Hugging Face's logo

Spaces:
isana25
/
DoctorTwin
Sleeping

App Files Community
isana25 commited on
Commit
13627cb
·
verified ·
1 Parent(s): 01f7e8c

Upload 23 files

Browse files
Files changed (23) hide show
  1. bert_mini_squadv2_finetuned/.DS_Store +0 -0
  2. bert_mini_squadv2_finetuned/checkpoint-190/config.json +24 -0
  3. bert_mini_squadv2_finetuned/checkpoint-190/model.safetensors +3 -0
  4. bert_mini_squadv2_finetuned/checkpoint-190/optimizer.pt +3 -0
  5. bert_mini_squadv2_finetuned/checkpoint-190/rng_state.pth +3 -0
  6. bert_mini_squadv2_finetuned/checkpoint-190/scheduler.pt +3 -0
  7. bert_mini_squadv2_finetuned/checkpoint-190/special_tokens_map.json +7 -0
  8. bert_mini_squadv2_finetuned/checkpoint-190/tokenizer.json +0 -0
  9. bert_mini_squadv2_finetuned/checkpoint-190/tokenizer_config.json +58 -0
  10. bert_mini_squadv2_finetuned/checkpoint-190/trainer_state.json +175 -0
  11. bert_mini_squadv2_finetuned/checkpoint-190/training_args.bin +3 -0
  12. bert_mini_squadv2_finetuned/checkpoint-190/vocab.txt +0 -0
  13. bert_mini_squadv2_finetuned/checkpoint-380/config.json +24 -0
  14. bert_mini_squadv2_finetuned/checkpoint-380/model.safetensors +3 -0
  15. bert_mini_squadv2_finetuned/checkpoint-380/optimizer.pt +3 -0
  16. bert_mini_squadv2_finetuned/checkpoint-380/rng_state.pth +3 -0
  17. bert_mini_squadv2_finetuned/checkpoint-380/scheduler.pt +3 -0
  18. bert_mini_squadv2_finetuned/checkpoint-380/special_tokens_map.json +7 -0
  19. bert_mini_squadv2_finetuned/checkpoint-380/tokenizer.json +0 -0
  20. bert_mini_squadv2_finetuned/checkpoint-380/tokenizer_config.json +58 -0
  21. bert_mini_squadv2_finetuned/checkpoint-380/trainer_state.json +316 -0
  22. bert_mini_squadv2_finetuned/checkpoint-380/training_args.bin +3 -0
  23. bert_mini_squadv2_finetuned/checkpoint-380/vocab.txt +0 -0
bert_mini_squadv2_finetuned/.DS_Store ADDED
Binary file (6.15 kB). View file
 
bert_mini_squadv2_finetuned/checkpoint-190/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForQuestionAnswering"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 1024,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 4,
16
+ "num_hidden_layers": 4,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.51.3",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
bert_mini_squadv2_finetuned/checkpoint-190/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a95d1d7544acae67ac4c047b04ca93af3e3789438993fbb8ae5a3c792d85c4
3
+ size 44429248
bert_mini_squadv2_finetuned/checkpoint-190/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a703edc5c197369b17f21e514bccc61a528d7699fe52c1b4596e149a9c10e0b2
3
+ size 88899962
bert_mini_squadv2_finetuned/checkpoint-190/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59565d1cac8a23c1223dbfea9c7121252bfc33172e5301f81ff1451da8a23f98
3
+ size 13990
bert_mini_squadv2_finetuned/checkpoint-190/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529dc0afd82e0bc122714706eb37b613be15cc5632d08d955bf6906ab68e92fd
3
+ size 1064
bert_mini_squadv2_finetuned/checkpoint-190/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
bert_mini_squadv2_finetuned/checkpoint-190/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
bert_mini_squadv2_finetuned/checkpoint-190/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
bert_mini_squadv2_finetuned/checkpoint-190/trainer_state.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 190,
3
+ "best_metric": 3.1472160816192627,
4
