Hugging Face's logo

leomaurodesenv
/
bert-basketball-qa

Question Answering
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
leomaurodesenv commited on
Commit
ccc6b3e
路
verified 路
1 Parent(s): c88853d

feat: add tokenizer

Browse files
Files changed (9) hide show
  1. checkpoint-200/model.safetensors +1 -1
  2. checkpoint-200/optimizer.pt +1 -1
  3. checkpoint-200/rng_state.pth +1 -1
  4. checkpoint-200/special_tokens_map.json +37 -0
  5. checkpoint-200/tokenizer.json +0 -0
  6. checkpoint-200/tokenizer_config.json +56 -0
  7. checkpoint-200/trainer_state.json +59 -9
  8. checkpoint-200/training_args.bin +1 -1
  9. checkpoint-200/vocab.txt +0 -0
checkpoint-200/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de45ab94e2b2f5bb17dc9f63277f3b556dc10ea9b563eee8047d1e255df8961e
3
  size 435596088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3073915012bf42dbcb789033d68162966442f9fa97006a5ae84e8d7634c694c
3
  size 435596088
checkpoint-200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a2b8a4659cb7c8ec633781056acfd02d3e082a550a026abe1d91455d1407455
3
  size 871311930
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51f03950fe603a064a2a800ffd98577029f7173e11c16b27f8b1a70abc228e4
3
  size 871311930
checkpoint-200/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddfcf7dfe961c2039ec7f4b7072495318a15a902be3ae4d0fe5ca93681ab772d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b8db646d3c3262b539b2723691b384848145fb3315df90e1eff20ea1d98f34
3
  size 14244
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-200/trainer_state.json CHANGED
@@ -1,30 +1,80 @@
1
  {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
  "epoch": 100.0,
6
- "eval_steps": 500,
7
  "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
 
 
 
 
 
 
 
12
  {
13
  "epoch": 50.0,
14
- "grad_norm": 0.030773935839533806,
15
  "learning_rate": 5e-06,
16
- "loss": 0.1023,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  "step": 100
18
  },
 
 
 
 
 
 
 
19
  {
20
  "epoch": 100.0,
21
- "grad_norm": 0.011482714675366879,
22
  "learning_rate": 0.0,
23
- "loss": 0.0009,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  "step": 200
25
  }
26
  ],
27
- "logging_steps": 100,
28
  "max_steps": 200,
29
  "num_input_tokens_seen": 0,
30
  "num_train_epochs": 100,
 
1
  {
2
+ "best_global_step": 200,
3
+ "best_metric": 81.93050193050193,
4
+ "best_model_checkpoint": "bert-basketball-qa/checkpoint-200",
5
  "epoch": 100.0,
6
+ "eval_steps": 100,
7
  "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
+ {
13
+ "epoch": 25.0,
14
+ "grad_norm": 6.94656337145716e-05,
15
+ "learning_rate": 7.500000000000001e-06,
16
+ "loss": 0.0,
17
+ "step": 50
18
+ },
19
  {
20
  "epoch": 50.0,
21
+ "grad_norm": 5.321024218574166e-05,
22
  "learning_rate": 5e-06,
23
+ "loss": 0.0,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 50.0,
28
+ "eval_HasAns_exact": 76.47058823529412,
29
+ "eval_HasAns_f1": 80.65599212658037,
30
+ "eval_HasAns_total": 68,
31
+ "eval_best_exact": 76.47058823529412,
32
+ "eval_best_exact_thresh": 0.0,
33
+ "eval_best_f1": 80.65599212658037,
34
+ "eval_best_f1_thresh": 0.0,
35
+ "eval_exact": 76.47058823529412,
36
+ "eval_f1": 80.65599212658037,
37
+ "eval_loss": 2.25223708152771,
38
+ "eval_runtime": 1.2791,
39
+ "eval_samples_per_second": 53.163,
40
+ "eval_steps_per_second": 3.909,
41
+ "eval_total": 68,
42
  "step": 100
43
  },
44
+ {
45
+ "epoch": 75.0,
46
+ "grad_norm": 5.5171589337987825e-05,
47
+ "learning_rate": 2.5e-06,
48
+ "loss": 0.0001,
49
+ "step": 150
50
+ },
51
  {
52
  "epoch": 100.0,
53
+ "grad_norm": 5.7267650845460594e-05,
54
  "learning_rate": 0.0,
55
+ "loss": 0.0,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 100.0,
60
+ "eval_HasAns_exact": 77.94117647058823,
61
+ "eval_HasAns_f1": 81.93050193050193,
62
+ "eval_HasAns_total": 68,
63
+ "eval_best_exact": 77.94117647058823,
64
+ "eval_best_exact_thresh": 0.0,
65
+ "eval_best_f1": 81.93050193050193,
66
+ "eval_best_f1_thresh": 0.0,
67
+ "eval_exact": 77.94117647058823,
68
+ "eval_f1": 81.93050193050193,
69
+ "eval_loss": 2.152153491973877,
70
+ "eval_runtime": 1.3599,
71
+ "eval_samples_per_second": 50.003,
72
+ "eval_steps_per_second": 3.677,
73
+ "eval_total": 68,
74
  "step": 200
75
  }
76
  ],
77
+ "logging_steps": 50,
78
  "max_steps": 200,
79
  "num_input_tokens_seen": 0,
80
  "num_train_epochs": 100,
checkpoint-200/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bf8253242f047a78de69386b37d54d7bdf23c1d3d473fd0207e2a42b1095ea0
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6965711c3080d1534eb6998d0eef12da1e8225178a797d7c50d29f830fbffcf2
3
  size 5304
checkpoint-200/vocab.txt ADDED
The diff for this file is too large to render. See raw diff