Hugging Face's logo

sofyc
/
Gemma-2b-MultiCap-mt

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
sofyc commited on
Commit
338714c
•
1 Parent(s): e65e4d8

commit

Browse files
Files changed (4) hide show
  1. README.md +9 -9
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.9009
22
 
23
  ## Model description
24
 
@@ -46,19 +46,19 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.03
49
- - num_epochs: 2
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
- | 0.8793 | 0.2554 | 100 | 0.9322 |
56
- | 0.9059 | 0.5109 | 200 | 0.8803 |
57
- | 0.8399 | 0.7663 | 300 | 0.8680 |
58
- | 0.7227 | 1.0217 | 400 | 0.8711 |
59
- | 0.7079 | 1.2771 | 500 | 0.8840 |
60
- | 0.6536 | 1.5326 | 600 | 0.8905 |
61
- | 0.7085 | 1.7880 | 700 | 0.9009 |
62
 
63
 
64
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8644
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.03
49
+ - num_epochs: 1
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.1429 | 0.1277 | 50 | 1.1222 |
56
+ | 0.8782 | 0.2554 | 100 | 0.9298 |
57
+ | 0.8032 | 0.3831 | 150 | 0.8972 |
58
+ | 0.9111 | 0.5109 | 200 | 0.8814 |
59
+ | 0.8477 | 0.6386 | 250 | 0.8734 |
60
+ | 0.8528 | 0.7663 | 300 | 0.8679 |
61
+ | 0.8024 | 0.8940 | 350 | 0.8644 |
62
 
63
 
64
  ### Framework versions
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj",
25
- "k_proj",
26
- "down_proj",
27
  "o_proj",
28
  "up_proj",
29
- "gate_proj"
 
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
 
23
  "o_proj",
24
  "up_proj",
25
+ "gate_proj",
26
+ "k_proj",
27
+ "q_proj",
28
+ "down_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92d8006185f2ff35c9c3b1b138b24219f706e074f5baab5f92d2ebbf9091fb17
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f85cb1dd72e4a37416c5536a13afa107dfb6bf1ca12e54c43b2d81a07d4e661
3
  size 83115256
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:535ff769450ab9748dfd329f86c5973c530384dd7525e1c778b0ef4b9ff34cdf
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d3555ecfec0b1c0eee0381a276f88762ecc6cd4069bcb020627adf589134da1
3
  size 5496