NebulaByte commited on
Commit
0d2d9e7
1 Parent(s): c982945

End of training

Browse files
Files changed (4) hide show
  1. README.md +54 -0
  2. adapter_config.json +23 -0
  3. adapter_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/flan-t5-small
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - squad
8
+ model-index:
9
+ - name: flan_t5_small_squadv1_lora_extractive_qa
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # flan_t5_small_squadv1_lora_extractive_qa
17
+
18
+ This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the squad dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.001
38
+ - train_batch_size: 12
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - num_epochs: 1
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.34.1
52
+ - Pytorch 2.1.0+cu118
53
+ - Datasets 2.14.6
54
+ - Tokenizers 0.14.1
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "google/flan-t5-small",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": [
13
+ "qa_outputs"
14
+ ],
15
+ "peft_type": "LORA",
16
+ "r": 8,
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q",
20
+ "v"
21
+ ],
22
+ "task_type": "QUESTION_ANS"
23
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1c71bd790c78818f4cf3013669955f4d7ad7039d7958c6918a3103b7ce085c
3
+ size 1416468
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:175699fad154cd50132cc2216c9b346a17cf3229f5aea6759fd82ed508a0de57
3
+ size 4536