jackie691224 commited on
Commit
c2edba6
1 Parent(s): aeaeb08

Training in progress, epoch 2

Browse files
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: taide/Llama3-TAIDE-LX-8B-Chat-Alpha1
3
+ datasets:
4
+ - generator
5
+ library_name: peft
6
+ tags:
7
+ - trl
8
+ - sft
9
+ - generated_from_trainer
10
+ model-index:
11
+ - name: demo
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
+ # demo
19
+
20
+ This model is a fine-tuned version of [taide/Llama3-TAIDE-LX-8B-Chat-Alpha1](https://huggingface.co/taide/Llama3-TAIDE-LX-8B-Chat-Alpha1) on the generator dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0002
40
+ - train_batch_size: 3
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 6
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: constant
47
+ - lr_scheduler_warmup_ratio: 0.03
48
+ - num_epochs: 3
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - PEFT 0.7.2.dev0
57
+ - Transformers 4.36.2
58
+ - Pytorch 2.3.1+cu121
59
+ - Datasets 2.20.0
60
+ - Tokenizers 0.15.2
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
- "down_proj",
24
  "o_proj",
25
- "v_proj",
 
26
  "gate_proj",
27
- "k_proj",
28
- "up_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
+ "k_proj",
24
  "o_proj",
25
+ "down_proj",
26
+ "up_proj",
27
  "gate_proj",
28
+ "v_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ef205d6e586dee2a73f1209e9a51408d156a26ab7d3b8efa7e763908e361864
3
  size 3443619040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea043d4e6911b537470cb8dbeba0a73fb225b85ba91af673c1a478dc4db2b7bd
3
  size 3443619040
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8198fe0c17e97eb98e399e5e5701273eecd59d02615d2d18a8ea985ed11e63f4
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f3e37d9b760b67956edc3d7e5951889c77a31c73aaf431b649454ee17dd46db
3
  size 4728