sridhar1111111111111111 commited on
Commit
e96b855
1 Parent(s): ab90aef

gemma2B-It-Medical-Finetuned-2epochs

Browse files
README.md CHANGED
@@ -37,13 +37,13 @@ More information needed
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0002
39
  - train_batch_size: 2
40
- - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 8
43
  - total_train_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 2
47
 
48
  ### Training results
49
 
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0002
39
  - train_batch_size: 2
40
+ - eval_batch_size: 2
41
  - seed: 42
42
  - gradient_accumulation_steps: 8
43
  - total_train_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - training_steps: 140
47
 
48
  ### Training results
49
 
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "google/gemma-2b-it",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -15,17 +15,17 @@
15
  "megatron_core": "megatron.core",
16
  "modules_to_save": null,
17
  "peft_type": "LORA",
18
- "r": 32,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "k_proj",
23
- "down_proj",
24
  "q_proj",
25
  "up_proj",
 
 
 
26
  "gate_proj",
27
- "o_proj",
28
- "v_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
15
  "megatron_core": "megatron.core",
16
  "modules_to_save": null,
17
  "peft_type": "LORA",
18
+ "r": 16,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "q_proj",
23
  "up_proj",
24
+ "down_proj",
25
+ "v_proj",
26
+ "k_proj",
27
  "gate_proj",
28
+ "o_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:934c9dc96cbcbdf7a0291059d54fad03ea27608fa06c284ed0be9e650bc1b8c3
3
- size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564baef948c1c3ec200d528fd06a5fcd757bff2b54a677d3190b1dae17846cb8
3
+ size 78484352
runs/Mar27_09-49-24_5c1c4e61306f/events.out.tfevents.1711532972.5c1c4e61306f.406.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5270e5a589353335a36f2a78ad9adb0cfe06ccc49d1b674be5f333b7c32c41f
3
+ size 4996
runs/Mar27_09-50-41_5c1c4e61306f/events.out.tfevents.1711533047.5c1c4e61306f.406.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2aa91aba0cadf3fbb7987d2d125bd9d93617195d7a91e1e982786edac16a43
3
+ size 8257
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77c7ac08fea4403b0d9beed0ef5095552d19edd85f199fb8f60683b4c33202f6
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d762cae44da0ef032ea87b818369afc5bca58006ca7507457c9fb71cee95e261
3
  size 4920