Hugging Face's logo

elmanz
/
output

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
 Metrics Community
elmanz commited on
Commit
0bfcf05
·
verified ·
1 Parent(s): c1e7fc2

End of training

Browse files
Files changed (12) hide show
  1. README.md +54 -0
  2. adapter_config.json +32 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Aug03_19-14-18_2074e56e5124/events.out.tfevents.1722712458.2074e56e5124.1817.0 +3 -0
  5. runs/Aug03_20-10-27_2074e56e5124/events.out.tfevents.1722715836.2074e56e5124.1817.1 +3 -0
  6. runs/Aug03_20-12-10_2074e56e5124/events.out.tfevents.1722715934.2074e56e5124.1817.2 +3 -0
  7. runs/Aug03_20-13-14_2074e56e5124/events.out.tfevents.1722715994.2074e56e5124.1817.3 +3 -0
  8. runs/Aug03_20-13-55_2074e56e5124/events.out.tfevents.1722716035.2074e56e5124.1817.4 +3 -0
  9. runs/Aug03_20-15-08_2074e56e5124/events.out.tfevents.1722716113.2074e56e5124.1817.5 +3 -0
  10. runs/Aug03_20-42-57_2074e56e5124/events.out.tfevents.1722717791.2074e56e5124.1817.6 +3 -0
  11. runs/Aug03_20-47-04_2074e56e5124/events.out.tfevents.1722718028.2074e56e5124.1817.7 +3 -0
  12. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: distilbert-base-cased
3
+ library_name: peft
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: output
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
+ # output
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: 0.0001
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 1
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 10
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - PEFT 0.12.0
51
+ - Transformers 4.42.4
52
+ - Pytorch 2.3.1+cu121
53
+ - Datasets 2.20.0
54
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "distilbert-base-cased",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "classifier",
19
+ "score"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_lin",
27
+ "v_lin"
28
+ ],
29
+ "task_type": "SEQ_CLS",
30
+ "use_dora": false,
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c4454b213b01aa65a58174f1bb6f1cb87ea022a690350b76d34944a69ecd03
3
+ size 593288
runs/Aug03_19-14-18_2074e56e5124/events.out.tfevents.1722712458.2074e56e5124.1817.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954c629358ed4d48adb71148cc4be6ae589efad5a8106aa7bbc5af5f501484e7
3
+ size 7270
runs/Aug03_20-10-27_2074e56e5124/events.out.tfevents.1722715836.2074e56e5124.1817.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a50c9da47d52a54e888093ab32d5a45fdceb472d3b6796462a42aac8f9e8c02
3
+ size 7270
runs/Aug03_20-12-10_2074e56e5124/events.out.tfevents.1722715934.2074e56e5124.1817.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6235681829c147a0d4a4997f5a449f88a53072caa396c564dbc6781bb0054b81
3
+ size 4825
runs/Aug03_20-13-14_2074e56e5124/events.out.tfevents.1722715994.2074e56e5124.1817.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a778819817a5ba7e87ac671a590a9b3e378ec386da35c5efafe63e200fdd5bf4
3
+ size 5447
runs/Aug03_20-13-55_2074e56e5124/events.out.tfevents.1722716035.2074e56e5124.1817.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6132241be8eb28d4fc8ef9232255713e9d1ea1e6fb8f84be19514ab5096a6d05
3
+ size 6283
runs/Aug03_20-15-08_2074e56e5124/events.out.tfevents.1722716113.2074e56e5124.1817.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae1933a92311dff15ce8ab20cdc5ad147464a104f385da05e607d67e4d7efff
3
+ size 7269
runs/Aug03_20-42-57_2074e56e5124/events.out.tfevents.1722717791.2074e56e5124.1817.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b98bab9fb15e156e729303da170e0b09c4cc096939395c245a90ff1323f826
3
+ size 7315
runs/Aug03_20-47-04_2074e56e5124/events.out.tfevents.1722718028.2074e56e5124.1817.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f31c420886021ea3debbfdac8d20a9604c0dc0af35e790e803d9e3b0047bca9
3
+ size 7315
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482d22578048112f1b55cd066a1fbb596f46cef7c6d8d72d1f481f86092f04e5
3
+ size 5112