Hugging Face's logo

EricAI03
/
math_token_classification

Token Classification
Safetensors
English
roberta
ner
math
mathematics
equations
Eval Results (legacy)
Model card Files
xet
 Community
EricAI03 commited on
Commit
2e201a8
·
verified ·
1 Parent(s): 4661832

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. checkpoint-166/config.json +51 -0
  2. checkpoint-166/model.safetensors +3 -0
  3. checkpoint-166/optimizer.pt +3 -0
  4. checkpoint-166/rng_state.pth +3 -0
  5. checkpoint-166/scaler.pt +3 -0
  6. checkpoint-166/scheduler.pt +3 -0
  7. checkpoint-166/tokenizer.json +0 -0
  8. checkpoint-166/tokenizer_config.json +17 -0
  9. checkpoint-166/trainer_state.json +71 -0
  10. checkpoint-166/training_args.bin +3 -0
  11. checkpoint-249/config.json +51 -0
  12. checkpoint-249/model.safetensors +3 -0
  13. checkpoint-249/optimizer.pt +3 -0
  14. checkpoint-249/rng_state.pth +3 -0
  15. checkpoint-249/scaler.pt +3 -0
  16. checkpoint-249/scheduler.pt +3 -0
  17. checkpoint-249/tokenizer.json +0 -0
  18. checkpoint-249/tokenizer_config.json +17 -0
  19. checkpoint-249/trainer_state.json +86 -0
  20. checkpoint-249/training_args.bin +3 -0
  21. checkpoint-83/config.json +51 -0
  22. checkpoint-83/model.safetensors +3 -0
  23. checkpoint-83/optimizer.pt +3 -0
  24. checkpoint-83/rng_state.pth +3 -0
  25. checkpoint-83/scaler.pt +3 -0
  26. checkpoint-83/scheduler.pt +3 -0
  27. checkpoint-83/tokenizer.json +0 -0
  28. checkpoint-83/tokenizer_config.json +17 -0
  29. checkpoint-83/trainer_state.json +49 -0
  30. checkpoint-83/training_args.bin +3 -0
checkpoint-166/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "-100": "SPECIAL_TOKEN",
16
+ "0": "O",
17
+ "1": "B-ALGEBRA",
18
+ "2": "I-ALGEBRA",
19
+ "3": "B-CALCULUS",
20
+ "4": "I-CALCULUS",
21
+ "5": "B-GEOMETRY",
22
+ "6": "I-GEOMETRY",
23
+ "7": "B-TRIGONOMETRY",
24
+ "8": "I-TRIGONOMETRY"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "is_decoder": false,
29
+ "label2id": {
30
+ "B-ALGEBRA": 1,
31
+ "B-CALCULUS": 3,
32
+ "B-GEOMETRY": 5,
33
+ "B-TRIGONOMETRY": 7,
34
+ "I-ALGEBRA": 2,
35
+ "I-CALCULUS": 4,
36
+ "I-GEOMETRY": 6,
37
+ "I-TRIGONOMETRY": 8,
38
+ "O": 0
39
+ },
40
+ "layer_norm_eps": 1e-05,
41
+ "max_position_embeddings": 514,
42
+ "model_type": "roberta",
43
+ "num_attention_heads": 12,
44
+ "num_hidden_layers": 12,
45
+ "pad_token_id": 1,
46
+ "tie_word_embeddings": true,
47
+ "transformers_version": "5.16.1",
48
+ "type_vocab_size": 1,
49
+ "use_cache": false,
50
+ "vocab_size": 50265
51
+ }
checkpoint-166/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1be9b557ed31484e4ec5ee56e81dcef368556096acc412d6df028b3dc3838bb
3
+ size 496274848
checkpoint-166/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fce50b633a01e87cca83ecb3fd36ab0b162c03d815f79671153ca15b693873e
3
+ size 992671435
checkpoint-166/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5fd1ab109b7d10f7a6e6c68e4ba5b03d53a1a59b7256e4663e6a46366b566e8
3
+ size 14645
checkpoint-166/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31db7207a4d153727be1dce003db7174679951f876999d56489d7eb8cb4c921b
3
+ size 1383
checkpoint-166/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa899854d8d59c2d0bdcc6f3f7d0e0dba773881150da4b54aca68ca3bc27b9f4
3
+ size 1465
checkpoint-166/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-166/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "mask_token": "<mask>",
11
+ "model_max_length": 512,
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "tokenizer_class": "RobertaTokenizer",
15
+ "trim_offsets": true,
16
+ "unk_token": "<unk>"
17
+ }
checkpoint-166/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 166,
3
+ "best_metric": 0.262949675321579,
4
+ "best_model_checkpoint": "./math_ner_roberta/checkpoint-166",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 166,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6024096385542169,
14
+ "grad_norm": 4.988605499267578,
15
+ "learning_rate": 2.4096385542168674e-05,
16
+ "loss": 1.4176820373535157,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 0.3655608594417572,
22
+ "eval_runtime": 3.3968,
23
+ "eval_samples_per_second": 68.595,
24
+ "eval_steps_per_second": 4.416,
25
+ "step": 83
26
+ },
27
+ {
28
+ "epoch": 1.2048192771084336,
29
+ "grad_norm": 18.059431076049805,
