ssktora commited on
Commit
aef95da
·
verified ·
1 Parent(s): 8d2ec05

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-11118/config.json +26 -0
  2. checkpoint-11118/optimizer.pt +3 -0
  3. checkpoint-11118/pytorch_model.bin +3 -0
  4. checkpoint-11118/rng_state.pth +3 -0
  5. checkpoint-11118/scheduler.pt +3 -0
  6. checkpoint-11118/tokenizer.json +0 -0
  7. checkpoint-11118/tokenizer_config.json +55 -0
  8. checkpoint-11118/trainer_state.json +0 -0
  9. checkpoint-11118/training_args.bin +3 -0
  10. checkpoint-11118/vocab.txt +0 -0
  11. checkpoint-12971/config.json +26 -0
  12. checkpoint-12971/optimizer.pt +3 -0
  13. checkpoint-12971/pytorch_model.bin +3 -0
  14. checkpoint-12971/rng_state.pth +3 -0
  15. checkpoint-12971/scheduler.pt +3 -0
  16. checkpoint-12971/tokenizer.json +0 -0
  17. checkpoint-12971/tokenizer_config.json +55 -0
  18. checkpoint-12971/trainer_state.json +0 -0
  19. checkpoint-12971/training_args.bin +3 -0
  20. checkpoint-12971/vocab.txt +0 -0
  21. checkpoint-14824/config.json +26 -0
  22. checkpoint-14824/optimizer.pt +3 -0
  23. checkpoint-14824/pytorch_model.bin +3 -0
  24. checkpoint-14824/rng_state.pth +3 -0
  25. checkpoint-14824/scheduler.pt +3 -0
  26. checkpoint-14824/tokenizer.json +0 -0
  27. checkpoint-14824/tokenizer_config.json +55 -0
  28. checkpoint-14824/trainer_state.json +0 -0
  29. checkpoint-14824/training_args.bin +3 -0
  30. checkpoint-14824/vocab.txt +0 -0
  31. checkpoint-16677/config.json +26 -0
  32. checkpoint-16677/optimizer.pt +3 -0
  33. checkpoint-16677/pytorch_model.bin +3 -0
  34. checkpoint-16677/rng_state.pth +3 -0
  35. checkpoint-16677/scheduler.pt +3 -0
  36. checkpoint-16677/tokenizer.json +0 -0
  37. checkpoint-16677/tokenizer_config.json +55 -0
  38. checkpoint-16677/trainer_state.json +0 -0
  39. checkpoint-16677/training_args.bin +3 -0
  40. checkpoint-16677/vocab.txt +0 -0
  41. checkpoint-1853/config.json +26 -0
  42. checkpoint-1853/optimizer.pt +3 -0
  43. checkpoint-1853/pytorch_model.bin +3 -0
  44. checkpoint-1853/rng_state.pth +3 -0
  45. checkpoint-1853/scheduler.pt +3 -0
  46. checkpoint-1853/tokenizer.json +0 -0
  47. checkpoint-1853/tokenizer_config.json +55 -0
  48. checkpoint-1853/trainer_state.json +1328 -0
  49. checkpoint-1853/training_args.bin +3 -0
  50. checkpoint-1853/vocab.txt +0 -0
checkpoint-11118/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/e5-base-v2",
3
+ "architectures": [
4
+ "BertModel"
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": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.43.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
checkpoint-11118/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c2aeea5976532fcfadfb26faf6adddcdb187ef5e977f69a8c19e35438736aa
3
+ size 871298443
checkpoint-11118/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1388125c28b1ffce6499bdb3a901976778da116fb74b75ddb7dbfee06c2d6bd
3
+ size 437996607
checkpoint-11118/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b540e2f579364899d666b5908117b431fbe801874a126cf16cf7babd2b8a2a12
3
+ size 14645
checkpoint-11118/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377fe88207e30e42ed2add57e371aa37136f8aac64c0727cadf567d86c5f33bd
3
+ size 1465
checkpoint-11118/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11118/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
+ }
checkpoint-11118/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11118/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5700588298a783e95c1ce2b2e3e984a108dafdc83314148b0e8703b669b1c239
3
+ size 5777
checkpoint-11118/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12971/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/e5-base-v2",
3
+ "architectures": [
4
+ "BertModel"
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": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.43.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
checkpoint-12971/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b562e8660e077a53a09bc774af597650bd077647c324bb13c3f1d228fcf43cb
3
+ size 871298443
checkpoint-12971/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac531318b31f38b2afe8b1be678c045938d04ceb4a7eb4d3d0718811799d3fd
3
+ size 437996607
checkpoint-12971/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8019ec3eeab7b0c9d484aca769f45ff0cff286443a69fdd5ab6a881dec17fc
3
+ size 14645
checkpoint-12971/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74051b3bb6700f1fd1e74666c73b717b918a7c8f6fde350756aa4534df66526b
3
+ size 1465
checkpoint-12971/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12971/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
+ }
checkpoint-12971/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12971/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5700588298a783e95c1ce2b2e3e984a108dafdc83314148b0e8703b669b1c239
3
+ size 5777
checkpoint-12971/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14824/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/e5-base-v2",