+ "best_model_checkpoint": "./bert_mini_squadv2_finetuned/checkpoint-190",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 190,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.05263157894736842,
14
+ "grad_norm": 4.97021484375,
15
+ "learning_rate": 1.9526315789473688e-05,
16
+ "loss": 5.8799,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.10526315789473684,
21
+ "grad_norm": 5.308949947357178,
22
+ "learning_rate": 1.9e-05,
23
+ "loss": 5.6001,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.15789473684210525,
28
+ "grad_norm": 5.93297004699707,
29
+ "learning_rate": 1.8473684210526317e-05,
30
+ "loss": 5.356,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.21052631578947367,
35
+ "grad_norm": 6.4546613693237305,
36
+ "learning_rate": 1.7947368421052634e-05,
37
+ "loss": 5.0317,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.2631578947368421,
42
+ "grad_norm": 6.0348734855651855,
43
+ "learning_rate": 1.742105263157895e-05,
44
+ "loss": 4.8894,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.3157894736842105,
49
+ "grad_norm": 7.766897201538086,
50
+ "learning_rate": 1.6894736842105263e-05,
51
+ "loss": 4.5613,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.3684210526315789,
56
+ "grad_norm": 6.935646057128906,
57
+ "learning_rate": 1.636842105263158e-05,
58
+ "loss": 4.4883,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.42105263157894735,
63
+ "grad_norm": 6.82500696182251,
64
+ "learning_rate": 1.5842105263157896e-05,
65
+ "loss": 4.2883,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.47368421052631576,
70
+ "grad_norm": 7.159075736999512,
71
+ "learning_rate": 1.5315789473684212e-05,
72
+ "loss": 4.165,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.5263157894736842,
77
+ "grad_norm": 7.179778575897217,
78
+ "learning_rate": 1.4789473684210527e-05,
79
+ "loss": 4.1544,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.5789473684210527,
84
+ "grad_norm": 7.615407943725586,
85
+ "learning_rate": 1.4263157894736843e-05,
86
+ "loss": 3.9639,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.631578947368421,
91
+ "grad_norm": 8.331777572631836,
92
+ "learning_rate": 1.373684210526316e-05,
93
+ "loss": 3.9313,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.6842105263157895,
98
+ "grad_norm": 8.408103942871094,
99
+ "learning_rate": 1.3210526315789476e-05,
100
+ "loss": 3.8429,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.7368421052631579,
105
+ "grad_norm": 7.173701286315918,
106
+ "learning_rate": 1.268421052631579e-05,
107
+ "loss": 3.8753,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.7894736842105263,
112
+ "grad_norm": 8.077372550964355,
113
+ "learning_rate": 1.2157894736842107e-05,
114
+ "loss": 3.726,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.8421052631578947,
119
+ "grad_norm": 8.297250747680664,
120
+ "learning_rate": 1.1631578947368423e-05,
121
+ "loss": 3.7247,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.8947368421052632,
126
+ "grad_norm": 8.952900886535645,
127
+ "learning_rate": 1.1105263157894736e-05,
128
+ "loss": 3.5831,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.9473684210526315,
133
+ "grad_norm": 7.744213581085205,
134
+ "learning_rate": 1.0578947368421053e-05,
135
+ "loss": 3.6806,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 1.0,
140
+ "grad_norm": 8.072354316711426,
141
+ "learning_rate": 1.005263157894737e-05,
142
+ "loss": 3.6219,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 1.0,
147
+ "eval_loss": 3.1472160816192627,
148
+ "eval_runtime": 33.3578,