30
+ "learning_rate": 1.807228915662651e-05,
31
+ "loss": 0.5126217651367188,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 1.8072289156626506,
36
+ "grad_norm": 7.703867435455322,
37
+ "learning_rate": 1.2048192771084337e-05,
38
+ "loss": 0.48525764465332033,
39
+ "step": 150
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "eval_loss": 0.262949675321579,
44
+ "eval_runtime": 3.348,
45
+ "eval_samples_per_second": 69.594,
46
+ "eval_steps_per_second": 4.48,
47
+ "step": 166
48
+ }
49
+ ],
50
+ "logging_steps": 50,
51
+ "max_steps": 249,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 3,
54
+ "save_steps": 500,
55
+ "stateful_callbacks": {
56
+ "TrainerControl": {
57
+ "args": {
58
+ "should_epoch_stop": false,
59
+ "should_evaluate": false,
60
+ "should_log": false,
61
+ "should_save": true,
62
+ "should_training_stop": false
63
+ },
64
+ "attributes": {}
65
+ }
66
+ },
67
+ "total_flos": 496258845421920.0,
68
+ "train_batch_size": 16,
69
+ "trial_name": null,
70
+ "trial_params": null
71
+ }
checkpoint-166/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd60ea97b38a4623de45aa4a7e25eba5b5a79a4f2a0e6f22336cfa15d569d3c7
3
+ size 5265
checkpoint-249/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "-100": "SPECIAL_TOKEN",
16
+ "0": "O",
17
+ "1": "B-ALGEBRA",
18
+ "2": "I-ALGEBRA",
19
+ "3": "B-CALCULUS",
20
+ "4": "I-CALCULUS",
21
+ "5": "B-GEOMETRY",
22
+ "6": "I-GEOMETRY",
23
+ "7": "B-TRIGONOMETRY",
24
+ "8": "I-TRIGONOMETRY"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "is_decoder": false,
29
+ "label2id": {
30
+ "B-ALGEBRA": 1,
31
+ "B-CALCULUS": 3,
32
+ "B-GEOMETRY": 5,
33
+ "B-TRIGONOMETRY": 7,
34
+ "I-ALGEBRA": 2,
35
+ "I-CALCULUS": 4,
36
+ "I-GEOMETRY": 6,
37
+ "I-TRIGONOMETRY": 8,
38
+ "O": 0
39
+ },
40
+ "layer_norm_eps": 1e-05,
41
+ "max_position_embeddings": 514,
42
+ "model_type": "roberta",
43
+ "num_attention_heads": 12,
44
+ "num_hidden_layers": 12,
45
+ "pad_token_id": 1,
46
+ "tie_word_embeddings": true,
47
+ "transformers_version": "5.16.1",
48
+ "type_vocab_size": 1,
49
+ "use_cache": false,
50
+ "vocab_size": 50265
51
+ }
checkpoint-249/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768e54d0330794f5e508204dcdbcba2043808cacb5f14fe66bd1300ae965e09a
3
+ size 496274848
checkpoint-249/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a7bf835dddf484a363c223c59a56cc26790a8719cc1104befe9b254baf8cc8
3
+ size 992671435
checkpoint-249/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1379efe7daea0b258dcf53e5308fd5cc4e1f66284c73ef5c13b370a2b353f14a
3
+ size 14645
checkpoint-249/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125f0452d36c635350302e29b4348f1d745b5396775844dac737c8ed09bd3345
3
+ size 1383
checkpoint-249/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac7447959d5af35f72d507d38527780eb24d94b5aa4cedeb54e3f67fca6bac4
3
+ size 1465
checkpoint-249/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-249/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "mask_token": "<mask>",
11
+ "model_max_length": 512,
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "tokenizer_class": "RobertaTokenizer",
15
+ "trim_offsets": true,
16
+ "unk_token": "<unk>"
17
+ }
checkpoint-249/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 249,
3
+ "best_metric": 0.24590285122394562,
4
+ "best_model_checkpoint": "./math_ner_roberta/checkpoint-249",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 249,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6024096385542169,
14
+ "grad_norm": 4.988605499267578,
15
+ "learning_rate": 2.4096385542168674e-05,
16
+ "loss": 1.4176820373535157,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 0.3655608594417572,
22
+ "eval_runtime": 3.3968,
23
+ "eval_samples_per_second": 68.595,
24
+ "eval_steps_per_second": 4.416,
25
+ "step": 83
26
+ },
27
+ {
28
+ "epoch": 1.2048192771084336,
29
+ "grad_norm": 18.059431076049805,
30
+ "learning_rate": 1.807228915662651e-05,
31
+ "loss": 0.5126217651367188,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 1.8072289156626506,
36
+ "grad_norm": 7.703867435455322,
37
+ "learning_rate": 1.2048192771084337e-05,
38
+ "loss": 0.48525764465332033,
39
+ "step": 150
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "eval_loss": 0.262949675321579,
44
+ "eval_runtime": 3.348,
