Doowon96 commited on
Commit
fae9e6c
1 Parent(s): 250970b

Training in progress, epoch 3

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-2/checkpoint-1142/config.json +44 -0
  3. run-2/checkpoint-1142/model.safetensors +3 -0
  4. run-2/checkpoint-1142/optimizer.pt +3 -0
  5. run-2/checkpoint-1142/rng_state.pth +3 -0
  6. run-2/checkpoint-1142/scheduler.pt +3 -0
  7. run-2/checkpoint-1142/special_tokens_map.json +37 -0
  8. run-2/checkpoint-1142/tokenizer.json +0 -0
  9. run-2/checkpoint-1142/tokenizer_config.json +57 -0
  10. run-2/checkpoint-1142/trainer_state.json +56 -0
  11. run-2/checkpoint-1142/training_args.bin +3 -0
  12. run-2/checkpoint-1142/vocab.txt +0 -0
  13. run-2/checkpoint-571/config.json +44 -0
  14. run-2/checkpoint-571/model.safetensors +3 -0
  15. run-2/checkpoint-571/optimizer.pt +3 -0
  16. run-2/checkpoint-571/rng_state.pth +3 -0
  17. run-2/checkpoint-571/scheduler.pt +3 -0
  18. run-2/checkpoint-571/special_tokens_map.json +37 -0
  19. run-2/checkpoint-571/tokenizer.json +0 -0
  20. run-2/checkpoint-571/tokenizer_config.json +57 -0
  21. run-2/checkpoint-571/trainer_state.json +41 -0
  22. run-2/checkpoint-571/training_args.bin +3 -0
  23. run-2/checkpoint-571/vocab.txt +0 -0
  24. run-3/checkpoint-1142/config.json +44 -0
  25. run-3/checkpoint-1142/model.safetensors +3 -0
  26. run-3/checkpoint-1142/optimizer.pt +3 -0
  27. run-3/checkpoint-1142/rng_state.pth +3 -0
  28. run-3/checkpoint-1142/scheduler.pt +3 -0
  29. run-3/checkpoint-1142/special_tokens_map.json +37 -0
  30. run-3/checkpoint-1142/tokenizer.json +0 -0
  31. run-3/checkpoint-1142/tokenizer_config.json +57 -0
  32. run-3/checkpoint-1142/trainer_state.json +56 -0
  33. run-3/checkpoint-1142/training_args.bin +3 -0
  34. run-3/checkpoint-1142/vocab.txt +0 -0
  35. run-3/checkpoint-1713/config.json +44 -0
  36. run-3/checkpoint-1713/model.safetensors +3 -0
  37. run-3/checkpoint-1713/optimizer.pt +3 -0
  38. run-3/checkpoint-1713/rng_state.pth +3 -0
  39. run-3/checkpoint-1713/scheduler.pt +3 -0
  40. run-3/checkpoint-1713/special_tokens_map.json +37 -0
  41. run-3/checkpoint-1713/tokenizer.json +0 -0
  42. run-3/checkpoint-1713/tokenizer_config.json +57 -0
  43. run-3/checkpoint-1713/trainer_state.json +71 -0
  44. run-3/checkpoint-1713/training_args.bin +3 -0
  45. run-3/checkpoint-1713/vocab.txt +0 -0
  46. run-3/checkpoint-571/config.json +44 -0
  47. run-3/checkpoint-571/model.safetensors +3 -0
  48. run-3/checkpoint-571/optimizer.pt +3 -0
  49. run-3/checkpoint-571/rng_state.pth +3 -0
  50. run-3/checkpoint-571/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:351f953c787e3fb330b87341e1a1621362d3c65f828cd992c17fedf551acbed0
3
  size 442514444
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657ad1b06454c7cf66877f8c0d4d1e55bb4628687c9af4fd677930785a2cd0c5
3
  size 442514444
run-2/checkpoint-1142/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/bert-base",
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": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.36.2",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 32000
44
+ }
run-2/checkpoint-1142/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f640c88a1a2b551508c54d8fd13df0c731545d84133e6a193cc4bebc8b4c73
3
+ size 442514444
run-2/checkpoint-1142/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:334bee1d142e3e705a9e55a5e803ca015602065ee06c31b483533bbeeeb59602
3
+ size 885149946
run-2/checkpoint-1142/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392a40edf894cdbb4dc2f873232ccfdc00723724a29750a025312040faf941d2
3
+ size 14244
run-2/checkpoint-1142/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c00d630a77b336f2b3cb4e6c6db6819c212053dae593d8032bd2098ebadf826
3
+ size 1064
run-2/checkpoint-1142/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-2/checkpoint-1142/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-1142/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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": false,
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-2/checkpoint-1142/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8438106937309019,
3
+ "best_model_checkpoint": "test-klue/ynat-hps/run-2/checkpoint-1142",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1142,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.88,
13
+ "learning_rate": 3.969337129256189e-05,
14
+ "loss": 0.6457,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_f1": 0.8110665638206435,
20
+ "eval_loss": 0.6358334422111511,
21
+ "eval_runtime": 12.2409,
22
+ "eval_samples_per_second": 743.983,
23
+ "eval_steps_per_second": 2.941,
24
+ "step": 571
25
+ },
26
+ {
27
+ "epoch": 1.75,
28
+ "learning_rate": 8.779530722030823e-06,
29
+ "loss": 0.3347,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_f1": 0.8438106937309019,
35
+ "eval_loss": 0.615491509437561,
36
+ "eval_runtime": 12.3816,