149
+ "eval_samples_per_second": 15.259,
150
+ "eval_steps_per_second": 0.959,
151
+ "step": 190
152
+ }
153
+ ],
154
+ "logging_steps": 10,
155
+ "max_steps": 380,
156
+ "num_input_tokens_seen": 0,
157
+ "num_train_epochs": 2,
158
+ "save_steps": 500,
159
+ "stateful_callbacks": {
160
+ "TrainerControl": {
161
+ "args": {
162
+ "should_epoch_stop": false,
163
+ "should_evaluate": false,
164
+ "should_log": false,
165
+ "should_save": true,
166
+ "should_training_stop": false
167
+ },
168
+ "attributes": {}
169
+ }
170
+ },
171
+ "total_flos": 22104484706304.0,
172
+ "train_batch_size": 16,
173
+ "trial_name": null,
174
+ "trial_params": null
175
+ }
bert_mini_squadv2_finetuned/checkpoint-190/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a9a14d556c611be72d9d9aa9c812277950ece42f7330882cb64e1642a447a5
3
+ size 5240
bert_mini_squadv2_finetuned/checkpoint-190/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
bert_mini_squadv2_finetuned/checkpoint-380/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForQuestionAnswering"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 1024,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 4,
16
+ "num_hidden_layers": 4,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.51.3",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
bert_mini_squadv2_finetuned/checkpoint-380/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd85270e30d38d4232955e62efb9bc84649d52f11d49f621db38cba439aced9d
3
+ size 44429248
bert_mini_squadv2_finetuned/checkpoint-380/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba2e7f7b1ee8914bc14297aca535ba75ee90dca1ef6eb89a9b16855ee9cd0227
3
+ size 88899962
bert_mini_squadv2_finetuned/checkpoint-380/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6db0114ed51724dab0a897ce469f57c1ffe627efd12f30fe2eaaa52d6d23e91
3
+ size 13990
bert_mini_squadv2_finetuned/checkpoint-380/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127b2719fa7b876792e4457c5d329d887a1c95fb5205db9f770c4a98846e056a
3
+ size 1064
bert_mini_squadv2_finetuned/checkpoint-380/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
bert_mini_squadv2_finetuned/checkpoint-380/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
bert_mini_squadv2_finetuned/checkpoint-380/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
bert_mini_squadv2_finetuned/checkpoint-380/trainer_state.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 380,
3
+ "best_metric": 2.9931933879852295,
4
+ "best_model_checkpoint": "./bert_mini_squadv2_finetuned/checkpoint-380",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 380,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.05263157894736842,
14
+ "grad_norm": 4.97021484375,
15
+ "learning_rate": 1.9526315789473688e-05,
16
+ "loss": 5.8799,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.10526315789473684,
21
+ "grad_norm": 5.308949947357178,
22
+ "learning_rate": 1.9e-05,
23
+ "loss": 5.6001,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.15789473684210525,
28
+ "grad_norm": 5.93297004699707,
29
+ "learning_rate": 1.8473684210526317e-05,
30
+ "loss": 5.356,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.21052631578947367,
35
+ "grad_norm": 6.4546613693237305,
36
+ "learning_rate": 1.7947368421052634e-05,
37
+ "loss": 5.0317,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.2631578947368421,
42
+ "grad_norm": 6.0348734855651855,
43
+ "learning_rate": 1.742105263157895e-05,
44
+ "loss": 4.8894,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.3157894736842105,
