Hugging Face's logo

grounded-ai
/
phi3-hallucination-judge

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
1
Jlonge4 commited on
Commit
0ec4ac6
•
1 Parent(s): 30fba16

Jlonge4/outputs

Browse files
Files changed (7) hide show
  1. README.md +2 -3
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +2 -2
  4. runs/Jun13_02-39-21_84b89b73e769/events.out.tfevents.1718246362.84b89b73e769.2447.0 +3 -0
  5. runs/Jun13_02-42-49_84b89b73e769/events.out.tfevents.1718246570.84b89b73e769.4299.0 +3 -0
  6. runs/Jun13_02-46-47_84b89b73e769/events.out.tfevents.1718246809.84b89b73e769.5292.0 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0005
39
  - train_batch_size: 2
40
  - eval_batch_size: 8
41
  - seed: 42
@@ -44,8 +44,7 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 10
47
- - training_steps: 20
48
- - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
  - train_batch_size: 2
40
  - eval_batch_size: 8
41
  - seed: 42
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 10
47
+ - training_steps: 150
 
48
 
49
  ### Training results
50
 
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "gate_proj",
24
- "k_proj",
25
  "q_proj",
26
- "up_proj",
27
- "down_proj",
 
28
  "v_proj",
29
- "o_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "q_proj",
24
+ "o_proj",
25
+ "k_proj",
26
+ "gate_proj",
27
  "v_proj",
28
+ "down_proj",
29
+ "up_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 sha256:21b26c4d2931449acf14c09b0c1c3a4c0fe7e486f89e2b9e7a70bc9ddfda41f4
3
- size 71320216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071ad31a0773a3c111fad311d98e8efcd65a29770cfc50c75c4f1772946afa26
3
+ size 35668720
runs/Jun13_02-39-21_84b89b73e769/events.out.tfevents.1718246362.84b89b73e769.2447.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934e72438df96d2f9b75125975e404dedad3951efc8e992a1235be942fc3cdb7
3
+ size 36638
runs/Jun13_02-42-49_84b89b73e769/events.out.tfevents.1718246570.84b89b73e769.4299.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a82494bc367da413b18c38246e05e41c15c0348c263cffa65a8793b8a53cd8
3
+ size 34385
runs/Jun13_02-46-47_84b89b73e769/events.out.tfevents.1718246809.84b89b73e769.5292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c8fbb724a131406141440e08c54e06f6ca2fc4af732de2113ae2ff350bdd60c
3
+ size 36638
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddc2f7a0066efb4e758b012ccf06290a2498c7b11e8c15f86b37d8a4b95d4c0
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9d203829ad04d89369be414f844601686c36143c952b4fae32d4380247fc1d
3
  size 5048