maidacundo commited on
Commit
315c592
1 Parent(s): 896014c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -16
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
  datasets:
@@ -7,7 +8,6 @@ datasets:
7
  model-index:
8
  - name: falcon_qlora_sql
9
  results: []
10
- library_name: peft
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
  # falcon_qlora_sql
17
 
18
  This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the spider dataset.
 
 
19
 
20
  ## Model description
21
 
@@ -31,33 +33,40 @@ More information needed
31
 
32
  ## Training procedure
33
 
34
-
35
- The following `bitsandbytes` quantization config was used during training:
36
- - load_in_8bit: False
37
- - load_in_4bit: True
38
- - llm_int8_threshold: 6.0
39
- - llm_int8_skip_modules: None
40
- - llm_int8_enable_fp32_cpu_offload: False
41
- - llm_int8_has_fp16_weight: False
42
- - bnb_4bit_quant_type: nf4
43
- - bnb_4bit_use_double_quant: True
44
- - bnb_4bit_compute_dtype: bfloat16
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
- - learning_rate: 0.0003
49
  - train_batch_size: 16
50
  - eval_batch_size: 16
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - lr_scheduler_warmup_steps: 22.8
55
  - num_epochs: 3
56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  ### Framework versions
58
 
59
- - PEFT 0.4.0.dev0
60
  - Transformers 4.31.0.dev0
61
- - Pytorch 2.0.1+cu118
62
  - Datasets 2.13.1
63
  - Tokenizers 0.13.3
 
1
  ---
2
  license: apache-2.0
3
+ base_model: tiiuae/falcon-7b
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
8
  model-index:
9
  - name: falcon_qlora_sql
10
  results: []
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
16
  # falcon_qlora_sql
17
 
18
  This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the spider dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1772
21
 
22
  ## Model description
23
 
 
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: 16
41
  - eval_batch_size: 16
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 43.7
46
  - num_epochs: 3
47
 
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 0.2917 | 0.23 | 100 | 0.3571 |
53
+ | 0.8787 | 0.46 | 200 | 0.3685 |
54
+ | 0.3366 | 0.68 | 300 | 0.4001 |
55
+ | 0.2319 | 0.91 | 400 | 0.3134 |
56
+ | 0.3005 | 1.14 | 500 | 0.3567 |
57
+ | 0.4231 | 1.37 | 600 | 0.3052 |
58
+ | 0.2535 | 1.6 | 700 | 0.3218 |
59
+ | 0.2257 | 1.83 | 800 | 0.2744 |
60
+ | 0.0771 | 2.05 | 900 | 0.2567 |
61
+ | 0.0978 | 2.28 | 1000 | 0.2304 |
62
+ | 0.2031 | 2.51 | 1100 | 0.2236 |
63
+ | 0.2471 | 2.74 | 1200 | 0.2431 |
64
+ | 0.1514 | 2.97 | 1300 | 0.1897 |
65
+
66
+
67
  ### Framework versions
68
 
 
69
  - Transformers 4.31.0.dev0
70
+ - Pytorch 2.0.1+cu117
71
  - Datasets 2.13.1
72
  - Tokenizers 0.13.3