49
+ "grad_norm": 7.766897201538086,
50
+ "learning_rate": 1.6894736842105263e-05,
51
+ "loss": 4.5613,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.3684210526315789,
56
+ "grad_norm": 6.935646057128906,
57
+ "learning_rate": 1.636842105263158e-05,
58
+ "loss": 4.4883,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.42105263157894735,
63
+ "grad_norm": 6.82500696182251,
64
+ "learning_rate": 1.5842105263157896e-05,
65
+ "loss": 4.2883,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.47368421052631576,
70
+ "grad_norm": 7.159075736999512,
71
+ "learning_rate": 1.5315789473684212e-05,
72
+ "loss": 4.165,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.5263157894736842,
77
+ "grad_norm": 7.179778575897217,
78
+ "learning_rate": 1.4789473684210527e-05,
79
+ "loss": 4.1544,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.5789473684210527,
84
+ "grad_norm": 7.615407943725586,
85
+ "learning_rate": 1.4263157894736843e-05,
86
+ "loss": 3.9639,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.631578947368421,
91
+ "grad_norm": 8.331777572631836,
92
+ "learning_rate": 1.373684210526316e-05,
93
+ "loss": 3.9313,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.6842105263157895,
98
+ "grad_norm": 8.408103942871094,
99
+ "learning_rate": 1.3210526315789476e-05,
100
+ "loss": 3.8429,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.7368421052631579,
105
+ "grad_norm": 7.173701286315918,
106
+ "learning_rate": 1.268421052631579e-05,
107
+ "loss": 3.8753,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.7894736842105263,
112
+ "grad_norm": 8.077372550964355,
113
+ "learning_rate": 1.2157894736842107e-05,
114
+ "loss": 3.726,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.8421052631578947,
119
+ "grad_norm": 8.297250747680664,
120
+ "learning_rate": 1.1631578947368423e-05,
121
+ "loss": 3.7247,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.8947368421052632,
126
+ "grad_norm": 8.952900886535645,
127
+ "learning_rate": 1.1105263157894736e-05,
128
+ "loss": 3.5831,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.9473684210526315,
133
+ "grad_norm": 7.744213581085205,
134
+ "learning_rate": 1.0578947368421053e-05,
135
+ "loss": 3.6806,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 1.0,
140
+ "grad_norm": 8.072354316711426,
141
+ "learning_rate": 1.005263157894737e-05,
142
+ "loss": 3.6219,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 1.0,
147
+ "eval_loss": 3.1472160816192627,
148
+ "eval_runtime": 33.3578,
149
+ "eval_samples_per_second": 15.259,
150
+ "eval_steps_per_second": 0.959,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 1.0526315789473684,
155
+ "grad_norm": 8.19955825805664,
156
+ "learning_rate": 9.526315789473684e-06,
157
+ "loss": 3.6322,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 1.1052631578947367,
162
+ "grad_norm": 9.592784881591797,
163
+ "learning_rate": 9e-06,
164
+ "loss": 3.4887,
165
+ "step": 210
166
+ },
167
+ {
168
+ "epoch": 1.1578947368421053,
169
+ "grad_norm": 10.357446670532227,
170
+ "learning_rate": 8.473684210526317e-06,
171
+ "loss": 3.468,
172
+ "step": 220
173
+ },
174
+ {
175
+ "epoch": 1.2105263157894737,
176
+ "grad_norm": 9.067779541015625,
177
+ "learning_rate": 7.947368421052633e-06,
178
+ "loss": 3.7465,
179
+ "step": 230
180
+ },
181
+ {
182
+ "epoch": 1.263157894736842,
183
+ "grad_norm": 8.634210586547852,
184
+ "learning_rate": 7.421052631578948e-06,
185
+ "loss": 3.2895,
186
+ "step": 240
187
