mrm8488 commited on
Commit
91dc282
1 Parent(s): 172cf5d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -13
README.md CHANGED
@@ -1,20 +1,60 @@
1
  ---
2
- library_name: peft
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ## Training procedure
5
 
 
6
 
7
- The following `bitsandbytes` quantization config was used during training:
8
- - load_in_8bit: False
9
- - load_in_4bit: True
10
- - llm_int8_threshold: 6.0
11
- - llm_int8_skip_modules: None
12
- - llm_int8_enable_fp32_cpu_offload: False
13
- - llm_int8_has_fp16_weight: False
14
- - bnb_4bit_quant_type: nf4
15
- - bnb_4bit_use_double_quant: False
16
- - bnb_4bit_compute_dtype: float16
17
- ### Framework versions
18
 
 
 
 
 
 
 
 
 
 
 
19
 
20
- - PEFT 0.4.0.dev0
 
 
 
 
1
  ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: falcon-7b-ft-codeAlpaca_20k-v2
6
+ results: []
7
  ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # falcon-7b-ft-codeAlpaca_20k-v2
13
+
14
+ This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.7367
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
  ## Training procedure
31
 
32
+ ### Training hyperparameters
33
 
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0002
36
+ - train_batch_size: 64
37
+ - eval_batch_size: 64
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: constant
41
+ - lr_scheduler_warmup_ratio: 0.03
42
+ - training_steps: 550
43
+
44
+ ### Training results
45
 
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 0.7985 | 0.35 | 100 | 0.7680 |
49
+ | 0.7259 | 0.71 | 200 | 0.7499 |
50
+ | 0.6691 | 1.06 | 300 | 0.7480 |
51
+ | 0.6873 | 1.42 | 400 | 0.7423 |
52
+ | 0.5799 | 1.77 | 500 | 0.7367 |
53
+
54
+
55
+ ### Framework versions
56
 
57
+ - Transformers 4.31.0.dev0
58
+ - Pytorch 2.0.1+cu118
59
+ - Datasets 2.13.0
60
+ - Tokenizers 0.13.3