoint-2500/rng_state.pth +3 -0
  39. run-19/checkpoint-2500/scheduler.pt +3 -0
  40. run-19/checkpoint-2500/special_tokens_map.json +7 -0
  41. run-19/checkpoint-2500/tokenizer.json +0 -0
  42. run-19/checkpoint-2500/tokenizer_config.json +55 -0
  43. run-19/checkpoint-2500/trainer_state.json +86 -0
  44. run-19/checkpoint-2500/training_args.bin +3 -0
  45. run-19/checkpoint-2500/vocab.txt +0 -0
  46. run-19/checkpoint-3000/config.json +26 -0
  47. run-19/checkpoint-3000/model.safetensors +3 -0
  48. run-19/checkpoint-3000/optimizer.pt +3 -0
  49. run-19/checkpoint-3000/rng_state.pth +3 -0
  50. run-19/checkpoint-3000/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c29f28a26440785cc17c0c69e2005ae8d1919923d00137ce7e693b29124494df
3
  size 1340618660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72209b9df4502711fb0a9fb259fc535f893260274e7ba5e9ba48218f87827596
3
  size 1340618660
run-19/checkpoint-1000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-19/checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d5c142a9b88ab788e5ec3a0716a2f5323fec7fe191c143bed68428482d15cf
3
+ size 1340618660
run-19/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:538e67a31f8a4f275f4f4e2f38dc7723d79e06aad221213ab38d764ca90db647
3
+ size 2681472237
run-19/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1a256d949d074cb5d76270949caf88a9f9cee6049fc1f352d070a28cfba690
3
+ size 14244
run-19/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7298461e471d6d1e12aa5ac2d47224349ed147c47a4dc903d2d5ade3388d684
3
+ size 1064
run-19/checkpoint-1000/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-19/checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-19/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3404825737265416,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6702412868632708,
13
+ "grad_norm": 12.96187973022461,
14
+ "learning_rate": 5.852478627669732e-06,
15
+ "loss": 0.5779,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7619845867156982,
21
+ "eval_loss": 0.48268476128578186,
22
+ "eval_runtime": 9.469,
23
+ "eval_samples_per_second": 315.027,
24
+ "eval_steps_per_second": 19.749,
25
+ "step": 746
26
+ },
27
+ {
28
+ "epoch": 1.3404825737265416,
29
+ "grad_norm": 19.64900779724121,
30
+ "learning_rate": 5.432041944647482e-06,
31
+ "loss": 0.464,
32
+ "step": 1000
33
+ }
34
+ ],
35
+ "logging_steps": 500,
36
+ "max_steps": 7460,
37
+ "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 10,
39
+ "save_steps": 500,
40
+ "total_flos": 3237110898676416.0,
41
+ "train_batch_size": 16,
42
+ "trial_name": null,
43
+ "trial_params": {
44
+ "learning_rate": 6.272915310691983e-06,
45
+ "per_device_train_batch_size": 16
46
+ }
47
+ }
run-19/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
3
+ size 5048
run-19/checkpoint-1000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-1500/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-19/checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba2cd9ea7d2e75041af45a4b08984800df5f7cfe46ffe27f6f106a6a58c4549
3
+ size 1340618660
run-19/checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2bb1e5b6461c00c564f9eae64df7fa51fc8b2d0dde47531b14874f74540d42
3
+ size 2681472237
run-19/checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6c109e0b81728091fd53d38fe23ff184b43ac15b141962e34b108757cda4da
3
+ size 14244
run-19/checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11ab39e9c13a3955bc1f74d16f1908727992a8ebcd5569d78e27e46594818bd2
3
+ size 1064
run-19/checkpoint-1500/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-19/checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-19/checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0107238605898123,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6702412868632708,
13
