Hugging Face's logo

dccuchile
/
bertin-roberta-base-spanish-finetuned-qa-sqac

Question Answering
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
josecannete commited on
Commit
ecb4914
•
1 Parent(s): 9f0da00

adding model finetuned on sqac

Browse files
Files changed (14) hide show
  1. all_results.json +11 -0
  2. config.json +28 -0
  3. eval_nbest_predictions.json +0 -0
  4. eval_predictions.json +0 -0
  5. eval_results.json +6 -0
  6. merges.txt +0 -0
  7. pytorch_model.bin +3 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +65 -0
  11. train_results.json +8 -0
  12. trainer_state.json +109 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_exact_match": 62.5,
4
+ "eval_f1": 80.15398176853643,
5
+ "eval_samples": 2077,
6
+ "train_loss": 0.9571071643184349,
7
+ "train_runtime": 543.2284,
8
+ "train_samples": 16548,
9
+ "train_samples_per_second": 60.925,
10
+ "train_steps_per_second": 3.811
11
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bertin-project/bertin-roberta-base-spanish",
3
+ "architectures": [
4
+ "RobertaForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.22.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50262
28
+ }
eval_nbest_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_exact_match": 62.5,
4
+ "eval_f1": 80.15398176853643,
5
+ "eval_samples": 2077
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81715d8e5195eedc0be6773bc709a70d9c9a3299dbe089167de5a15efd89017
3
+ size 496288177
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "max_len": 512,
37
+ "name_or_path": "bertin-project/bertin-roberta-base-spanish",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": null,
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.9571071643184349,
4
+ "train_runtime": 543.2284,
5
+ "train_samples": 16548,
6
+ "train_samples_per_second": 60.925,
7
+ "train_steps_per_second": 3.811
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 80.15398176853643,
3
+ "best_model_checkpoint": "/home/jcanete/ft-data/all_results/sqac/bertin_roberta_base/epochs_2_bs_16_lr_3e-5/checkpoint-2000",
4
+ "epoch": 2.0,
5
+ "global_step": 2070,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.19,
12
+ "eval_exact_match": 44.527896995708154,
13
+ "eval_f1": 65.6105308029204,
14
+ "step": 200
15
+ },
16
+ {
17
+ "epoch": 0.39,
18
+ "eval_exact_match": 53.487124463519315,
19
+ "eval_f1": 72.463429226185,
20
+ "step": 400
21
+ },
22
+ {
23
+ "epoch": 0.48,
24
+ "learning_rate": 2.279710144927536e-05,
25
+ "loss": 2.0283,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 0.58,
30
+ "eval_exact_match": 55.472103004291846,
31
+ "eval_f1": 73.77270325735508,
32
+ "step": 600
33
+ },
34
+ {
35
+ "epoch": 0.77,
36
+ "eval_exact_match": 59.38841201716738,
37
+ "eval_f1": 76.95926171469165,
38
+ "step": 800
39
+ },
40
+ {
41
+ "epoch": 0.97,
42
+ "learning_rate": 1.555072463768116e-05,
43
+ "loss": 1.0347,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 0.97,
48
+ "eval_exact_match": 59.97854077253219,
49
+ "eval_f1": 78.2749680853618,
50
+ "step": 1000
51
+ },
52
+ {
53
+ "epoch": 1.16,
54
+ "eval_exact_match": 59.44206008583691,
55
+ "eval_f1": 78.2209721909282,
56
+ "step": 1200
57
+ },
58
+ {
59
+ "epoch": 1.35,
60
+ "eval_exact_match": 61.48068669527897,
61
+ "eval_f1": 78.9917873380796,
62
+ "step": 1400
63
+ },
64
+ {
65
+ "epoch": 1.45,
66
+ "learning_rate": 8.304347826086955e-06,
67
+ "loss": 0.4519,
68
+ "step": 1500
69
+ },
70
+ {
71
+ "epoch": 1.55,
72
+ "eval_exact_match": 60.997854077253216,
73
+ "eval_f1": 79.01542543724356,
74
+ "step": 1600
75
+ },
76
+ {
77
+ "epoch": 1.74,
78
+ "eval_exact_match": 62.17811158798283,
79
+ "eval_f1": 79.82176827691146,
80
+ "step": 1800
81
+ },
82
+ {
83
+ "epoch": 1.93,
84
+ "learning_rate": 1.0579710144927535e-06,
85
+ "loss": 0.3936,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 1.93,
90
+ "eval_exact_match": 62.5,
91
+ "eval_f1": 80.15398176853643,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 2.0,
96
+ "step": 2070,
97
+ "total_flos": 8445258157133184.0,
98
+ "train_loss": 0.9571071643184349,
99
+ "train_runtime": 543.2284,
100
+ "train_samples_per_second": 60.925,
101
+ "train_steps_per_second": 3.811
102
+ }
103
+ ],
104
+ "max_steps": 2070,
105
+ "num_train_epochs": 2,
106
+ "total_flos": 8445258157133184.0,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0b9ada164ae803afda62e093fef7a7440e281e7fe5d4afa0e18cc308a4b29f
3
+ size 3439
vocab.json ADDED
The diff for this file is too large to render. See raw diff