37
+ "eval_samples_per_second": 735.528,
38
+ "eval_steps_per_second": 2.908,
39
+ "step": 1142
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1142,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 2,
46
+ "save_steps": 500,
47
+ "total_flos": 81304965964800.0,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 7.060721186309296e-05,
52
+ "num_train_epochs": 2,
53
+ "per_device_train_batch_size": 8,
54
+ "seed": 23
55
+ }
56
+ }
run-2/checkpoint-1142/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef8926caa6b810e5960c2aed353133aafe2da374956d2bab8b46eb545884bd7
3
+ size 4728
run-2/checkpoint-1142/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-571/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/bert-base",
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": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.36.2",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 32000
44
+ }
run-2/checkpoint-571/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351f953c787e3fb330b87341e1a1621362d3c65f828cd992c17fedf551acbed0
3
+ size 442514444
run-2/checkpoint-571/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55deeebd85491dea736e30974394b8f2cf4758ddc344a3bd31d73e5fd66da3ee
3
+ size 885149946
run-2/checkpoint-571/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00edf36574b1f8322deb613878f137832ada74e411f85d2fb78251aa5f6efbae
3
+ size 14244
run-2/checkpoint-571/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b12c41255e0d24d38f2f7814263220ba011f6098c473538806ae6a9b9a9117e
3
+ size 1064
run-2/checkpoint-571/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-2/checkpoint-571/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-571/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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": false,
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-2/checkpoint-571/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8110665638206435,
3
+ "best_model_checkpoint": "test-klue/ynat-hps/run-2/checkpoint-571",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 571,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.88,
13
+ "learning_rate": 3.969337129256189e-05,
14
+ "loss": 0.6457,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_f1": 0.8110665638206435,
20
+ "eval_loss": 0.6358334422111511,
21
+ "eval_runtime": 12.2409,
22
+ "eval_samples_per_second": 743.983,
23
+ "eval_steps_per_second": 2.941,
24
+ "step": 571
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 1142,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 2,
31
+ "save_steps": 500,
32
+ "total_flos": 40747042762800.0,
33
+ "train_batch_size": 8,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "learning_rate": 7.060721186309296e-05,
37
+ "num_train_epochs": 2,
38
+ "per_device_train_batch_size": 8,
39
+ "seed": 23
40
+ }
41
+ }
run-2/checkpoint-571/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef8926caa6b810e5960c2aed353133aafe2da374956d2bab8b46eb545884bd7
3
+ size 4728
run-2/checkpoint-571/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1142/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/bert-base",
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": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.36.2",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 32000
44
+ }
run-3/checkpoint-1142/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:105ad63d58707a509c4c5855473b56f015a28bdf462c21640745bf2590457fd4
3
+ size 442514444
run-3/checkpoint-1142/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac15ac9aee16c080a58539992376314dd8cc04aa914a6de644d93180656970c6
3
+ size 885149946
run-3/checkpoint-1142/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f268df61038f9d6454a4f7991438f9dae178fac6752f933d281924440c4261d
3
+ size 14244
run-3/checkpoint-1142/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a640af7dc5c8281913795ec5471aa2317c0a1d2662d3869d3dfee32b8f1da7
3
+ size 1064
run-3/checkpoint-1142/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-3/checkpoint-1142/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1142/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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": false,
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-3/checkpoint-1142/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8504556783745718,
3
+ "best_model_checkpoint": "test-klue/ynat-hps/run-3/checkpoint-1142",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1142,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.88,
13
+ "learning_rate": 1.0665865551075277e-05,
14
+ "loss": 0.6897,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_f1": 0.8405267782311162,
20
+ "eval_loss": 0.5007498860359192,
21
+ "eval_runtime": 12.2145,
22
+ "eval_samples_per_second": 745.59,
23
+ "eval_steps_per_second": 2.947,
24
+ "step": 571