3
+ "architectures": [
4
+ "BertModel"
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": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.43.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
checkpoint-14824/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d7871763ea8325875f4333123c14d5d1bcf992b30b264bfb806859ce7190bb
3
+ size 871298443
checkpoint-14824/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:268a12cd1b2d6bbfd230497c41c50782552ba66d12947ef3037590bbc73c7527
3
+ size 437996607
checkpoint-14824/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4d97a3f14dc200660b4547f67457fca224de922f2bdb06c08e4d85691647f1
3
+ size 14645
checkpoint-14824/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4c1a6165520754f0146fb1a1349521e95d27576f503d46b69e2ec6e52144b6
3
+ size 1465
checkpoint-14824/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14824/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
+ }
checkpoint-14824/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14824/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5700588298a783e95c1ce2b2e3e984a108dafdc83314148b0e8703b669b1c239
3
+ size 5777
checkpoint-14824/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16677/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/e5-base-v2",
3
+ "architectures": [
4
+ "BertModel"
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": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.43.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
checkpoint-16677/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303d31db3b9da84fe13482be31e3a3f25098ba7e9851a0557d62c88fdcf41714
3
+ size 871298443
checkpoint-16677/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12b3a64a892befdf1dc0f1ebb03a823b4cd8c46e09f395f1448a124cdb59006b
3
+ size 437996607
checkpoint-16677/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a49063e95ef6ad97e995553a393b9473379ab9aa8c9ed79537839d4e0119cd
3
+ size 14645
checkpoint-16677/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5394a1eac72e1a904c9364d0afbad631005bbfdd486d10b3d6dff7e1601efcab
3
+ size 1465
checkpoint-16677/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16677/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
+ }
checkpoint-16677/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16677/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5700588298a783e95c1ce2b2e3e984a108dafdc83314148b0e8703b669b1c239
3
+ size 5777
checkpoint-16677/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1853/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/e5-base-v2",
3
+ "architectures": [
4
+ "BertModel"
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": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.43.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
checkpoint-1853/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981a19567c04c2b2cb9b1a653a980a4da95c4b67f3d797729c9bf94d9d820221
3
+ size 871298443
checkpoint-1853/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:470805b0ce63601f0782c614826d3963cd29818aaa5de7839d40717da037dbc9
3
+ size 437996607
checkpoint-1853/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b80b6fd6641f8d23bd438cdf6cceef57e16c2fce00df1725f75f09caf97a19de
3
+ size 14645
checkpoint-1853/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d851ecd6c343c0ff07e7ab1a38de41108844243787871e94dabeeeb08eda1c3
3
+ size 1465
checkpoint-1853/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1853/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
+ }
checkpoint-1853/trainer_state.json ADDED
@@ -0,0 +1,1328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1853,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005396654074473826,
13
+ "grad_norm": 29.233814239501953,
14
+ "learning_rate": 1e-05,
15
+ "loss": 2.7721,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.010793308148947653,
20
+ "grad_norm": 41.590599060058594,
21
+ "learning_rate": 1e-05,
22
+ "loss": 1.0356,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.016189962223421478,
27
+ "grad_norm": 30.425613403320312,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.9625,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.021586616297895305,
34
+ "grad_norm": 18.49728775024414,
35
+ "learning_rate": 1e-05,
36
+ "loss": 0.7988,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.026983270372369132,
41
+ "grad_norm": 24.669769287109375,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.7037,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.032379924446842956,
48
+ "grad_norm": 31.885276794433594,
49
+ "learning_rate": 1e-05,
50
+ "loss": 0.7008,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.037776578521316787,
55
+ "grad_norm": 39.430580139160156,
56
+ "learning_rate": 1e-05,
57
+ "loss": 0.8244,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.04317323259579061,
62
