Hugging Face's logo

jahb57
/
ORIGINAL_LORA_Model

TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
jahb57 commited on
Commit
d0eec1f
·
1 Parent(s): 6309aae

jahb57/ORIGINAL_LORA_Model

Browse files
Files changed (9) hide show
  1. README.md +71 -0
  2. adapter_config.json +26 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Nov06_15-28-18_f6f0bd6af14c/events.out.tfevents.1699284504.f6f0bd6af14c.213.0 +3 -0
  5. runs/Nov06_15-29-10_f6f0bd6af14c/events.out.tfevents.1699284550.f6f0bd6af14c.213.1 +3 -0
  6. runs/Nov06_15-33-37_f6f0bd6af14c/events.out.tfevents.1699284819.f6f0bd6af14c.2956.0 +3 -0
  7. runs/Nov06_15-39-54_f6f0bd6af14c/events.out.tfevents.1699285196.f6f0bd6af14c.5252.0 +3 -0
  8. runs/Nov06_15-41-34_f6f0bd6af14c/events.out.tfevents.1699285296.f6f0bd6af14c.5929.0 +3 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: jahb57/test_trainer
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - yelp_review_full
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: ORIGINAL_LORA_Model
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # ORIGINAL_LORA_Model
19
+
20
+ This model is a fine-tuned version of [jahb57/test_trainer](https://huggingface.co/jahb57/test_trainer) on the yelp_review_full dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.8158
23
+ - Accuracy: 0.6355
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 12
44
+ - eval_batch_size: 12
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 10
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
+ | 0.9375 | 1.0 | 1667 | 0.8691 | 0.6155 |
55
+ | 0.8754 | 2.0 | 3334 | 0.8640 | 0.619 |
56
+ | 0.865 | 3.0 | 5001 | 0.8303 | 0.628 |
57
+ | 0.8558 | 4.0 | 6668 | 0.8217 | 0.6295 |
58
+ | 0.8267 | 5.0 | 8335 | 0.8195 | 0.6295 |
59
+ | 0.8042 | 6.0 | 10002 | 0.8388 | 0.638 |
60
+ | 0.797 | 7.0 | 11669 | 0.8172 | 0.6405 |
61
+ | 0.7887 | 8.0 | 13336 | 0.8146 | 0.6385 |
62
+ | 0.7764 | 9.0 | 15003 | 0.8202 | 0.635 |
63
+ | 0.7807 | 10.0 | 16670 | 0.8158 | 0.6355 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.35.0
69
+ - Pytorch 2.1.0+cu118
70
+ - Datasets 2.14.6
71
+ - Tokenizers 0.14.1
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "jahb57/test_trainer",
5
+ "bias": "none",
6
+ "fan_in_fan_out": true,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.1,
13
+ "modules_to_save": [
14
+ "classifier"
15
+ ],
16
+ "peft_type": "LORA",
17
+ "r": 16,
18
+ "rank_pattern": {},
19
+ "revision": null,
20
+ "target_modules": [
21
+ "c_fc",
22
+ "c_proj",
23
+ "c_attn"
24
+ ],
25
+ "task_type": "SEQ_CLS"
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c64bd3bb8412fb435fc046094a11c7145885a565a9f0abfb84ae46923da198
3
+ size 9464800
runs/Nov06_15-28-18_f6f0bd6af14c/events.out.tfevents.1699284504.f6f0bd6af14c.213.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0bb0672eb1878a1dfab28f3f5d9b6ba593a308b0e46f4fccc48ba0358d9955
3
+ size 4815
runs/Nov06_15-29-10_f6f0bd6af14c/events.out.tfevents.1699284550.f6f0bd6af14c.213.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6204ca4f52786364cd4ba41d857f7bb8da6b489f3852c4751692b64729ae282
3
+ size 4184
runs/Nov06_15-33-37_f6f0bd6af14c/events.out.tfevents.1699284819.f6f0bd6af14c.2956.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1041b55350cabaa6d8e8435a4da181be2f2635c9fe854119ec76dc680de13b
3
+ size 4817
runs/Nov06_15-39-54_f6f0bd6af14c/events.out.tfevents.1699285196.f6f0bd6af14c.5252.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e3ed66d7dc0ced45d59c6e69ed6b6d84fa8523f9bb209fccbc4f092e6de27a
3
+ size 4184
runs/Nov06_15-41-34_f6f0bd6af14c/events.out.tfevents.1699285296.f6f0bd6af14c.5929.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865f375bf8254113c670175e462e4746a5d9526336928d148eb7a58238f961a3
3
+ size 13597
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10343f2c7423aaa4bfa63c8fdbb192fd3adc0c42c87e1a2efcd032aa40886922
3
+ size 4600