25
+ },
26
+ {
27
+ "epoch": 1.75,
28
+ "learning_rate": 7.676553457164043e-06,
29
+ "loss": 0.3368,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_f1": 0.8504556783745718,
35
+ "eval_loss": 0.5121398568153381,
36
+ "eval_runtime": 12.4319,
37
+ "eval_samples_per_second": 732.553,
38
+ "eval_steps_per_second": 2.896,
39
+ "step": 1142
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 2284,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 4,
46
+ "save_steps": 500,
47
+ "total_flos": 81317299849200.0,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 1.3655177644986507e-05,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 8,
54
+ "seed": 30
55
+ }
56
+ }
run-3/checkpoint-1142/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a614592c80a4a414de05cd99fe99271561717829d2d0ccd2753babdf84eaf93f
3
+ size 4728
run-3/checkpoint-1142/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1713/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/bert-base",
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": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.36.2",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 32000
44
+ }
run-3/checkpoint-1713/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657ad1b06454c7cf66877f8c0d4d1e55bb4628687c9af4fd677930785a2cd0c5
3
+ size 442514444
run-3/checkpoint-1713/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49add4284ac8e72f6c79de6d859255707e3fd9d5ab090f977ea3ee4923a5e92d
3
+ size 885149946
run-3/checkpoint-1713/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79bf805cd72fede2b0319e160c158c100c6e1b6a0d7b8faba01df2c8978d863b
3
+ size 14244
run-3/checkpoint-1713/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c47f0e41597ff2391b9022a08e6f0893e1cdae680edba5c606892c503244ff1
3
+ size 1064
run-3/checkpoint-1713/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-3/checkpoint-1713/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1713/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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": false,
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-3/checkpoint-1713/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8504556783745718,
3
+ "best_model_checkpoint": "test-klue/ynat-hps/run-3/checkpoint-1142",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1713,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.88,
13
+ "learning_rate": 1.0665865551075277e-05,
14
+ "loss": 0.6897,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_f1": 0.8405267782311162,
20
+ "eval_loss": 0.5007498860359192,
21
+ "eval_runtime": 12.2145,
22
+ "eval_samples_per_second": 745.59,
23
+ "eval_steps_per_second": 2.947,
24
+ "step": 571
25
+ },
26
+ {
27
+ "epoch": 1.75,
28
+ "learning_rate": 7.676553457164043e-06,
29
+ "loss": 0.3368,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_f1": 0.8504556783745718,
35
+ "eval_loss": 0.5121398568153381,
36
+ "eval_runtime": 12.4319,
37
+ "eval_samples_per_second": 732.553,
38
+ "eval_steps_per_second": 2.896,
39
+ "step": 1142
40
+ },
41
+ {
42
+ "epoch": 2.63,
43
+ "learning_rate": 4.687241363252811e-06,
44
+ "loss": 0.2662,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_f1": 0.8453442739504695,
50
+ "eval_loss": 0.6183401942253113,
51
+ "eval_runtime": 12.1492,
52
+ "eval_samples_per_second": 749.597,
53
+ "eval_steps_per_second": 2.963,
54
+ "step": 1713
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 2284,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 4,
61
+ "save_steps": 500,
62
+ "total_flos": 122084899086000.0,
63
+ "train_batch_size": 8,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 1.3655177644986507e-05,
67
+ "num_train_epochs": 4,
68
+ "per_device_train_batch_size": 8,
69
+ "seed": 30
70
+ }
71
+ }
run-3/checkpoint-1713/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a614592c80a4a414de05cd99fe99271561717829d2d0ccd2753babdf84eaf93f
3
+ size 4728
run-3/checkpoint-1713/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-571/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/bert-base",
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": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.36.2",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 32000
44
+ }
run-3/checkpoint-571/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d38547a465b9e1662178ac2ffce2728cc0afc553c461bf2c32d20110e20350a
3
+ size 442514444
run-3/checkpoint-571/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385648e234036377e34aacb16294ab0e490c45545a377e549e53b1c1f5ff7b55
3
+ size 885149946
run-3/checkpoint-571/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee041eee261574abf18f279661ffcadef4af240fe372d62a445dc0c9b535cffe
3
+ size 14244
run-3/checkpoint-571/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d046dec56ead4e4daf82b3e44d42b98ae82ca5b7195f362f2c4db64cbb8a0af5
3
+ size 1064