+ "grad_norm": 12.96187973022461,
14
+ "learning_rate": 5.852478627669732e-06,
15
+ "loss": 0.5779,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7619845867156982,
21
+ "eval_loss": 0.48268476128578186,
22
+ "eval_runtime": 9.469,
23
+ "eval_samples_per_second": 315.027,
24
+ "eval_steps_per_second": 19.749,
25
+ "step": 746
26
+ },
27
+ {
28
+ "epoch": 1.3404825737265416,
29
+ "grad_norm": 19.64900779724121,
30
+ "learning_rate": 5.432041944647482e-06,
31
+ "loss": 0.464,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7680187821388245,
37
+ "eval_loss": 0.5030698180198669,
38
+ "eval_runtime": 9.5015,
39
+ "eval_samples_per_second": 313.951,
40
+ "eval_steps_per_second": 19.681,
41
+ "step": 1492
42
+ },
43
+ {
44
+ "epoch": 2.0107238605898123,
45
+ "grad_norm": 9.11796760559082,
46
+ "learning_rate": 5.0116052616252305e-06,
47
+ "loss": 0.4025,
48
+ "step": 1500
49
+ }
50
+ ],
51
+ "logging_steps": 500,
52
+ "max_steps": 7460,
53
+ "num_input_tokens_seen": 0,
54
+ "num_train_epochs": 10,
55
+ "save_steps": 500,
56
+ "total_flos": 4548890869239276.0,
57
+ "train_batch_size": 16,
58
+ "trial_name": null,
59
+ "trial_params": {
60
+ "learning_rate": 6.272915310691983e-06,
61
+ "per_device_train_batch_size": 16
62
+ }
63
+ }
run-19/checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
3
+ size 5048
run-19/checkpoint-1500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-2000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-19/checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca885030d990592145e230f366c913fcb92e22e6a0c94a859117567f6b13e64e
3
+ size 1340618660
run-19/checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77eb133f526ae01eb3a937bfcd8ebc44b6e76f7904676d8bb342a396f43bcd48
3
+ size 2681472237
run-19/checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58a3d1eb6b21b20dd7b0d4230faa8548ab3124fbf5bb32e938d1276eb9a4c73
3
+ size 14244
run-19/checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0fa54d9d10f8e153bcc0c86c326474c2406a2147c0cf972cf1024a939ba069
3
+ size 1064
run-19/checkpoint-2000/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-19/checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-19/checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.680965147453083,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6702412868632708,
13
+ "grad_norm": 12.96187973022461,
14
+ "learning_rate": 5.852478627669732e-06,
15
+ "loss": 0.5779,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7619845867156982,
21
+ "eval_loss": 0.48268476128578186,
22
+ "eval_runtime": 9.469,
23
+ "eval_samples_per_second": 315.027,
24
+ "eval_steps_per_second": 19.749,
25
+ "step": 746
26
+ },
27
+ {
28
+ "epoch": 1.3404825737265416,
29
+ "grad_norm": 19.64900779724121,
30
+ "learning_rate": 5.432041944647482e-06,
31
+ "loss": 0.464,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7680187821388245,
37
+ "eval_loss": 0.5030698180198669,
38
+ "eval_runtime": 9.5015,
39
+ "eval_samples_per_second": 313.951,
40
+ "eval_steps_per_second": 19.681,
41
+ "step": 1492
42
+ },
43
+ {
44
+ "epoch": 2.0107238605898123,
45
+ "grad_norm": 9.11796760559082,
46
+ "learning_rate": 5.0116052616252305e-06,
47
+ "loss": 0.4025,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 2.680965147453083,
52
+ "grad_norm": 11.002016067504883,
53
+ "learning_rate": 4.59116857860298e-06,
54
+ "loss": 0.2688,
55
+ "step": 2000
56
+ }
57
+ ],
58
+ "logging_steps": 500,
59
+ "max_steps": 7460,
60
+ "num_input_tokens_seen": 0,
61
+ "num_train_epochs": 10,
62
+ "save_steps": 500,
63
+ "total_flos": 5845028279107500.0,
64
+ "train_batch_size": 16,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "learning_rate": 6.272915310691983e-06,
68
+ "per_device_train_batch_size": 16
69
+ }
70
+ }