+ "grad_norm": 31.985998153686523,
63
+ "learning_rate": 1e-05,
64
+ "loss": 0.6062,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.048569886670264434,
69
+ "grad_norm": 34.52704620361328,
70
+ "learning_rate": 1e-05,
71
+ "loss": 0.6404,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.053966540744738264,
76
+ "grad_norm": 26.020505905151367,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.4898,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.05936319481921209,
83
+ "grad_norm": 20.571788787841797,
84
+ "learning_rate": 1e-05,
85
+ "loss": 0.4647,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.06475984889368591,
90
+ "grad_norm": 23.191669464111328,
91
+ "learning_rate": 1e-05,
92
+ "loss": 0.514,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.07015650296815974,
97
+ "grad_norm": 24.66558074951172,
98
+ "learning_rate": 1e-05,
99
+ "loss": 0.4045,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.07555315704263357,
104
+ "grad_norm": 21.027311325073242,
105
+ "learning_rate": 1e-05,
106
+ "loss": 0.4915,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.08094981111710739,
111
+ "grad_norm": 19.729063034057617,
112
+ "learning_rate": 1e-05,
113
+ "loss": 0.5797,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.08634646519158122,
118
+ "grad_norm": 18.003055572509766,
119
+ "learning_rate": 1e-05,
120
+ "loss": 0.4057,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.09174311926605505,
125
+ "grad_norm": 17.475120544433594,
126
+ "learning_rate": 1e-05,
127
+ "loss": 0.5727,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.09713977334052887,
132
+ "grad_norm": 12.938204765319824,
133
+ "learning_rate": 1e-05,
134
+ "loss": 0.4603,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.1025364274150027,
139
+ "grad_norm": 15.203913688659668,
140
+ "learning_rate": 1e-05,
141
+ "loss": 0.3722,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.10793308148947653,
146
+ "grad_norm": 14.949216842651367,
147
+ "learning_rate": 1e-05,
148
+ "loss": 0.4513,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.11332973556395035,
153
+ "grad_norm": 21.059656143188477,
154
+ "learning_rate": 1e-05,
155
+ "loss": 0.4286,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.11872638963842418,
160
+ "grad_norm": 15.692352294921875,
161
+ "learning_rate": 1e-05,
162
+ "loss": 0.3947,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.124123043712898,
167
+ "grad_norm": 16.783273696899414,
168
+ "learning_rate": 1e-05,
169
+ "loss": 0.316,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.12951969778737182,
174
+ "grad_norm": 13.165032386779785,
175
+ "learning_rate": 1e-05,
176
+ "loss": 0.3057,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.13491635186184567,
181
+ "grad_norm": 11.906001091003418,
182
+ "learning_rate": 1e-05,
183
+ "loss": 0.335,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.14031300593631948,
188
+ "grad_norm": 11.135077476501465,
189
+ "learning_rate": 1e-05,
190
+ "loss": 0.3502,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.1457096600107933,
195
+ "grad_norm": 13.552120208740234,
196
+ "learning_rate": 1e-05,
197
+ "loss": 0.4856,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.15110631408526715,
202
+ "grad_norm": 8.249211311340332,
203
+ "learning_rate": 1e-05,
204
+ "loss": 0.3541,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.15650296815974096,
209
+ "grad_norm": 9.598445892333984,
210
+ "learning_rate": 1e-05,
211
+ "loss": 0.3433,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.16189962223421478,
216
+ "grad_norm": 14.606228828430176,
217
+ "learning_rate": 1e-05,
218
+ "loss": 0.3092,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.16729627630868862,
223
+ "grad_norm": 14.358266830444336,
224
+ "learning_rate": 1e-05,
225
+ "loss": 0.2367,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.17269293038316244,
230
+ "grad_norm": 13.869871139526367,
231
+ "learning_rate": 1e-05,
232
+ "loss": 0.3792,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.17808958445763626,
237
+ "grad_norm": 6.00723934173584,
238
+ "learning_rate": 1e-05,
239
+ "loss": 0.2773,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.1834862385321101,
244
+ "grad_norm": 9.07499885559082,
245
+ "learning_rate": 1e-05,
246
+ "loss": 0.2157,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.18888289260658392,
251
+ "grad_norm": 10.11136531829834,
252
+ "learning_rate": 1e-05,
253
+ "loss": 0.2814,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.19427954668105774,
258
+ "grad_norm": 8.610591888427734,
259
+ "learning_rate": 1e-05,
260
+ "loss": 0.3358,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.19967620075553158,
265
+ "grad_norm": 7.348660945892334,
266
+ "learning_rate": 1e-05,
267
+ "loss": 0.3133,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.2050728548300054,
272
+ "grad_norm": 9.130489349365234,
273
+ "learning_rate": 1e-05,
274
