jalaluddin94 commited on
Commit
0567466
1 Parent(s): b93d486

End of training

Browse files
Files changed (4) hide show
  1. README.md +48 -0
  2. config.json +39 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: jalaluddin94/xlmr-large-nli-indoindo
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: trf-learn-xlmr-large
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # trf-learn-xlmr-large
15
+
16
+ This model is a fine-tuned version of [jalaluddin94/xlmr-large-nli-indoindo](https://huggingface.co/jalaluddin94/xlmr-large-nli-indoindo) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 3e-06
36
+ - train_batch_size: 2
37
+ - eval_batch_size: 2
38
+ - seed: 101
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 6
42
+
43
+ ### Framework versions
44
+
45
+ - Transformers 4.35.0
46
+ - Pytorch 2.0.0
47
+ - Datasets 2.1.0
48
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jalaluddin94/xlmr-large-nli-indoindo",
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
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "xlm-roberta",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "output_past": true,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.35.0",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 250002
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b4eb4e66ea384faa4ce81cf9110892bc2b68843b6d478f81a203783bd32b78
3
+ size 2239622772
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0d82dae011902c9c2720895601eaab7fdfa6aa8c2cf5b8bbdbebf73f1a9403
3
+ size 4283