Hugging Face's logo

Baidicoot
/
run-gemma

PEFT
Safetensors
trl
reward-trainer
Generated from Trainer
Model card Files
xet
 Community
Baidicoot commited on
Commit
a6c258c
·
verified ·
1 Parent(s): 054f29d

End of training

Browse files
Files changed (4) hide show
  1. README.md +23 -22
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4736
24
- - Accuracy: 0.8
25
 
26
  ## Model description
27
 
@@ -46,32 +46,33 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
 
49
  - training_steps: 200
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | 0.7109 | 0.2941 | 10 | 0.7341 | 0.3684 |
56
- | 0.7148 | 0.5882 | 20 | 0.7228 | 0.3947 |
57
- | 0.6992 | 0.8824 | 30 | 0.7039 | 0.4895 |
58
- | 0.668 | 1.1765 | 40 | 0.6780 | 0.5789 |
59
- | 0.6328 | 1.4706 | 50 | 0.6501 | 0.6474 |
60
- | 0.6211 | 1.7647 | 60 | 0.6144 | 0.6737 |
61
- | 0.5781 | 2.0588 | 70 | 0.5833 | 0.6842 |
62
- | 0.5156 | 2.3529 | 80 | 0.5591 | 0.7 |
63
- | 0.5352 | 2.6471 | 90 | 0.5355 | 0.7368 |
64
- | 0.5508 | 2.9412 | 100 | 0.5179 | 0.7421 |
65
- | 0.543 | 3.2353 | 110 | 0.4917 | 0.7579 |
66
- | 0.4141 | 3.5294 | 120 | 0.4833 | 0.7684 |
67
- | 0.4102 | 3.8235 | 130 | 0.4706 | 0.7737 |
68
- | 0.4316 | 4.1176 | 140 | 0.4643 | 0.7789 |
69
- | 0.4844 | 4.4118 | 150 | 0.4683 | 0.8 |
70
- | 0.4199 | 4.7059 | 160 | 0.4668 | 0.8 |
71
- | 0.4082 | 5.0 | 170 | 0.4795 | 0.7842 |
72
- | 0.3516 | 5.2941 | 180 | 0.4804 | 0.7842 |
73
- | 0.4238 | 5.5882 | 190 | 0.4826 | 0.7947 |
74
- | 0.3867 | 5.8824 | 200 | 0.4736 | 0.8 |
75
 
76
 
77
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.4238
24
+ - Accuracy: 0.7778
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 20
50
  - training_steps: 200
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|
56
+ | 0.7031 | 0.1087 | 10 | 0.6740 | 0.5752 |
57
+ | 0.6719 | 0.2174 | 20 | 0.6701 | 0.6046 |
58
+ | 0.6602 | 0.3261 | 30 | 0.6497 | 0.6601 |
59
+ | 0.6367 | 0.4348 | 40 | 0.6113 | 0.7059 |
60
+ | 0.6172 | 0.5435 | 50 | 0.5686 | 0.7320 |
61
+ | 0.5625 | 0.6522 | 60 | 0.5276 | 0.7451 |
62
+ | 0.5664 | 0.7609 | 70 | 0.4938 | 0.7451 |
63
+ | 0.5859 | 0.8696 | 80 | 0.4651 | 0.7712 |
64
+ | 0.5 | 0.9783 | 90 | 0.4560 | 0.7647 |
65
+ | 0.5898 | 1.0870 | 100 | 0.4560 | 0.7582 |
66
+ | 0.5664 | 1.1957 | 110 | 0.4459 | 0.7516 |
67
+ | 0.4648 | 1.3043 | 120 | 0.4387 | 0.7745 |
68
+ | 0.5117 | 1.4130 | 130 | 0.4306 | 0.7712 |
69
+ | 0.4219 | 1.5217 | 140 | 0.4239 | 0.7680 |
70
+ | 0.3828 | 1.6304 | 150 | 0.4314 | 0.7680 |
71
+ | 0.3789 | 1.7391 | 160 | 0.4319 | 0.7647 |
72
+ | 0.3828 | 1.8478 | 170 | 0.4291 | 0.7680 |
73
+ | 0.3438 | 1.9565 | 180 | 0.4279 | 0.7745 |
74
+ | 0.3496 | 2.0652 | 190 | 0.4274 | 0.7712 |
75
+ | 0.3945 | 2.1739 | 200 | 0.4238 | 0.7778 |
76
 
77
 
78
  ### Framework versions
adapter_config.json CHANGED
@@ -25,13 +25,13 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "gate_proj",
29
- "k_proj",
30
  "o_proj",
31
- "down_proj",
32
- "v_proj",
33
  "q_proj",
34
- "up_proj"
 
 
 
35
  ],
36
  "task_type": "SEQ_CLS",
37
  "use_dora": false,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
 
28
  "o_proj",
29
+ "k_proj",
 
30
  "q_proj",
31
+ "up_proj",
32
+ "gate_proj",
33
+ "v_proj",
34
+ "down_proj"
35
  ],
36
  "task_type": "SEQ_CLS",
37
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b05d6ee9218a751f915d98379e369ceafb80bd3cd5541fa88499982c9bc311a
3
  size 39260648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1830e519b9fb4dfa4e4c42a3a24e90246f11070dd81e5207fe8bb2b6b993a858
3
  size 39260648
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32843623ebe38f8ab6155e3692cf643a1e11e57840ee40996c7cd8a239283642
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5fe4c47db0ef08955bd7d9219f1ad59a76a9ba1728b459dff4c3c272321f78
3
  size 5240