+ "loss": 0.3825,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.2104695089044792,
279
+ "grad_norm": 10.860395431518555,
280
+ "learning_rate": 1e-05,
281
+ "loss": 0.2901,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.21586616297895306,
286
+ "grad_norm": 13.92383861541748,
287
+ "learning_rate": 1e-05,
288
+ "loss": 0.2765,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.22126281705342687,
293
+ "grad_norm": 10.262186050415039,
294
+ "learning_rate": 1e-05,
295
+ "loss": 0.3204,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.2266594711279007,
300
+ "grad_norm": 12.785383224487305,
301
+ "learning_rate": 1e-05,
302
+ "loss": 0.2899,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.23205612520237454,
307
+ "grad_norm": 7.4662089347839355,
308
+ "learning_rate": 1e-05,
309
+ "loss": 0.2543,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.23745277927684835,
314
+ "grad_norm": 9.430139541625977,
315
+ "learning_rate": 1e-05,
316
+ "loss": 0.2249,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.24284943335132217,
321
+ "grad_norm": 15.234227180480957,
322
+ "learning_rate": 1e-05,
323
+ "loss": 0.2782,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.248246087425796,
328
+ "grad_norm": 12.813672065734863,
329
+ "learning_rate": 1e-05,
330
+ "loss": 0.3109,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.25364274150026983,
335
+ "grad_norm": 8.589320182800293,
336
+ "learning_rate": 1e-05,
337
+ "loss": 0.2568,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.25903939557474365,
342
+ "grad_norm": 10.285687446594238,
343
+ "learning_rate": 1e-05,
344
+ "loss": 0.3188,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.26443604964921746,
349
+ "grad_norm": 6.851498126983643,
350
+ "learning_rate": 1e-05,
351
+ "loss": 0.281,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.26983270372369134,
356
+ "grad_norm": 14.00925064086914,
357
+ "learning_rate": 1e-05,
358
+ "loss": 0.3208,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.27522935779816515,
363
+ "grad_norm": 5.691648006439209,
364
+ "learning_rate": 1e-05,
365
+ "loss": 0.2477,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.28062601187263897,
370
+ "grad_norm": 9.477752685546875,
371
+ "learning_rate": 1e-05,
372
+ "loss": 0.2657,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.2860226659471128,
377
+ "grad_norm": 14.55162525177002,
378
+ "learning_rate": 1e-05,
379
+ "loss": 0.315,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.2914193200215866,
384
+ "grad_norm": 8.495135307312012,
385
+ "learning_rate": 1e-05,
386
+ "loss": 0.1899,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.2968159740960604,
391
+ "grad_norm": 7.937713146209717,
392
+ "learning_rate": 1e-05,
393
+ "loss": 0.2235,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.3022126281705343,
398
+ "grad_norm": 6.74868631362915,
399
+ "learning_rate": 1e-05,
400
+ "loss": 0.2017,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.3076092822450081,
405
+ "grad_norm": 10.642626762390137,
406
+ "learning_rate": 1e-05,
407
+ "loss": 0.271,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.3130059363194819,
412
+ "grad_norm": 7.630133628845215,
413
+ "learning_rate": 1e-05,
414
+ "loss": 0.2843,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.31840259039395574,
419
+ "grad_norm": 7.430366516113281,
420
+ "learning_rate": 1e-05,
421
+ "loss": 0.3251,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.32379924446842956,
426
+ "grad_norm": 9.424999237060547,
427
+ "learning_rate": 1e-05,
428
+ "loss": 0.2786,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.3291958985429034,
433
+ "grad_norm": 9.91606330871582,
434
+ "learning_rate": 1e-05,
435
+ "loss": 0.3073,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.33459255261737725,
440
+ "grad_norm": 11.460907936096191,
441
+ "learning_rate": 1e-05,
442
+ "loss": 0.2649,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.33998920669185106,
447
+ "grad_norm": 7.377775192260742,
448
+ "learning_rate": 1e-05,
449
+ "loss": 0.2736,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.3453858607663249,
454
+ "grad_norm": 6.579836368560791,
455
+ "learning_rate": 1e-05,
456
+ "loss": 0.2087,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.3507825148407987,
461
+ "grad_norm": 7.274311542510986,
462
+ "learning_rate": 1e-05,
463
+ "loss": 0.179,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.3561791689152725,
468
+ "grad_norm": 4.020033359527588,
469
+ "learning_rate": 1e-05,
470
+ "loss": 0.2366,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.36157582298974633,
475
+ "grad_norm": 5.806532382965088,
476
+ "learning_rate": 1e-05,
477
+ "loss": 0.2293,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.3669724770642202,
482
+ "grad_norm": 9.085073471069336,
483
+ "learning_rate": 1e-05,
484
+ "loss": 0.2155,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.372369131138694,
