Hugging Face's logo

poltextlab
/
xlm-roberta-large-portuguese-cap-v3

Text Classification
Transformers
PyTorch
Portuguese
xlm-roberta
Inference Endpoints
Model card Files Community
poltextlab commited on
Commit
5c0ef31
•
1 Parent(s): b1f430a

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. config.json +77 -0
  2. pytorch_model.bin +3 -0
  3. tmp/checkpoint-7940/config.json +77 -0
  4. tmp/checkpoint-7940/optimizer.pt +3 -0
  5. tmp/checkpoint-7940/pytorch_model.bin +3 -0
  6. tmp/checkpoint-7940/rng_state.pth +3 -0
  7. tmp/checkpoint-7940/scheduler.pt +3 -0
  8. tmp/checkpoint-7940/trainer_state.json +91 -0
  9. tmp/checkpoint-7940/training_args.bin +3 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 4096,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_10": 10,
43
+ "LABEL_11": 11,
44
+ "LABEL_12": 12,
45
+ "LABEL_13": 13,
46
+ "LABEL_14": 14,
47
+ "LABEL_15": 15,
48
+ "LABEL_16": 16,
49
+ "LABEL_17": 17,
50
+ "LABEL_18": 18,
51
+ "LABEL_19": 19,
52
+ "LABEL_2": 2,
53
+ "LABEL_20": 20,
54
+ "LABEL_21": 21,
55
+ "LABEL_3": 3,
56
+ "LABEL_4": 4,
57
+ "LABEL_5": 5,
58
+ "LABEL_6": 6,
59
+ "LABEL_7": 7,
60
+ "LABEL_8": 8,
61
+ "LABEL_9": 9
62
+ },
63
+ "layer_norm_eps": 1e-05,
64
+ "max_position_embeddings": 514,
65
+ "model_type": "xlm-roberta",
66
+ "num_attention_heads": 16,
67
+ "num_hidden_layers": 24,
68
+ "output_past": true,
69
+ "pad_token_id": 1,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "multi_label_classification",
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.28.1",
74
+ "type_vocab_size": 1,
75
+ "use_cache": true,
76
+ "vocab_size": 250002
77
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c47cf0d5782e2ebe312423fd005e8789805d6980bcc30ac6c0816452b4404d2
3
+ size 2239791925
tmp/checkpoint-7940/config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 4096,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_10": 10,
43
+ "LABEL_11": 11,
44
+ "LABEL_12": 12,
45
+ "LABEL_13": 13,
46
+ "LABEL_14": 14,
47
+ "LABEL_15": 15,
48
+ "LABEL_16": 16,
49
+ "LABEL_17": 17,
50
+ "LABEL_18": 18,
51
+ "LABEL_19": 19,
52
+ "LABEL_2": 2,
53
+ "LABEL_20": 20,
54
+ "LABEL_21": 21,
55
+ "LABEL_3": 3,
56
+ "LABEL_4": 4,
57
+ "LABEL_5": 5,
58
+ "LABEL_6": 6,
59
+ "LABEL_7": 7,
60
+ "LABEL_8": 8,
61
+ "LABEL_9": 9
62
+ },
63
+ "layer_norm_eps": 1e-05,
64
+ "max_position_embeddings": 514,
65
+ "model_type": "xlm-roberta",
66
+ "num_attention_heads": 16,
67
+ "num_hidden_layers": 24,
68
+ "output_past": true,
69
+ "pad_token_id": 1,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "multi_label_classification",
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.28.1",
74
+ "type_vocab_size": 1,
75
+ "use_cache": true,
76
+ "vocab_size": 250002
77
+ }
tmp/checkpoint-7940/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9b850a22ced455e3c3481cf147c3bb0f115c92861f4ba04494918db2b7487b
3
+ size 4479535225
tmp/checkpoint-7940/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c47cf0d5782e2ebe312423fd005e8789805d6980bcc30ac6c0816452b4404d2
3
+ size 2239791925
tmp/checkpoint-7940/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d3d5f456448620e152c7c9f77dcffd0a136128383319de667756fa8f3a828c7
3
+ size 14575
tmp/checkpoint-7940/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551628520d1d3c2d23ff15ddf98f0f0d50e282c620d506aee3558da0eb281e5d
3
+ size 627
tmp/checkpoint-7940/trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.03575996309518814,
3
+ "best_model_checkpoint": "../model/xlm-roberta-large_8_5e-06_512_train_portuguese_5_512/tmp/checkpoint-7940",
4
+ "epoch": 5.0,
5
+ "global_step": 7940,
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": 4.5e-06,
13
+ "loss": 0.1057,
14
+ "step": 1588
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8224181360201511,
19
+ "eval_loss": 0.05803457647562027,
20
+ "eval_runtime": 39.2947,
21
+ "eval_samples_per_second": 40.413,
22
+ "eval_steps_per_second": 5.064,
23
+ "step": 1588
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.000000000000001e-06,
28
+ "loss": 0.0475,
29
+ "step": 3176
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8677581863979849,
34
+ "eval_loss": 0.04084894061088562,
35
+ "eval_runtime": 39.1837,
36
+ "eval_samples_per_second": 40.527,
37
+ "eval_steps_per_second": 5.079,
38
+ "step": 3176
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3.5e-06,
43
+ "loss": 0.0332,
44
+ "step": 4764
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8797229219143576,
49
+ "eval_loss": 0.035842426121234894,
50
+ "eval_runtime": 38.8555,
51
+ "eval_samples_per_second": 40.869,
52
+ "eval_steps_per_second": 5.122,
53
+ "step": 4764
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 3e-06,
58
+ "loss": 0.0265,
59
+ "step": 6352
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.8816120906801007,
64
+ "eval_loss": 0.036147672683000565,
65
+ "eval_runtime": 39.012,
66
+ "eval_samples_per_second": 40.705,
67
+ "eval_steps_per_second": 5.101,
68
+ "step": 6352
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 2.5e-06,
73
+ "loss": 0.0215,
74
+ "step": 7940
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_accuracy": 0.8809823677581864,
79
+ "eval_loss": 0.03575996309518814,
80
+ "eval_runtime": 38.8621,
81
+ "eval_samples_per_second": 40.862,
82
+ "eval_steps_per_second": 5.121,
83
+ "step": 7940
84
+ }
85
+ ],
86
+ "max_steps": 15880,
87
+ "num_train_epochs": 10,
88
+ "total_flos": 5.920028043411456e+16,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
tmp/checkpoint-7940/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e9ec530cda62cb03dca7cb87579e3aaf100407df38d3aca7ed28adaf47f0d3
3
+ size 3643
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e9ec530cda62cb03dca7cb87579e3aaf100407df38d3aca7ed28adaf47f0d3
3
+ size 3643