EkeminiThompson commited on
Commit
2d017fa
·
verified ·
1 Parent(s): cc75d62

distilbert-lora-imdb

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: distilbert-base-uncased
5
+ tags:
6
+ - base_model:adapter:distilbert-base-uncased
7
+ - lora
8
+ - transformers
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ model-index:
13
+ - name: results
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # results
21
+
22
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.2586
25
+ - Accuracy: 0.897
26
+ - F1: 0.8970
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 0.0002
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 16
48
+ - seed: 42
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 3
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - PEFT 0.17.1
60
+ - Transformers 4.56.2
61
+ - Pytorch 2.8.0+cu126
62
+ - Datasets 4.1.1
63
+ - Tokenizers 0.22.0
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "DistilBertForSequenceClassification",
5
+ "parent_library": "transformers.models.distilbert.modeling_distilbert"
6
+ },
7
+ "base_model_name_or_path": "distilbert-base-uncased",
8
+ "bias": "none",
9
+ "corda_config": null,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 16,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "qalora_group_size": 16,
27
+ "r": 8,
28
+ "rank_pattern": {},
29
+ "revision": null,
30
+ "target_modules": [
31
+ "v_lin",
32
+ "q_lin"
33
+ ],
34
+ "target_parameters": null,
35
+ "task_type": null,
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_qalora": false,
39
+ "use_rslora": false
40
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a150425c1a0fce17bf5f94c135ee1fa168ace9141bd9be1e6dac5afe62ba2b
3
+ size 593288
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f71c1ba34213d515b9d0bcf2d24ee24431506c228a53a1457430dafc1d8ebd
3
+ size 5713