Hugging Face's logo

Ouafae
/
qa_finetuning

TensorBoard
Safetensors
distilbert
Model card Files Metrics Community
Ouafae commited on
Commit
50ad384
·
verified ·
1 Parent(s): 7a955cf

Training in progress, step 500

Browse files
Files changed (19) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-500/config.json +24 -0
  3. run-0/checkpoint-500/model.safetensors +3 -0
  4. run-0/checkpoint-500/optimizer.pt +3 -0
  5. run-0/checkpoint-500/rng_state.pth +3 -0
  6. run-0/checkpoint-500/scheduler.pt +3 -0
  7. run-0/checkpoint-500/special_tokens_map.json +7 -0
  8. run-0/checkpoint-500/tokenizer.json +0 -0
  9. run-0/checkpoint-500/tokenizer_config.json +55 -0
  10. run-0/checkpoint-500/trainer_state.json +122 -0
  11. run-0/checkpoint-500/training_args.bin +3 -0
  12. run-0/checkpoint-500/vocab.txt +0 -0
  13. runs/Nov18_09-36-44_aa151f0a91fc/events.out.tfevents.1731922946.aa151f0a91fc.30.1 +3 -0
  14. runs/Nov18_09-49-00_aa151f0a91fc/events.out.tfevents.1731923341.aa151f0a91fc.30.2 +3 -0
  15. runs/Nov18_09-50-02_aa151f0a91fc/events.out.tfevents.1731923403.aa151f0a91fc.30.3 +3 -0
  16. runs/Nov18_09-51-19_aa151f0a91fc/events.out.tfevents.1731923480.aa151f0a91fc.30.4 +3 -0
  17. runs/Nov18_09-51-50_aa151f0a91fc/events.out.tfevents.1731923511.aa151f0a91fc.30.5 +3 -0
  18. runs/Nov18_10-11-09_aa151f0a91fc/events.out.tfevents.1731924671.aa151f0a91fc.1516.0 +3 -0
  19. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4cc33b8d0b52dcf2a12f056d1fcef90253d2526a82e2e0ad9738277ef4b90bd
3
  size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22334d74c5c733e93aef36f260a94ab7568cee484898d6633c4c2a40e0aee116
3
  size 265470032
run-0/checkpoint-500/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.45.1",
23
+ "vocab_size": 30522
24
+ }
run-0/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22334d74c5c733e93aef36f260a94ab7568cee484898d6633c4c2a40e0aee116
3
+ size 265470032
run-0/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f8790bee27f0911b59b0308921dfbc40d9e05d08b063fdb7401cf6042c4e0ca
3
+ size 531000890
run-0/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0079ea12c60f90aac1c2706b779080ae98d89d1838648a9488ea409925f0e165
3
+ size 14308
run-0/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f08bb70ff0d7f2842e554449bf414c55bddfcc0ec916880890493b75e9e6339
3
+ size 1064
run-0/checkpoint-500/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
+ }
run-0/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-500/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": false,
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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.5879857540130615,
3
+ "best_model_checkpoint": "qa_finetuning/run-0/checkpoint-500",
4
+ "epoch": 1.5974440894568689,
5
+ "eval_steps": 100,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.3194888178913738,
13
+ "grad_norm": 4.872162818908691,
14
+ "learning_rate": 2.2236495574546495e-06,
15
+ "loss": 5.793,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.3194888178913738,
20
+ "eval_loss": 5.499853610992432,
21
+ "eval_runtime": 3.4844,
22
+ "eval_samples_per_second": 143.499,
23
+ "eval_steps_per_second": 4.592,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.6389776357827476,
28
+ "grad_norm": 5.640169620513916,
29
+ "learning_rate": 2.0718646047273696e-06,
30
+ "loss": 5.1611,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.6389776357827476,
35
+ "eval_loss": 4.561793327331543,
36
+ "eval_runtime": 3.7947,
37
+ "eval_samples_per_second": 131.764,
38
+ "eval_steps_per_second": 4.216,
39
+ "step": 200
40
+ },
41
+ {
42
+ "epoch": 0.9584664536741214,
43
+ "grad_norm": 6.388542175292969,