489
+ "grad_norm": 6.555941104888916,
490
+ "learning_rate": 1e-05,
491
+ "loss": 0.1883,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.37776578521316784,
496
+ "grad_norm": 7.962392807006836,
497
+ "learning_rate": 1e-05,
498
+ "loss": 0.2434,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.38316243928764165,
503
+ "grad_norm": 8.351177215576172,
504
+ "learning_rate": 1e-05,
505
+ "loss": 0.2944,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.38855909336211547,
510
+ "grad_norm": 8.052698135375977,
511
+ "learning_rate": 1e-05,
512
+ "loss": 0.2638,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.3939557474365893,
517
+ "grad_norm": 8.064635276794434,
518
+ "learning_rate": 1e-05,
519
+ "loss": 0.2193,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.39935240151106316,
524
+ "grad_norm": 5.15111780166626,
525
+ "learning_rate": 1e-05,
526
+ "loss": 0.2221,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.404749055585537,
531
+ "grad_norm": 6.953875541687012,
532
+ "learning_rate": 1e-05,
533
+ "loss": 0.3105,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.4101457096600108,
538
+ "grad_norm": 6.684737682342529,
539
+ "learning_rate": 1e-05,
540
+ "loss": 0.2246,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.4155423637344846,
545
+ "grad_norm": 11.400216102600098,
546
+ "learning_rate": 1e-05,
547
+ "loss": 0.2972,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.4209390178089584,
552
+ "grad_norm": 7.080048561096191,
553
+ "learning_rate": 1e-05,
554
+ "loss": 0.2225,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.4263356718834323,
559
+ "grad_norm": 8.054226875305176,
560
+ "learning_rate": 1e-05,
561
+ "loss": 0.2131,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.4317323259579061,
566
+ "grad_norm": 4.726242542266846,
567
+ "learning_rate": 1e-05,
568
+ "loss": 0.2632,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.43712898003237993,
573
+ "grad_norm": 5.8682942390441895,
574
+ "learning_rate": 1e-05,
575
+ "loss": 0.2042,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.44252563410685375,
580
+ "grad_norm": 10.576642990112305,
581
+ "learning_rate": 1e-05,
582
+ "loss": 0.1665,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.44792228818132757,
587
+ "grad_norm": 8.981599807739258,
588
+ "learning_rate": 1e-05,
589
+ "loss": 0.2466,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.4533189422558014,
594
+ "grad_norm": 5.737548828125,
595
+ "learning_rate": 1e-05,
596
+ "loss": 0.2609,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.45871559633027525,
601
+ "grad_norm": 8.086627960205078,
602
+ "learning_rate": 1e-05,
603
+ "loss": 0.2821,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.46411225040474907,
608
+ "grad_norm": 3.403313398361206,
609
+ "learning_rate": 1e-05,
610
+ "loss": 0.2281,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.4695089044792229,
615
+ "grad_norm": 3.788487672805786,
616
+ "learning_rate": 1e-05,
617
+ "loss": 0.2798,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.4749055585536967,
622
+ "grad_norm": 2.9724912643432617,
623
+ "learning_rate": 1e-05,
624
+ "loss": 0.2317,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.4803022126281705,
629
+ "grad_norm": 5.880742073059082,
630
+ "learning_rate": 1e-05,
631
+ "loss": 0.2615,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.48569886670264434,
636
+ "grad_norm": 4.259861946105957,
637
+ "learning_rate": 1e-05,
638
+ "loss": 0.1988,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.4910955207771182,
643
+ "grad_norm": 8.759398460388184,
644
+ "learning_rate": 1e-05,
645
+ "loss": 0.1831,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.496492174851592,
650
+ "grad_norm": 7.270608425140381,
651
+ "learning_rate": 1e-05,
652
+ "loss": 0.2976,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.5018888289260658,
657
+ "grad_norm": 8.03155517578125,
658
+ "learning_rate": 1e-05,
659
+ "loss": 0.2559,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.5072854830005397,
664
+ "grad_norm": 8.855595588684082,
665
+ "learning_rate": 1e-05,
666
+ "loss": 0.207,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.5126821370750135,
671
+ "grad_norm": 10.3396577835083,
672
+ "learning_rate": 1e-05,
673
+ "loss": 0.2343,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.5180787911494873,
678
+ "grad_norm": 7.144564628601074,
679
+ "learning_rate": 1e-05,
680
+ "loss": 0.3085,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.5234754452239612,
685
+ "grad_norm": 6.791202068328857,
686
+ "learning_rate": 1e-05,
687
+ "loss": 0.2256,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.5288720992984349,
692
+ "grad_norm": 10.9970064163208,
693
+ "learning_rate": 1e-05,
694
+ "loss": 0.2426,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.5342687533729088,
699
+ "grad_norm": 10.478626251220703,
700
+ "learning_rate": 1e-05,
701
