Jukaboo commited on
Commit
a366749
1 Parent(s): 3928436

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -13
README.md CHANGED
@@ -1,20 +1,56 @@
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: True
16
- - bnb_4bit_compute_dtype: bfloat16
17
- ### Framework versions
 
 
18
 
19
 
20
- - PEFT 0.4.0
 
 
 
 
 
 
 
1
  ---
2
+ base_model: meta-llama/Llama-2-7b-chat-hf
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - mlsum
7
+ model-index:
8
+ - name: Llama2_7B_mlsum_ft
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
+ # Llama2_7B_mlsum_ft
16
+
17
+ This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the mlsum 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: 0.0002
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 4
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 2
45
+ - training_steps: 10
46
+
47
+ ### Training results
48
 
49
 
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.31.0
54
+ - Pytorch 2.0.1+cu118
55
+ - Datasets 2.14.4
56
+ - Tokenizers 0.13.3