44
+ "learning_rate": 1.9200796520000897e-06,
45
+ "loss": 4.4606,
46
+ "step": 300
47
+ },
48
+ {
49
+ "epoch": 0.9584664536741214,
50
+ "eval_loss": 4.023355960845947,
51
+ "eval_runtime": 3.583,
52
+ "eval_samples_per_second": 139.546,
53
+ "eval_steps_per_second": 4.465,
54
+ "step": 300
55
+ },
56
+ {
57
+ "epoch": 1.2779552715654952,
58
+ "grad_norm": 7.301818370819092,
59
+ "learning_rate": 1.76829469927281e-06,
60
+ "loss": 4.0751,
61
+ "step": 400
62
+ },
63
+ {
64
+ "epoch": 1.2779552715654952,
65
+ "eval_loss": 3.76656436920166,
66
+ "eval_runtime": 3.7005,
67
+ "eval_samples_per_second": 135.118,
68
+ "eval_steps_per_second": 4.324,
69
+ "step": 400
70
+ },
71
+ {
72
+ "epoch": 1.5974440894568689,
73
+ "grad_norm": 9.462298393249512,
74
+ "learning_rate": 1.61650974654553e-06,
75
+ "loss": 3.8854,
76
+ "step": 500
77
+ },
78
+ {
79
+ "epoch": 1.5974440894568689,
80
+ "eval_loss": 3.5879857540130615,
81
+ "eval_runtime": 3.6179,
82
+ "eval_samples_per_second": 138.201,
83
+ "eval_steps_per_second": 4.422,
84
+ "step": 500
85
+ }
86
+ ],
87
+ "logging_steps": 100,
88
+ "max_steps": 1565,
89
+ "num_input_tokens_seen": 0,
90
+ "num_train_epochs": 5,
91
+ "save_steps": 500,
92
+ "stateful_callbacks": {
93
+ "EarlyStoppingCallback": {
94
+ "args": {
95
+ "early_stopping_patience": 3,
96
+ "early_stopping_threshold": 0.0
97
+ },
98
+ "attributes": {
99
+ "early_stopping_patience_counter": 0
100
+ }
101
+ },
102
+ "TrainerControl": {
103
+ "args": {
104
+ "should_epoch_stop": false,
105
+ "should_evaluate": false,
106
+ "should_log": false,
107
+ "should_save": true,
108
+ "should_training_stop": false
109
+ },
110
+ "attributes": {}
111
+ }
112
+ },
113
+ "total_flos": 783134681591808.0,
114
+ "train_batch_size": 16,
115
+ "trial_name": null,
116
+ "trial_params": {
117
+ "learning_rate": 2.3754345101819293e-06,
118
+ "num_train_epochs": 5,
119
+ "per_device_train_batch_size": 8,
120
+ "seed": 31
121
+ }
122
+ }
run-0/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ef1379406259e48f9c8943dd50b0a6da2c00398967a46798f218c876807a1f
3
+ size 5176
run-0/checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Nov18_09-36-44_aa151f0a91fc/events.out.tfevents.1731922946.aa151f0a91fc.30.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4eeaf858f711497d81c86f6e35a498be64d19d6141d8b467e9e8d2b666cd1e7
3
+ size 4832
runs/Nov18_09-49-00_aa151f0a91fc/events.out.tfevents.1731923341.aa151f0a91fc.30.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6943c48c40e9002ca64da1c3cac85e2819918287b4cbf6f6d85574dca0d08feb
3
+ size 4839
runs/Nov18_09-50-02_aa151f0a91fc/events.out.tfevents.1731923403.aa151f0a91fc.30.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4781d7b8da4d4920638f7f1241c2067d1a2f10e5dd1177a0cf54ad93bb1d817
3
+ size 4872
runs/Nov18_09-51-19_aa151f0a91fc/events.out.tfevents.1731923480.aa151f0a91fc.30.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eede621b545755ad70c7c88f202b3b4b8101cf755aba83c6191d2c421d84668
3
+ size 4888
runs/Nov18_09-51-50_aa151f0a91fc/events.out.tfevents.1731923511.aa151f0a91fc.30.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf9cfff6ab2352a5c8d3efe6d1368399b0e37c7f3d1db62e154bfa653b9a8a0
3
+ size 4887
runs/Nov18_10-11-09_aa151f0a91fc/events.out.tfevents.1731924671.aa151f0a91fc.1516.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd21cce020de441d61b16d2f5cea6bd966503e50943c7664c7477669919ba0a
3
+ size 7272
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:402b2439b600ffbf748e5b356349c52da746deb8c130785c86fd777ae8904832
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ef1379406259e48f9c8943dd50b0a6da2c00398967a46798f218c876807a1f
3
  size 5176