Hugging Face's logo

berkamphoon
/
medgemma-27b-it-dr1

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
sft
Model card Files
xet
 Metrics Community
1
berkamphoon commited on
Commit
8cc1a7f
·
verified ·
1 Parent(s): 9a3392a

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. adapter_config.json +8 -8
  3. adapter_model.safetensors +2 -2
  4. runs/Aug17_10-58-21_meedgxh100a/events.out.tfevents.1755442703.meedgxh100a.2464184.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yoon307-kaist/medgemma-27b-it-dr1-Project/runs/pv4gsqem)
31
 
32
 
33
  This model was trained with SFT.
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yoon307-kaist/medgemma-27b-it-dr1-Project/runs/fgq6qofy)
31
 
32
 
33
  This model was trained with SFT.
adapter_config.json CHANGED
@@ -13,7 +13,7 @@
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
- "lora_alpha": 16,
17
  "lora_bias": false,
18
  "lora_dropout": 0.05,
19
  "megatron_config": null,
@@ -24,20 +24,20 @@
24
  ],
25
  "peft_type": "LORA",
26
  "qalora_group_size": 16,
27
- "r": 32,
28
  "rank_pattern": {},
29
  "revision": null,
30
  "target_modules": [
31
  "fc2",
32
- "up_proj",
33
- "down_proj",
34
- "q_proj",
35
  "out_proj",
36
- "o_proj",
 
37
  "fc1",
 
38
  "k_proj",
39
- "v_proj",
40
- "gate_proj"
 
41
  ],
42
  "task_type": "CAUSAL_LM",
43
  "trainable_token_indices": null,
 
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
+ "lora_alpha": 8,
17
  "lora_bias": false,
18
  "lora_dropout": 0.05,
19
  "megatron_config": null,
 
24
  ],
25
  "peft_type": "LORA",
26
  "qalora_group_size": 16,
27
+ "r": 16,
28
  "rank_pattern": {},
29
  "revision": null,
30
  "target_modules": [
31
  "fc2",
 
 
 
32
  "out_proj",
33
+ "up_proj",
34
+ "v_proj",
35
  "fc1",
36
+ "gate_proj",
37
  "k_proj",
38
+ "down_proj",
39
+ "q_proj",
40
+ "o_proj"
41
  ],
42
  "task_type": "CAUSAL_LM",
43
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:329fce20ce20e2dbb0532a3754e76f0eb956b52b87f18dfeb9face5f420dc225
3
- size 6616400680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c799da1f9522cd4c367024c89342d57a81cf1df561cd6e0e0fb7b84d8c6bb376
3
+ size 6127553104
runs/Aug17_10-58-21_meedgxh100a/events.out.tfevents.1755442703.meedgxh100a.2464184.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bffc7a4e25fccfe8e518763b0a02dde6faf87fcdd7688f32d1c4b7f6be65e6a9
3
+ size 9917
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff2725b5f478f317eb2bc69a855ba5891dc8e660df60451e507ced3b3b7a2a17
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa55de11d2621e9d9d3b04c74a4d009f8a42f84dcd893136e46d5577a49fa83
3
  size 5816