fzzhang commited on
Commit
7eea211
·
verified ·
1 Parent(s): 69f8409

Training in progress, epoch 1

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: FelixChao/Severus-7B
7
+ model-index:
8
+ - name: severus_gsm8k_quantized_s
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
+ # severus_gsm8k_quantized_s
16
+
17
+ This model is a fine-tuned version of [FelixChao/Severus-7B](https://huggingface.co/FelixChao/Severus-7B) 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: 1e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 8
39
+ - seed: 0
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 5
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - PEFT 0.7.2.dev0
51
+ - Transformers 4.36.2
52
+ - Pytorch 2.1.2
53
+ - Datasets 2.16.1
54
+ - Tokenizers 0.15.1
adapter_config.json CHANGED
@@ -19,11 +19,11 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
  "v_proj",
 
24
  "gate_proj",
25
- "o_proj",
26
- "k_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "v_proj",
23
+ "k_proj",
24
  "gate_proj",
25
+ "q_proj",
26
+ "o_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34374314bff381fbe1dfda2795ac48fb7b02560d9c0dfd152137124e82cd3865
3
  size 92317600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a31219711112b1ce498d4d9f644a590facf6e6b8bf661c35e8aef1b2d29155
3
  size 92317600
runs/Feb20_01-48-34_instance-51/events.out.tfevents.1708393715.instance-51.583504.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a2221c90ce8ba4b2317b30711be3918b4fd01bd91aaa6e0ed25fc4ded560881
3
- size 16368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511ae0eb49ddb18747209170d6a779eaa9c65f061df55e80f9c1b9f826d1d5bb
3
+ size 34381
runs/Feb20_07-16-22_instance-51/events.out.tfevents.1708413383.instance-51.611438.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94fe998eeaa6d2c35e813cd7b483dd06e3bd8b641892e798e23142da8bab8d3f
3
+ size 10559
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:007b7c9ce1f387f9879f865a8565d17680c12d48dbcf36ba460fb34daad8b15a
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e9eae26c42c67bd1243879377c2bf0af63099761f9a392c671b7b56864da26
3
  size 4728