+ "loss": 0.2366,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.5396654074473827,
706
+ "grad_norm": 7.615540504455566,
707
+ "learning_rate": 1e-05,
708
+ "loss": 0.2386,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.5450620615218564,
713
+ "grad_norm": 10.919700622558594,
714
+ "learning_rate": 1e-05,
715
+ "loss": 0.2146,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.5504587155963303,
720
+ "grad_norm": 5.4628095626831055,
721
+ "learning_rate": 1e-05,
722
+ "loss": 0.1707,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.5558553696708041,
727
+ "grad_norm": 7.794273853302002,
728
+ "learning_rate": 1e-05,
729
+ "loss": 0.2188,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.5612520237452779,
734
+ "grad_norm": 3.660203695297241,
735
+ "learning_rate": 1e-05,
736
+ "loss": 0.2031,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.5666486778197517,
741
+ "grad_norm": 6.309048652648926,
742
+ "learning_rate": 1e-05,
743
+ "loss": 0.1868,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.5720453318942256,
748
+ "grad_norm": 4.429934024810791,
749
+ "learning_rate": 1e-05,
750
+ "loss": 0.225,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.5774419859686994,
755
+ "grad_norm": 7.08953857421875,
756
+ "learning_rate": 1e-05,
757
+ "loss": 0.2234,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.5828386400431732,
762
+ "grad_norm": 5.881676197052002,
763
+ "learning_rate": 1e-05,
764
+ "loss": 0.1651,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.5882352941176471,
769
+ "grad_norm": 7.384402275085449,
770
+ "learning_rate": 1e-05,
771
+ "loss": 0.1686,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.5936319481921208,
776
+ "grad_norm": 6.034684658050537,
777
+ "learning_rate": 1e-05,
778
+ "loss": 0.2284,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.5990286022665947,
783
+ "grad_norm": 2.630262613296509,
784
+ "learning_rate": 1e-05,
785
+ "loss": 0.2197,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.6044252563410686,
790
+ "grad_norm": 6.340832233428955,
791
+ "learning_rate": 1e-05,
792
+ "loss": 0.1857,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.6098219104155423,
797
+ "grad_norm": 9.152372360229492,
798
+ "learning_rate": 1e-05,
799
+ "loss": 0.2412,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.6152185644900162,
804
+ "grad_norm": 5.497441291809082,
805
+ "learning_rate": 1e-05,
806
+ "loss": 0.1669,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.62061521856449,
811
+ "grad_norm": 9.082748413085938,
812
+ "learning_rate": 1e-05,
813
+ "loss": 0.156,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.6260118726389639,
818
+ "grad_norm": 4.197298526763916,
819
+ "learning_rate": 1e-05,
820
+ "loss": 0.2195,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.6314085267134377,
825
+ "grad_norm": 6.62587308883667,
826
+ "learning_rate": 1e-05,
827
+ "loss": 0.2377,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.6368051807879115,
832
+ "grad_norm": 5.473176956176758,
833
+ "learning_rate": 1e-05,
834
+ "loss": 0.1852,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.6422018348623854,
839
+ "grad_norm": 11.426214218139648,
840
+ "learning_rate": 1e-05,
841
+ "loss": 0.2576,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.6475984889368591,
846
+ "grad_norm": 5.523359775543213,
847
+ "learning_rate": 1e-05,
848
+ "loss": 0.1803,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.652995143011333,
853
+ "grad_norm": 8.255809783935547,
854
+ "learning_rate": 1e-05,
855
+ "loss": 0.2187,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.6583917970858068,
860
+ "grad_norm": 6.8662800788879395,
861
+ "learning_rate": 1e-05,
862
+ "loss": 0.1688,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.6637884511602806,
867
+ "grad_norm": 6.395972728729248,
868
+ "learning_rate": 1e-05,
869
+ "loss": 0.256,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.6691851052347545,
874
+ "grad_norm": 5.074724197387695,
875
+ "learning_rate": 1e-05,
876
+ "loss": 0.2205,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.6745817593092283,
881
+ "grad_norm": 8.648845672607422,
882
+ "learning_rate": 1e-05,
883
+ "loss": 0.1993,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.6799784133837021,
888
+ "grad_norm": 8.962705612182617,
889
+ "learning_rate": 1e-05,
890
+ "loss": 0.1674,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.6853750674581759,
895
+ "grad_norm": 7.555551528930664,
896
+ "learning_rate": 1e-05,
897
+ "loss": 0.1769,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.6907717215326498,
902
+ "grad_norm": 7.777824878692627,
903
+ "learning_rate": 1e-05,
904
+ "loss": 0.2648,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.6961683756071236,
909
+ "grad_norm": 6.23061990737915,
910
+ "learning_rate": 1e-05,
911
+ "loss": 0.2291,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.7015650296815974,
916
+ "grad_norm": 4.784579753875732,
917
