larry1129 commited on
Commit
15a0e62
1 Parent(s): 8c7e469

Training complete, uploading model.

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/meta-llama-3.1-8b-bnb-4bit
3
+ library_name: peft
4
+ license: llama3.1
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - unsloth
9
+ - generated_from_trainer
10
+ model-index:
11
+ - name: WooWoof_AI_Vision
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
+ # WooWoof_AI_Vision
19
+
20
+ This model is a fine-tuned version of [unsloth/meta-llama-3.1-8b-bnb-4bit](https://huggingface.co/unsloth/meta-llama-3.1-8b-bnb-4bit) on an unknown 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: 0.0003
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 8
42
+ - seed: 3407
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_steps: 10
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - PEFT 0.13.0
55
+ - Transformers 4.45.1
56
+ - Pytorch 2.3.1
57
+ - Datasets 3.0.0
58
+ - Tokenizers 0.20.0
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
  "gate_proj",
25
  "up_proj",
26
  "v_proj",
27
  "o_proj",
28
  "k_proj",
 
29
  "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "gate_proj",
24
  "up_proj",
25
  "v_proj",
26
  "o_proj",
27
  "k_proj",
28
+ "q_proj",
29
  "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05bce3d38782f3b82a959aeacaa04d5d14d58524bc7e23807377e7ad2874a819
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ff97650ce0ddbe2e90a86262341d3b0d7f3a9d05b97c0cf28e55e5cbde41c4
3
  size 83945296
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b671956dbbbab1a4a1adeb0cb8e45e84463ed769231e6ab9a86a6717220ff735
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a96924cce0bb82d13209eb4116bb8248f4b7dc429375c6364fb2808f115cd3
3
  size 5496