Hugging Face's logo

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

Text Classification
Transformers
PyTorch
Dutch
xlm-roberta
Inference Endpoints
Model card Files Community
poltextlab commited on
Commit
8683102
•
1 Parent(s): 5757f95

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. config.json +75 -0
  2. pytorch_model.bin +3 -0
  3. tmp/checkpoint-25592/config.json +75 -0
  4. tmp/checkpoint-25592/optimizer.pt +3 -0
  5. tmp/checkpoint-25592/pytorch_model.bin +3 -0
  6. tmp/checkpoint-25592/rng_state.pth +3 -0
  7. tmp/checkpoint-25592/scheduler.pt +3 -0
  8. tmp/checkpoint-25592/trainer_state.json +76 -0
  9. tmp/checkpoint-25592/training_args.bin +3 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 4096,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_10": 10,
42
+ "LABEL_11": 11,
43
+ "LABEL_12": 12,
44
+ "LABEL_13": 13,
45
+ "LABEL_14": 14,
46
+ "LABEL_15": 15,
47
+ "LABEL_16": 16,
48
+ "LABEL_17": 17,
49
+ "LABEL_18": 18,
50
+ "LABEL_19": 19,
51
+ "LABEL_2": 2,
52
+ "LABEL_20": 20,
53
+ "LABEL_3": 3,
54
+ "LABEL_4": 4,
55
+ "LABEL_5": 5,
56
+ "LABEL_6": 6,
57
+ "LABEL_7": 7,
58
+ "LABEL_8": 8,
59
+ "LABEL_9": 9
60
+ },
61
+ "layer_norm_eps": 1e-05,
62
+ "max_position_embeddings": 514,
63
+ "model_type": "xlm-roberta",
64
+ "num_attention_heads": 16,
65
+ "num_hidden_layers": 24,
66
+ "output_past": true,
67
+ "pad_token_id": 1,
68
+ "position_embedding_type": "absolute",
69
+ "problem_type": "multi_label_classification",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.28.1",
72
+ "type_vocab_size": 1,
73
+ "use_cache": true,
74
+ "vocab_size": 250002
75
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1efa68c8451f75486f09921d49a3adc996dc4314f4619dd188ba0107f3089d19
3
+ size 2239787829
tmp/checkpoint-25592/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 4096,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_10": 10,
42
+ "LABEL_11": 11,
43
+ "LABEL_12": 12,
44
+ "LABEL_13": 13,
45
+ "LABEL_14": 14,
46
+ "LABEL_15": 15,
47
+ "LABEL_16": 16,
48
+ "LABEL_17": 17,
49
+ "LABEL_18": 18,
50
+ "LABEL_19": 19,
51
+ "LABEL_2": 2,
52
+ "LABEL_20": 20,
53
+ "LABEL_3": 3,
54
+ "LABEL_4": 4,
55
+ "LABEL_5": 5,
56
+ "LABEL_6": 6,
57
+ "LABEL_7": 7,
58
+ "LABEL_8": 8,
59
+ "LABEL_9": 9
60
+ },
61
+ "layer_norm_eps": 1e-05,
62
+ "max_position_embeddings": 514,
63
+ "model_type": "xlm-roberta",
64
+ "num_attention_heads": 16,
65
+ "num_hidden_layers": 24,
66
+ "output_past": true,
67
+ "pad_token_id": 1,
68
+ "position_embedding_type": "absolute",
69
+ "problem_type": "multi_label_classification",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.28.1",
72
+ "type_vocab_size": 1,
73
+ "use_cache": true,
74
+ "vocab_size": 250002
75
+ }
tmp/checkpoint-25592/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469f1a32c67b09c832496f682b86edd876d5bba721c6b37ca3062a700829ba3d
3
+ size 4479527033
tmp/checkpoint-25592/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1efa68c8451f75486f09921d49a3adc996dc4314f4619dd188ba0107f3089d19
3
+ size 2239787829
tmp/checkpoint-25592/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377e06bb1c7f80e2b7b25558f82642e75ce9a03ea9d9402aacc9b79cee111720
3
+ size 14575
tmp/checkpoint-25592/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a91aa18d96df13554664229c78908078afceb4a6ab336a6034e6f9360781f50
3
+ size 627
tmp/checkpoint-25592/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.04989391192793846,
3
+ "best_model_checkpoint": "../model/xlm-roberta-large_8_5e-06_512_train_dutch_5_512/tmp/checkpoint-25592",
4
+ "epoch": 4.0,
5
+ "global_step": 25592,
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": 0.0878,
14
+ "step": 6398
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7808690215692404,
19
+ "eval_loss": 0.05946733057498932,
20
+ "eval_runtime": 157.6627,
21
+ "eval_samples_per_second": 40.58,
22
+ "eval_steps_per_second": 5.074,
23
+ "step": 6398
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.000000000000001e-06,
28
+ "loss": 0.053,
29
+ "step": 12796
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8150984682713348,
34
+ "eval_loss": 0.05160010606050491,
35
+ "eval_runtime": 157.2254,
36
+ "eval_samples_per_second": 40.693,
37
+ "eval_steps_per_second": 5.088,
38
+ "step": 12796
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3.5e-06,
43
+ "loss": 0.0413,
44
+ "step": 19194
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8276023757424195,
49
+ "eval_loss": 0.05165642499923706,
50
+ "eval_runtime": 157.2977,
51
+ "eval_samples_per_second": 40.674,
52
+ "eval_steps_per_second": 5.086,
53
+ "step": 19194
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 3e-06,
58
+ "loss": 0.0329,
59
+ "step": 25592
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.8421381681775555,
64
+ "eval_loss": 0.04989391192793846,
65
+ "eval_runtime": 157.2364,
66
+ "eval_samples_per_second": 40.69,
67
+ "eval_steps_per_second": 5.088,
68
+ "step": 25592
69
+ }
70
+ ],
71
+ "max_steps": 63980,
72
+ "num_train_epochs": 10,
73
+ "total_flos": 1.908121483839406e+17,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
tmp/checkpoint-25592/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab61e2b14f0beaa0076371acc133276a5179917e4ab49e258359f33667d7cd9c
3
+ size 3579
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab61e2b14f0beaa0076371acc133276a5179917e4ab49e258359f33667d7cd9c
3
+ size 3579