yuriachermann commited on
Commit
c1bf8ab
1 Parent(s): 17ba267

End of training

Browse files
Files changed (1) hide show
  1. README.md +25 -1
README.md CHANGED
@@ -6,6 +6,8 @@ tags:
6
  - sft
7
  - generated_from_trainer
8
  base_model: google/gemma-2b
 
 
9
  model-index:
10
  - name: Not-so-bright-AGI-v1
11
  results: []
@@ -16,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # Not-so-bright-AGI-v1
18
 
19
- This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
 
 
20
 
21
  ## Model description
22
 
@@ -46,6 +50,26 @@ The following hyperparameters were used during training:
46
  - lr_scheduler_warmup_ratio: 0.05
47
  - training_steps: 1480
48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  ### Framework versions
50
 
51
  - PEFT 0.10.0
 
6
  - sft
7
  - generated_from_trainer
8
  base_model: google/gemma-2b
9
+ datasets:
10
+ - generator
11
  model-index:
12
  - name: Not-so-bright-AGI-v1
13
  results: []
 
18
 
19
  # Not-so-bright-AGI-v1
20
 
21
+ This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 2.0548
24
 
25
  ## Model description
26
 
 
50
  - lr_scheduler_warmup_ratio: 0.05
51
  - training_steps: 1480
52
 
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 2.9165 | 3.2 | 100 | 2.6762 |
58
+ | 2.419 | 6.4 | 200 | 2.3629 |
59
+ | 2.2343 | 9.6 | 300 | 2.2060 |
60
+ | 2.1459 | 12.8 | 400 | 2.1401 |
61
+ | 2.0944 | 16.0 | 500 | 2.1112 |
62
+ | 2.0679 | 19.2 | 600 | 2.0942 |
63
+ | 2.0496 | 22.4 | 700 | 2.0826 |
64
+ | 2.0375 | 25.6 | 800 | 2.0743 |
65
+ | 2.0213 | 28.8 | 900 | 2.0684 |
66
+ | 2.0148 | 32.0 | 1000 | 2.0630 |
67
+ | 2.0048 | 35.2 | 1100 | 2.0593 |
68
+ | 1.9988 | 38.4 | 1200 | 2.0575 |
69
+ | 1.9968 | 41.6 | 1300 | 2.0555 |
70
+ | 1.9908 | 44.8 | 1400 | 2.0548 |
71
+
72
+
73
  ### Framework versions
74
 
75
  - PEFT 0.10.0