Blanca commited on
Commit
31e0fb1
1 Parent(s): 5d0069b
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/gpfs/projects/bsc88/projects/catalan_evaluation/models/roberta-large-ca-v2",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "paraf",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "No Parafrasis",
16
+ "1": "Parafrasis"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "No Parafrasis": 0,
22
+ "Parafrasis": 1
23
+ },
24
+ "layer_norm_eps": 1e-05,
25
+ "max_position_embeddings": 514,
26
+ "model_type": "roberta",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.17.0",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 50262
37
+ }
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 sha256:49a4b62f251baff1449d840251b3bd5691c06f1b83570d030c5063a2bb1289a2
3
+ size 1421600941
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "/gpfs/projects/bsc88/projects/catalan_evaluation/models/roberta-large-ca-v2", "tokenizer_class": "RobertaTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8438365477338476,
3
+ "best_model_checkpoint": "output/roberta-large-ca-v2/parafraseja.py_8_0.00005_date_22-10-14_time_16-03-07/checkpoint-4995",
4
+ "epoch": 5.0,
5
+ "global_step": 4995,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4e-05,
13
+ "loss": 0.5335,
14
+ "step": 999
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.836,
19
+ "eval_combined_score": 0.8360819180819181,
20
+ "eval_f1": 0.8361638361638362,
21
+ "eval_loss": 0.39040425419807434,
22
+ "eval_runtime": 58.4758,
23
+ "eval_samples_per_second": 34.202,
24
+ "eval_steps_per_second": 2.138,
25
+ "step": 999
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 3e-05,
30
+ "loss": 0.3403,
31
+ "step": 1998
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.832,
36
+ "eval_combined_score": 0.8342083739045765,
37
+ "eval_f1": 0.8364167478091529,
38
+ "eval_loss": 0.4153313934803009,
39
+ "eval_runtime": 58.4308,
40
+ "eval_samples_per_second": 34.229,
41
+ "eval_steps_per_second": 2.139,
42
+ "step": 1998
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 2e-05,
47
+ "loss": 0.2345,
48
+ "step": 2997
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8405,
53
+ "eval_combined_score": 0.8427098930481283,
54
+ "eval_f1": 0.8449197860962566,
55
+ "eval_loss": 0.4383120834827423,
56
+ "eval_runtime": 58.4693,
57
+ "eval_samples_per_second": 34.206,
58
+ "eval_steps_per_second": 2.138,
59
+ "step": 2997
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 1e-05,
64
+ "loss": 0.1644,
65
+ "step": 3996
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.836,
70
+ "eval_combined_score": 0.8401272554605888,
71
+ "eval_f1": 0.8442545109211776,
72
+ "eval_loss": 0.6573591828346252,
73
+ "eval_runtime": 58.3674,
74
+ "eval_samples_per_second": 34.266,
75
+ "eval_steps_per_second": 2.142,
76
+ "step": 3996
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "learning_rate": 0.0,
81
+ "loss": 0.1097,
82
+ "step": 4995
83
+ },
84
+ {
85
+ "epoch": 5.0,
86
+ "eval_accuracy": 0.841,
87
+ "eval_combined_score": 0.8438365477338476,
88
+ "eval_f1": 0.8466730954676953,
89
+ "eval_loss": 0.7086848616600037,
90
+ "eval_runtime": 58.3516,
91
+ "eval_samples_per_second": 34.275,
92
+ "eval_steps_per_second": 2.142,
93
+ "step": 4995
94
+ },
95
+ {
96
+ "epoch": 5.0,
97
+ "step": 4995,
98
+ "total_flos": 7.447995455717376e+16,
99
+ "train_loss": 0.27648499787629427,
100
+ "train_runtime": 7079.06,
101
+ "train_samples_per_second": 11.29,
102
+ "train_steps_per_second": 0.706
103
+ }
104
+ ],
105
+ "max_steps": 4995,
106
+ "num_train_epochs": 5,
107
+ "total_flos": 7.447995455717376e+16,
108
+ "trial_name": null,
109
+ "trial_params": null
110
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed676d440a87f46a5079e293c785b21237a9713d0cff8bae8bac8bdb041c102
3
+ size 3119
vocab.json ADDED
The diff for this file is too large to render. See raw diff