+ "learning_rate": 1e-05,
918
+ "loss": 0.1657,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.7069616837560713,
923
+ "grad_norm": 5.664929389953613,
924
+ "learning_rate": 1e-05,
925
+ "loss": 0.223,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.712358337830545,
930
+ "grad_norm": 5.156897068023682,
931
+ "learning_rate": 1e-05,
932
+ "loss": 0.2603,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.7177549919050189,
937
+ "grad_norm": 4.825225830078125,
938
+ "learning_rate": 1e-05,
939
+ "loss": 0.2073,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.7231516459794927,
944
+ "grad_norm": 4.079571723937988,
945
+ "learning_rate": 1e-05,
946
+ "loss": 0.1721,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.7285483000539665,
951
+ "grad_norm": 10.262605667114258,
952
+ "learning_rate": 1e-05,
953
+ "loss": 0.2038,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.7339449541284404,
958
+ "grad_norm": 7.239202499389648,
959
+ "learning_rate": 1e-05,
960
+ "loss": 0.2468,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.7393416082029142,
965
+ "grad_norm": 4.406205177307129,
966
+ "learning_rate": 1e-05,
967
+ "loss": 0.2068,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.744738262277388,
972
+ "grad_norm": 6.728589057922363,
973
+ "learning_rate": 1e-05,
974
+ "loss": 0.2275,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.7501349163518618,
979
+ "grad_norm": 10.06982421875,
980
+ "learning_rate": 1e-05,
981
+ "loss": 0.2351,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.7555315704263357,
986
+ "grad_norm": 3.351484537124634,
987
+ "learning_rate": 1e-05,
988
+ "loss": 0.1853,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.7609282245008095,
993
+ "grad_norm": 7.834474563598633,
994
+ "learning_rate": 1e-05,
995
+ "loss": 0.201,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.7663248785752833,
1000
+ "grad_norm": 1.604831576347351,
1001
+ "learning_rate": 1e-05,
1002
+ "loss": 0.1967,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.7717215326497572,
1007
+ "grad_norm": 8.6753511428833,
1008
+ "learning_rate": 1e-05,
1009
+ "loss": 0.1707,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.7771181867242309,
1014
+ "grad_norm": 14.741216659545898,
1015
+ "learning_rate": 1e-05,
1016
+ "loss": 0.228,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.7825148407987048,
1021
+ "grad_norm": 11.765339851379395,
1022
+ "learning_rate": 1e-05,
1023
+ "loss": 0.2225,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.7879114948731786,
1028
+ "grad_norm": 4.842400550842285,
1029
+ "learning_rate": 1e-05,
1030
+ "loss": 0.1578,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.7933081489476524,
1035
+ "grad_norm": 4.625942707061768,
1036
+ "learning_rate": 1e-05,
1037
+ "loss": 0.1773,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.7987048030221263,
1042
+ "grad_norm": 5.874000072479248,
1043
+ "learning_rate": 1e-05,
1044
+ "loss": 0.2121,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.8041014570966001,
1049
+ "grad_norm": 8.645938873291016,
1050
+ "learning_rate": 1e-05,
1051
+ "loss": 0.1781,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.809498111171074,
1056
+ "grad_norm": 9.911633491516113,
1057
+ "learning_rate": 1e-05,
1058
+ "loss": 0.193,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.8148947652455477,
1063
+ "grad_norm": 10.095293998718262,
1064
+ "learning_rate": 1e-05,
1065
+ "loss": 0.2153,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.8202914193200216,
1070
+ "grad_norm": 7.327795505523682,
1071
+ "learning_rate": 1e-05,
1072
+ "loss": 0.1971,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.8256880733944955,
1077
+ "grad_norm": 8.179699897766113,
1078
+ "learning_rate": 1e-05,
1079
+ "loss": 0.2281,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.8310847274689692,
1084
+ "grad_norm": 8.069372177124023,
1085
+ "learning_rate": 1e-05,
1086
+ "loss": 0.1693,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.8364813815434431,
1091
+ "grad_norm": 4.130002975463867,
1092
+ "learning_rate": 1e-05,
1093
+ "loss": 0.2075,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.8418780356179169,
1098
+ "grad_norm": 5.865467548370361,
1099
+ "learning_rate": 1e-05,
1100
+ "loss": 0.1454,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.8472746896923907,
1105
+ "grad_norm": 7.074893474578857,
1106
+ "learning_rate": 1e-05,
1107
+ "loss": 0.225,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.8526713437668646,
1112
+ "grad_norm": 7.433347225189209,
1113
+ "learning_rate": 1e-05,
1114
+ "loss": 0.2137,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.8580679978413384,
1119
+ "grad_norm": 4.781975746154785,
1120
+ "learning_rate": 1e-05,
1121
+ "loss": 0.1458,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.8634646519158122,
1126
+ "grad_norm": 4.815838813781738,
1127
+ "learning_rate": 1e-05,
1128
