ysaber commited on
Commit
17bb89e
·
verified ·
1 Parent(s): 67f8d42

End of training

Browse files
Files changed (4) hide show
  1. README.md +49 -0
  2. config.json +38 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert-base-cased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: my_test_model
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # my_test_model
16
+
17
+ This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3.0
43
+
44
+ ### Framework versions
45
+
46
+ - Transformers 4.49.0
47
+ - Pytorch 2.6.0
48
+ - Datasets 3.3.2
49
+ - Tokenizers 0.21.2
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "criminal-law",
13
+ "1": "employment",
14
+ "2": "tax-law",
15
+ "3": "trademark"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "criminal-law": 0,
20
+ "employment": 1,
21
+ "tax-law": 2,
22
+ "trademark": 3
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "output_past": true,
29
+ "pad_token_id": 0,
30
+ "problem_type": "single_label_classification",
31
+ "qa_dropout": 0.1,
32
+ "seq_classif_dropout": 0.2,
33
+ "sinusoidal_pos_embds": false,
34
+ "tie_weights_": true,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.49.0",
37
+ "vocab_size": 28996
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6020b4fd7e1f8ddb8234a9b86c6da0f7c7d972852e6ca3883da42444ca85c58d
3
+ size 263150840
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e18a933a03d2b755dd956a4e78a905e5ac19ed532776df5b04cfa44af008143
3
+ size 5304