45
+ "eval_samples_per_second": 69.594,
46
+ "eval_steps_per_second": 4.48,
47
+ "step": 166
48
+ },
49
+ {
50
+ "epoch": 2.4096385542168672,
51
+ "grad_norm": 7.324942111968994,
52
+ "learning_rate": 6.024096385542168e-06,
53
+ "loss": 0.29950580596923826,
54
+ "step": 200
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_loss": 0.24590285122394562,
59
+ "eval_runtime": 3.3559,
60
+ "eval_samples_per_second": 69.431,
61
+ "eval_steps_per_second": 4.47,
62
+ "step": 249
63
+ }
64
+ ],
65
+ "logging_steps": 50,
66
+ "max_steps": 249,
67
+ "num_input_tokens_seen": 0,
68
+ "num_train_epochs": 3,
69
+ "save_steps": 500,
70
+ "stateful_callbacks": {
71
+ "TrainerControl": {
72
+ "args": {
73
+ "should_epoch_stop": false,
74
+ "should_evaluate": false,
75
+ "should_log": false,
76
+ "should_save": true,
77
+ "should_training_stop": true
78
+ },
79
+ "attributes": {}
80
+ }
81
+ },
82
+ "total_flos": 751976629790400.0,
83
+ "train_batch_size": 16,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
checkpoint-249/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd60ea97b38a4623de45aa4a7e25eba5b5a79a4f2a0e6f22336cfa15d569d3c7
3
+ size 5265
checkpoint-83/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "-100": "SPECIAL_TOKEN",
16
+ "0": "O",
17
+ "1": "B-ALGEBRA",
18
+ "2": "I-ALGEBRA",
19
+ "3": "B-CALCULUS",
20
+ "4": "I-CALCULUS",
21
+ "5": "B-GEOMETRY",
22
+ "6": "I-GEOMETRY",
23
+ "7": "B-TRIGONOMETRY",
24
+ "8": "I-TRIGONOMETRY"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "is_decoder": false,
29
+ "label2id": {
30
+ "B-ALGEBRA": 1,
31
+ "B-CALCULUS": 3,
32
+ "B-GEOMETRY": 5,
33
+ "B-TRIGONOMETRY": 7,
34
+ "I-ALGEBRA": 2,
35
+ "I-CALCULUS": 4,
36
+ "I-GEOMETRY": 6,
37
+ "I-TRIGONOMETRY": 8,
38
+ "O": 0
39
+ },
40
+ "layer_norm_eps": 1e-05,
41
+ "max_position_embeddings": 514,
42
+ "model_type": "roberta",
43
+ "num_attention_heads": 12,
44
+ "num_hidden_layers": 12,
45
+ "pad_token_id": 1,
46
+ "tie_word_embeddings": true,
47
+ "transformers_version": "5.16.1",
48
+ "type_vocab_size": 1,
49
+ "use_cache": false,
50
+ "vocab_size": 50265
51
+ }
checkpoint-83/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52946567425d3a770b96ebb3441dcc04d416a2faa19be69a3c7abc974e58350c
3
+ size 496274848
checkpoint-83/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a03afb8a2f3ac21200f2f109ef25deab3635381beb237291cab6212f88732c
3
+ size 992671435
checkpoint-83/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96a02a4adbf6d5a3a3212b7bc086c4baa7f79abebe76c19b4c214eefe832964
3
+ size 14645
checkpoint-83/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e41be3311ca5df3a441f941b057a5aab6e6a9bff7f09dd2125a0c9d88024230
3
+ size 1383
checkpoint-83/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e47271aef9f3c2b561eb454416f7cf0d0d6980885d76081006cb87b8212750c
3
+ size 1465
checkpoint-83/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-83/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "mask_token": "<mask>",
11
+ "model_max_length": 512,
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "tokenizer_class": "RobertaTokenizer",
15
+ "trim_offsets": true,
16
+ "unk_token": "<unk>"
17
+ }
checkpoint-83/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 83,
3
+ "best_metric": 0.3655608594417572,
4
+ "best_model_checkpoint": "./math_ner_roberta/checkpoint-83",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 83,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6024096385542169,
14
+ "grad_norm": 4.988605499267578,
15
+ "learning_rate": 2.4096385542168674e-05,
16
+ "loss": 1.4176820373535157,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 0.3655608594417572,
22
+ "eval_runtime": 3.3968,
23
+ "eval_samples_per_second": 68.595,
24
+ "eval_steps_per_second": 4.416,
25
+ "step": 83
26
+ }
27
+ ],
28
+ "logging_steps": 50,
29
+ "max_steps": 249,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 3,
32
+ "save_steps": 500,
33
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": false
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 247812985784160.0,
46
+ "train_batch_size": 16,
47
+ "trial_name": null,
48
+ "trial_params": null
49
+ }
checkpoint-83/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd60ea97b38a4623de45aa4a7e25eba5b5a79a4f2a0e6f22336cfa15d569d3c7
3
+ size 5265