run-19/checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
3
+ size 5048
run-19/checkpoint-2000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-2500/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-19/checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b143d3974d05f85c839353f2004a6b74bea13ef51d61998bb59e60ce1a1000
3
+ size 1340618660
run-19/checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5232eb8c676c8ec6f25ba3d10bbc962f63e34e54fcc8e82c8fc594ac21f24753
3
+ size 2681472237
run-19/checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c60cac06bde3137dc5e45389d38d5cf66579dc186b1bafb1402f6e093666502
3
+ size 14244
run-19/checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3616251a0cbcf74f10deea530e9410077e3acab7d2d2a1cbbcec03f131fb2e
3
+ size 1064
run-19/checkpoint-2500/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-19/checkpoint-2500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-2500/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-19/checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.351206434316354,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6702412868632708,
13
+ "grad_norm": 12.96187973022461,
14
+ "learning_rate": 5.852478627669732e-06,
15
+ "loss": 0.5779,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7619845867156982,
21
+ "eval_loss": 0.48268476128578186,
22
+ "eval_runtime": 9.469,
23
+ "eval_samples_per_second": 315.027,
24
+ "eval_steps_per_second": 19.749,
25
+ "step": 746
26
+ },
27
+ {
28
+ "epoch": 1.3404825737265416,
29
+ "grad_norm": 19.64900779724121,
30
+ "learning_rate": 5.432041944647482e-06,
31
+ "loss": 0.464,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7680187821388245,
37
+ "eval_loss": 0.5030698180198669,
38
+ "eval_runtime": 9.5015,
39
+ "eval_samples_per_second": 313.951,
40
+ "eval_steps_per_second": 19.681,
41
+ "step": 1492
42
+ },
43
+ {
44
+ "epoch": 2.0107238605898123,
45
+ "grad_norm": 9.11796760559082,
46
+ "learning_rate": 5.0116052616252305e-06,
47
+ "loss": 0.4025,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 2.680965147453083,
52
+ "grad_norm": 11.002016067504883,
53
+ "learning_rate": 4.59116857860298e-06,
54
+ "loss": 0.2688,
55
+ "step": 2000
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_accuracy": 0.7747234106063843,
60
+ "eval_loss": 0.5899690389633179,
61
+ "eval_runtime": 9.4806,
62
+ "eval_samples_per_second": 314.643,
63
+ "eval_steps_per_second": 19.725,
64
+ "step": 2238
65
+ },
66
+ {
67
+ "epoch": 3.351206434316354,
68
+ "grad_norm": 3.2045211791992188,
69
+ "learning_rate": 4.170731895580729e-06,
70
+ "loss": 0.2182,
71
+ "step": 2500
72
+ }
73
+ ],
74
+ "logging_steps": 500,
75
+ "max_steps": 7460,
76
+ "num_input_tokens_seen": 0,
77
+ "num_train_epochs": 10,
78
+ "save_steps": 500,
79
+ "total_flos": 7151780933794332.0,
80
+ "train_batch_size": 16,
81
+ "trial_name": null,
82
+ "trial_params": {
83
+ "learning_rate": 6.272915310691983e-06,
84
+ "per_device_train_batch_size": 16
85
+ }
86
+ }
run-19/checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
3
+ size 5048
run-19/checkpoint-2500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-3000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-19/checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e0f887c54279934a0e0a7efaecab9fdb886b30b6a762088de1f7364e35193d
3
+ size 1340618660
run-19/checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b40fa93bedd51e9f04f1febba3637f2aaea4cfccf812e089ab9a933823a41ec
3
+ size 2681472237
run-19/checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac0fde3555dccd9e3c85c24a58ef16005dcfc5730b52d8c9c3e5f7feba7cc67
3
+ size 14244
run-19/checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78b1020363667e6802c00754b27318f6ac4d31f357b2d08133244a2090eca976
3
+ size 1064