Hugging Face's logo

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

Text Classification
Transformers
PyTorch
Italian
xlm-roberta
zero-shot-classification
Inference Endpoints
Model card Files Community
poltextlab commited on
Commit
eaabd19
•
1 Parent(s): fda19d9

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. config.json +77 -0
  2. pytorch_model.bin +3 -0
  3. tmp/checkpoint-6472/config.json +77 -0
  4. tmp/checkpoint-6472/optimizer.pt +3 -0
  5. tmp/checkpoint-6472/pytorch_model.bin +3 -0
  6. tmp/checkpoint-6472/rng_state.pth +3 -0
  7. tmp/checkpoint-6472/scaler.pt +3 -0
  8. tmp/checkpoint-6472/scheduler.pt +3 -0
  9. tmp/checkpoint-6472/trainer_state.json +76 -0
  10. tmp/checkpoint-6472/training_args.bin +3 -0
  11. 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": "4.26.1",
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 sha256:380c82fe864383cd54d20ee7a13bf83fce6da2486f3958add885da8ccb6ccbb3
3
+ size 2239791925
tmp/checkpoint-6472/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": "4.26.1",
74
+ "type_vocab_size": 1,
75
+ "use_cache": true,
76
+ "vocab_size": 250002
77
+ }
tmp/checkpoint-6472/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a204a76accedb033fbf5f3844ba79b1613b01d10a6393acb2deca5d15e3dab
3
+ size 4479535225
tmp/checkpoint-6472/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380c82fe864383cd54d20ee7a13bf83fce6da2486f3958add885da8ccb6ccbb3
3
+ size 2239791925
tmp/checkpoint-6472/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62893810ecf25f9a80121262478188c7ffa4527d0158c38a37d590501b42ef52
3
+ size 14575
tmp/checkpoint-6472/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88782bb2fa777c4852c695b4807f6481a98d9bc27027d50a399583533b49e1ce
3
+ size 557
tmp/checkpoint-6472/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ae7d6694057e740b28a32195b08003c21077cf853a5d6afec07a7f7b443565
3
+ size 627
tmp/checkpoint-6472/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06737739592790604,
3
+ "best_model_checkpoint": "../model/xlm-roberta-large_8_5e-06_512_train_test/train_italian_5_512/tmp/checkpoint-6472",
4
+ "epoch": 4.0,
5
+ "global_step": 6472,
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": 0.1514,
14
+ "step": 1618
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.6705809641532756,
19
+ "eval_loss": 0.09453820437192917,
20
+ "eval_runtime": 12.1128,
21
+ "eval_samples_per_second": 133.578,
22
+ "eval_steps_per_second": 16.759,
23
+ "step": 1618
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.000000000000001e-06,
28
+ "loss": 0.0825,
29
+ "step": 3236
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.7194066749072929,
34
+ "eval_loss": 0.07779930531978607,
35
+ "eval_runtime": 11.8497,
36
+ "eval_samples_per_second": 136.543,
37
+ "eval_steps_per_second": 17.131,
38
+ "step": 3236
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3.5e-06,
43
+ "loss": 0.063,
44
+ "step": 4854
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.7360939431396786,
49
+ "eval_loss": 0.07050800323486328,
50
+ "eval_runtime": 11.8524,
51
+ "eval_samples_per_second": 136.512,
52
+ "eval_steps_per_second": 17.127,
53
+ "step": 4854
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 3e-06,
58
+ "loss": 0.0514,
59
+ "step": 6472
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.7583436341161929,
64
+ "eval_loss": 0.06737739592790604,
65
+ "eval_runtime": 11.8085,
66
+ "eval_samples_per_second": 137.02,
67
+ "eval_steps_per_second": 17.191,
68
+ "step": 6472
69
+ }
70
+ ],
71
+ "max_steps": 16180,
72
+ "num_train_epochs": 10,
73
+ "total_flos": 4.824375498097459e+16,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
tmp/checkpoint-6472/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9594670f3ad29d7e99c117084c1778f18e85a557ff969eec280a7e517f9a402
3
+ size 3579
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9594670f3ad29d7e99c117084c1778f18e85a557ff969eec280a7e517f9a402
3
+ size 3579