+ "loss": 0.1881,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.868861305990286,
1133
+ "grad_norm": 5.3275146484375,
1134
+ "learning_rate": 1e-05,
1135
+ "loss": 0.1683,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.8742579600647599,
1140
+ "grad_norm": 4.237251281738281,
1141
+ "learning_rate": 1e-05,
1142
+ "loss": 0.204,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.8796546141392336,
1147
+ "grad_norm": 4.050580978393555,
1148
+ "learning_rate": 1e-05,
1149
+ "loss": 0.1707,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.8850512682137075,
1154
+ "grad_norm": 10.195475578308105,
1155
+ "learning_rate": 1e-05,
1156
+ "loss": 0.1637,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.8904479222881814,
1161
+ "grad_norm": 7.7511091232299805,
1162
+ "learning_rate": 1e-05,
1163
+ "loss": 0.2098,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.8958445763626551,
1168
+ "grad_norm": 5.1113715171813965,
1169
+ "learning_rate": 1e-05,
1170
+ "loss": 0.1749,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.901241230437129,
1175
+ "grad_norm": 4.634021282196045,
1176
+ "learning_rate": 1e-05,
1177
+ "loss": 0.2138,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.9066378845116028,
1182
+ "grad_norm": 9.203325271606445,
1183
+ "learning_rate": 1e-05,
1184
+ "loss": 0.2056,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.9120345385860766,
1189
+ "grad_norm": 9.506570816040039,
1190
+ "learning_rate": 1e-05,
1191
+ "loss": 0.2172,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.9174311926605505,
1196
+ "grad_norm": 7.978335857391357,
1197
+ "learning_rate": 1e-05,
1198
+ "loss": 0.1842,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.9228278467350243,
1203
+ "grad_norm": 5.630960941314697,
1204
+ "learning_rate": 1e-05,
1205
+ "loss": 0.1644,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.9282245008094981,
1210
+ "grad_norm": 4.95536470413208,
1211
+ "learning_rate": 1e-05,
1212
+ "loss": 0.2139,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.9336211548839719,
1217
+ "grad_norm": 5.746067047119141,
1218
+ "learning_rate": 1e-05,
1219
+ "loss": 0.175,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.9390178089584458,
1224
+ "grad_norm": 7.568691253662109,
1225
+ "learning_rate": 1e-05,
1226
+ "loss": 0.173,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.9444144630329195,
1231
+ "grad_norm": 1.8593629598617554,
1232
+ "learning_rate": 1e-05,
1233
+ "loss": 0.2013,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.9498111171073934,
1238
+ "grad_norm": 5.8079962730407715,
1239
+ "learning_rate": 1e-05,
1240
+ "loss": 0.1986,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.9552077711818673,
1245
+ "grad_norm": 4.595200061798096,
1246
+ "learning_rate": 1e-05,
1247
+ "loss": 0.1582,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.960604425256341,
1252
+ "grad_norm": 4.077558994293213,
1253
+ "learning_rate": 1e-05,
1254
+ "loss": 0.1965,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.9660010793308149,
1259
+ "grad_norm": 5.77232551574707,
1260
+ "learning_rate": 1e-05,
1261
+ "loss": 0.1555,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.9713977334052887,
1266
+ "grad_norm": 6.829488754272461,
1267
+ "learning_rate": 1e-05,
1268
+ "loss": 0.194,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.9767943874797625,
1273
+ "grad_norm": 7.6999897956848145,
1274
+ "learning_rate": 1e-05,
1275
+ "loss": 0.1901,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.9821910415542364,
1280
+ "grad_norm": 5.529928207397461,
1281
+ "learning_rate": 1e-05,
1282
+ "loss": 0.2215,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.9875876956287102,
1287
+ "grad_norm": 6.4435811042785645,
1288
+ "learning_rate": 1e-05,
1289
+ "loss": 0.1744,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.992984349703184,
1294
+ "grad_norm": 5.611225605010986,
1295
+ "learning_rate": 1e-05,
1296
+ "loss": 0.1787,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 0.9983810037776578,
1301
+ "grad_norm": 3.3860135078430176,
1302
+ "learning_rate": 1e-05,
1303
+ "loss": 0.2011,
1304
+ "step": 1850
1305
+ }
1306
+ ],
1307
+ "logging_steps": 10,
1308
+ "max_steps": 37060,
1309
+ "num_input_tokens_seen": 0,
1310
+ "num_train_epochs": 20,
1311
+ "save_steps": 500,
1312
+ "stateful_callbacks": {
1313
+ "TrainerControl": {
1314
+ "args": {
1315
+ "should_epoch_stop": false,
1316
+ "should_evaluate": false,
1317
+ "should_log": false,
1318
+ "should_save": true,
1319
+ "should_training_stop": false
1320
+ },
1321
+ "attributes": {}
1322
+ }
1323
+ },
1324
+ "total_flos": 0.0,
1325
+ "train_batch_size": 64,
1326
+ "trial_name": null,
1327
+ "trial_params": null
1328
+ }
checkpoint-1853/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5700588298a783e95c1ce2b2e3e984a108dafdc83314148b0e8703b669b1c239
3
+ size 5777
checkpoint-1853/vocab.txt ADDED
The diff for this file is too large to render. See raw diff