Hugging Face's logo

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

Text Classification
Transformers
PyTorch
Hungarian
xlm-roberta
zero-shot-classification
Inference Endpoints
Model card Files Community
poltextlab commited on
Commit
fb3814c
•
1 Parent(s): a0c166b

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-101625/config.json +77 -0
  4. tmp/checkpoint-101625/optimizer.pt +3 -0
  5. tmp/checkpoint-101625/pytorch_model.bin +3 -0
  6. tmp/checkpoint-101625/rng_state.pth +3 -0
  7. tmp/checkpoint-101625/scheduler.pt +3 -0
  8. tmp/checkpoint-101625/trainer_state.json +61 -0
  9. tmp/checkpoint-101625/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 sha256:7df4d39a75f08abcac3dee0242e56b244887be6d948122def988c105a71aee3e
3
+ size 2239791925
tmp/checkpoint-101625/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-101625/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86de7b2f8178d4f5759b18f5b4a13ebcbaa9cb6e5c5f3f1095e0420efc52d9d0
3
+ size 4479535993
tmp/checkpoint-101625/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df4d39a75f08abcac3dee0242e56b244887be6d948122def988c105a71aee3e
3
+ size 2239791925
tmp/checkpoint-101625/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea335e94f7115205d9f0eaf2151ff0230ffb650703aafd758fe5605ec78cb9e
3
+ size 14575
tmp/checkpoint-101625/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9d76d4a933d8d4244044cd37161b35ea164153f1c939b9e046ce53e36a3989
3
+ size 627
tmp/checkpoint-101625/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.04090982303023338,
3
+ "best_model_checkpoint": "../model/xlm-roberta-large_16_5e-06_512_train_hungarian_5_512/tmp/checkpoint-101625",
4
+ "epoch": 3.0,
5
+ "global_step": 101625,
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": 0.0548,
14
+ "step": 33875
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8137361988545787,
19
+ "eval_loss": 0.04528332129120827,
20
+ "eval_runtime": 1602.7178,
21
+ "eval_samples_per_second": 42.271,
22
+ "eval_steps_per_second": 2.642,
23
+ "step": 33875
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.000000000000001e-06,
28
+ "loss": 0.0412,
29
+ "step": 67750
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8293971777764657,
34
+ "eval_loss": 0.04114730656147003,
35
+ "eval_runtime": 1606.1775,
36
+ "eval_samples_per_second": 42.18,
37
+ "eval_steps_per_second": 2.637,
38
+ "step": 67750
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3.5e-06,
43
+ "loss": 0.0361,
44
+ "step": 101625
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8307846726102616,
49
+ "eval_loss": 0.04090982303023338,
50
+ "eval_runtime": 1602.7074,
51
+ "eval_samples_per_second": 42.271,
52
+ "eval_steps_per_second": 2.642,
53
+ "step": 101625
54
+ }
55
+ ],
56
+ "max_steps": 338750,
57
+ "num_train_epochs": 10,
58
+ "total_flos": 1.5153836519850762e+18,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
tmp/checkpoint-101625/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e086ef910f3137d3b9d25933584b7a2787a58a148e8f25378270a9ce8f674b38
3
+ size 3643
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e086ef910f3137d3b9d25933584b7a2787a58a148e8f25378270a9ce8f674b38
3
+ size 3643