Hugging Face's logo

DarshanDeshpande
/
gemma_2b_oasst1_reward_model

PEFT
Safetensors
trl
reward-trainer
Generated from Trainer
Model card Files Community
DarshanDeshpande commited on
Commit
5f274d4
•
1 Parent(s): 8a522e9

gemma_2b_oasst1_reward_model

Browse files
Files changed (5) hide show
  1. README.md +5 -9
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. tokenizer_config.json +1 -1
  5. 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: 0.4481
24
- - Accuracy: 0.8036
25
 
26
  ## Model description
27
 
@@ -55,13 +55,9 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
58
- | 0.4696 | 0.38 | 100 | 0.5181 | 0.7542 |
59
- | 0.4327 | 0.76 | 200 | 0.4738 | 0.8025 |
60
- | 0.3946 | 1.15 | 300 | 0.5145 | 0.7924 |
61
- | 0.3372 | 1.53 | 400 | 0.5370 | 0.7890 |
62
- | 0.3618 | 1.91 | 500 | 0.4481 | 0.8036 |
63
- | 0.3292 | 2.29 | 600 | 0.4799 | 0.7991 |
64
- | 0.4514 | 2.68 | 700 | 0.4763 | 0.8013 |
65
 
66
 
67
  ### 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: 0.4250
24
+ - Accuracy: 0.7881
25
 
26
  ## Model description
27
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
58
+ | 0.443 | 1.0 | 100 | 0.5045 | 0.7458 |
59
+ | 0.4098 | 2.0 | 200 | 0.4312 | 0.7938 |
60
+ | 0.5036 | 2.99 | 300 | 0.4250 | 0.7881 |
 
 
 
 
61
 
62
 
63
  ### Framework versions
adapter_config.json CHANGED
@@ -14,15 +14,15 @@
14
  "megatron_config": null,
15
  "megatron_core": "megatron.core",
16
  "modules_to_save": [
17
- "scores"
18
  ],
19
  "peft_type": "LORA",
20
  "r": 16,
21
  "rank_pattern": {},
22
  "revision": null,
23
  "target_modules": [
24
- "q_proj",
25
- "v_proj"
26
  ],
27
  "task_type": "SEQ_CLS",
28
  "use_dora": false,
 
14
  "megatron_config": null,
15
  "megatron_core": "megatron.core",
16
  "modules_to_save": [
17
+ "score"
18
  ],
19
  "peft_type": "LORA",
20
  "r": 16,
21
  "rank_pattern": {},
22
  "revision": null,
23
  "target_modules": [
24
+ "v_proj",
25
+ "q_proj"
26
  ],
27
  "task_type": "SEQ_CLS",
28
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd018fa832746abef320d15daa2a18ffa499ac099d65fa6cd61eecd8541ef664
3
  size 7390624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fbbe5c5a3cbdef631341ec6ca752168bcbfb155d7263b87eda0c2a0de80bc47
3
  size 7390624
tokenizer_config.json CHANGED
@@ -40,7 +40,7 @@
40
  "device": "cuda",
41
  "eos_token": "<eos>",
42
  "legacy": null,
43
- "max_length": 512,
44
  "model_max_length": 1000000000000000019884624838656,
45
  "pad_token": "<eos>",
46
  "padding": "max_length",
 
40
  "device": "cuda",
41
  "eos_token": "<eos>",
42
  "legacy": null,
43
+ "max_length": 128,
44
  "model_max_length": 1000000000000000019884624838656,
45
  "pad_token": "<eos>",
46
  "padding": "max_length",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b47e8c2a64e60d475eacab92795d3306f950bae04351265e2a2e58e609fba95
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:360893070a94058414051ef16b43089429c4f91060f408d7d06a8d39753745ff
3
  size 4856