+ },
188
+ {
189
+ "epoch": 1.3157894736842106,
190
+ "grad_norm": 7.1132941246032715,
191
+ "learning_rate": 6.894736842105264e-06,
192
+ "loss": 3.6037,
193
+ "step": 250
194
+ },
195
+ {
196
+ "epoch": 1.368421052631579,
197
+ "grad_norm": 8.3925142288208,
198
+ "learning_rate": 6.3684210526315795e-06,
199
+ "loss": 3.4975,
200
+ "step": 260
201
+ },
202
+ {
203
+ "epoch": 1.4210526315789473,
204
+ "grad_norm": 8.534266471862793,
205
+ "learning_rate": 5.842105263157896e-06,
206
+ "loss": 3.4788,
207
+ "step": 270
208
+ },
209
+ {
210
+ "epoch": 1.4736842105263157,
211
+ "grad_norm": 10.572562217712402,
212
+ "learning_rate": 5.315789473684211e-06,
213
+ "loss": 3.7405,
214
+ "step": 280
215
+ },
216
+ {
217
+ "epoch": 1.526315789473684,
218
+ "grad_norm": 8.039414405822754,
219
+ "learning_rate": 4.789473684210527e-06,
220
+ "loss": 3.4092,
221
+ "step": 290
222
+ },
223
+ {
224
+ "epoch": 1.5789473684210527,
225
+ "grad_norm": 8.852104187011719,
226
+ "learning_rate": 4.2631578947368425e-06,
227
+ "loss": 3.5734,
228
+ "step": 300
229
+ },
230
+ {
231
+ "epoch": 1.631578947368421,
232
+ "grad_norm": 9.102316856384277,
233
+ "learning_rate": 3.736842105263158e-06,
234
+ "loss": 3.3341,
235
+ "step": 310
236
+ },
237
+ {
238
+ "epoch": 1.6842105263157894,
239
+ "grad_norm": 8.393866539001465,
240
+ "learning_rate": 3.210526315789474e-06,
241
+ "loss": 3.3955,
242
+ "step": 320
243
+ },
244
+ {
245
+ "epoch": 1.736842105263158,
246
+ "grad_norm": 9.89341926574707,
247
+ "learning_rate": 2.68421052631579e-06,
248
+ "loss": 3.4553,
249
+ "step": 330
250
+ },
251
+ {
252
+ "epoch": 1.7894736842105263,
253
+ "grad_norm": 9.145729064941406,
254
+ "learning_rate": 2.1578947368421054e-06,
255
+ "loss": 3.4255,
256
+ "step": 340
257
+ },
258
+ {
259
+ "epoch": 1.8421052631578947,
260
+ "grad_norm": 8.320271492004395,
261
+ "learning_rate": 1.6315789473684212e-06,
262
+ "loss": 3.1645,
263
+ "step": 350
264
+ },
265
+ {
266
+ "epoch": 1.8947368421052633,
267
+ "grad_norm": 10.283031463623047,
268
+ "learning_rate": 1.1052631578947369e-06,
269
+ "loss": 3.3179,
270
+ "step": 360
271
+ },
272
+ {
273
+ "epoch": 1.9473684210526314,
274
+ "grad_norm": 11.425944328308105,
275
+ "learning_rate": 5.789473684210526e-07,
276
+ "loss": 3.2488,
277
+ "step": 370
278
+ },
279
+ {
280
+ "epoch": 2.0,
281
+ "grad_norm": 9.913457870483398,
282
+ "learning_rate": 5.263157894736842e-08,
283
+ "loss": 3.5268,
284
+ "step": 380
285
+ },
286
+ {
287
+ "epoch": 2.0,
288
+ "eval_loss": 2.9931933879852295,
289
+ "eval_runtime": 34.157,
290
+ "eval_samples_per_second": 14.902,
291
+ "eval_steps_per_second": 0.937,
292
+ "step": 380
293
+ }
294
+ ],
295
+ "logging_steps": 10,
296
+ "max_steps": 380,
297
+ "num_input_tokens_seen": 0,
298
+ "num_train_epochs": 2,
299
+ "save_steps": 500,
300
+ "stateful_callbacks": {
301
+ "TrainerControl": {
302
+ "args": {
303
+ "should_epoch_stop": false,
304
+ "should_evaluate": false,
305
+ "should_log": false,
306
+ "should_save": true,
307
+ "should_training_stop": true
308
+ },
309
+ "attributes": {}
310
+ }
311
+ },
312
+ "total_flos": 44208969412608.0,
313
+ "train_batch_size": 16,
314
+ "trial_name": null,
315
+ "trial_params": null
316
+ }
bert_mini_squadv2_finetuned/checkpoint-380/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a9a14d556c611be72d9d9aa9c812277950ece42f7330882cb64e1642a447a5
3
+ size 5240
bert_mini_squadv2_finetuned/checkpoint-380/vocab.txt ADDED
The diff for this file is too large to render. See raw diff