Hugging Face's logo

HiTZ
/
xlm-roberta-large-xnli-es

Text Classification
Transformers
PyTorch
xlm-roberta
Inference Endpoints
Model card Files Community
1
ragerri commited on
Commit
c73aab3
·
verified ·
1 Parent(s): c987785

Upload 12 files

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. all_results.json +15 -0
  3. config.json +40 -0
  4. eval_results.json +9 -0
  5. pytorch_model.bin +3 -0
  6. sentencepiece.bpe.model +3 -0
  7. special_tokens_map.json +15 -0
  8. test_mnli_results.json +9 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +20 -0
  11. train_results.json +8 -0
  12. trainer_state.json +85 -0
  13. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.849500998003992,
4
+ "eval_loss": 0.49887552857398987,
5
+ "eval_runtime": 171.8504,
6
+ "eval_samples": 2490,
7
+ "eval_samples_per_second": 29.153,
8
+ "eval_steps_per_second": 3.649,
9
+ "test_samples_mnli": 5010,
10
+ "train_loss": 0.3508187235567374,
11
+ "train_runtime": 165856.5757,
12
+ "train_samples": 392702,
13
+ "train_samples_per_second": 9.471,
14
+ "train_steps_per_second": 0.592
15
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "mnli",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 16,
30
+ "num_hidden_layers": 24,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.20.0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.8666666666666667,
4
+ "eval_loss": 0.457296758890152,
5
+ "eval_runtime": 85.4225,
6
+ "eval_samples": 2490,
7
+ "eval_samples_per_second": 29.149,
8
+ "eval_steps_per_second": 3.652
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed67bdfc56589e5457bfdada076f49789d2ae47d7e3689bb093a4db210c87f2
3
+ size 2239711213
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
test_mnli_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.849500998003992,
4
+ "eval_loss": 0.49887552857398987,
5
+ "eval_runtime": 171.8504,
6
+ "eval_samples_per_second": 29.153,
7
+ "eval_steps_per_second": 3.649,
8
+ "test_samples_mnli": 5010
9
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:affcfb1f45c4b14a70a6589c3d153b430ed4309e5a6613a88dab64d5a923a5d6
3
+ size 17082925
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "xlm-roberta-large",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.3508187235567374,
4
+ "train_runtime": 165856.5757,
5
+ "train_samples": 392702,
6
+ "train_samples_per_second": 9.471,
7
+ "train_steps_per_second": 0.592
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8666666666666667,
3
+ "best_model_checkpoint": "./outputs/xlm-roberta-large-best-model/xnli_16_0.1_0.00001_04-05-23_12-26/checkpoint-73632",
4
+ "epoch": 4.0,
5
+ "global_step": 98176,
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": 7.978761445522026e-06,
13
+ "loss": 0.548,
14
+ "step": 24544
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8526104417670682,
19
+ "eval_loss": 0.4045264422893524,
20
+ "eval_runtime": 85.4254,
21
+ "eval_samples_per_second": 29.148,
22
+ "eval_steps_per_second": 3.652,
23
+ "step": 24544
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 5.319174297014683e-06,
28
+ "loss": 0.3739,
29
+ "step": 49088
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8538152610441767,
34
+ "eval_loss": 0.3931969106197357,
35
+ "eval_runtime": 85.4189,
36
+ "eval_samples_per_second": 29.15,
37
+ "eval_steps_per_second": 3.653,
38
+ "step": 49088
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 2.6595871485073417e-06,
43
+ "loss": 0.2739,
44
+ "step": 73632
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8666666666666667,
49
+ "eval_loss": 0.457296758890152,
50
+ "eval_runtime": 85.1723,
51
+ "eval_samples_per_second": 29.235,
52
+ "eval_steps_per_second": 3.663,
53
+ "step": 73632
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 0.0,
58
+ "loss": 0.2075,
59
+ "step": 98176
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.8626506024096385,
64
+ "eval_loss": 0.5882326364517212,
65
+ "eval_runtime": 85.1965,
66
+ "eval_samples_per_second": 29.227,
67
+ "eval_steps_per_second": 3.662,
68
+ "step": 98176
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "step": 98176,
73
+ "total_flos": 1.4638901871267594e+18,
74
+ "train_loss": 0.3508187235567374,
75
+ "train_runtime": 165856.5757,
76
+ "train_samples_per_second": 9.471,
77
+ "train_steps_per_second": 0.592
78
+ }
79
+ ],
80
+ "max_steps": 98176,
81
+ "num_train_epochs": 4,
82
+ "total_flos": 1.4638901871267594e+18,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd0f44afea150f2636622c331f0c76466aaf76e8f65f15f1424d0ac1dbc57dd
3
+ size 3311