tomtseng commited on
Commit
8ef153f
·
verified ·
1 Parent(s): d67be9c

Model save

Browse files
README.md CHANGED
@@ -34,12 +34,12 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
- - train_batch_size: 4
38
- - eval_batch_size: 8
39
  - seed: 42
40
  - distributed_type: multi-GPU
41
- - gradient_accumulation_steps: 128
42
- - total_train_batch_size: 512
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - num_epochs: 1
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 16
39
  - seed: 42
40
  - distributed_type: multi-GPU
41
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 32
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - num_epochs: 1
adapter_config.json CHANGED
@@ -16,10 +16,10 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "k_proj",
20
- "q_proj",
21
  "v_proj",
22
- "o_proj"
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
+ "o_proj",
 
20
  "v_proj",
21
+ "k_proj",
22
+ "q_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
runs/Feb01_16-42-58_r2d2-tom-000-train-lora-t4whq/events.out.tfevents.1738428322.r2d2-tom-000-train-lora-t4whq.96.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbf1a6f080620a0a6868857852f6d8a3de1595c7e013e051718486078fb9262b
3
- size 4711
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9aba495b02ccda8d60922bc521640398ecb61207a84f1c19cdfc18112183e7
3
+ size 5019
runs/Feb01_23-21-59_r2d2-tom-000b-train-lora-pl9d7/events.out.tfevents.1738452258.r2d2-tom-000b-train-lora-pl9d7.96.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8e818c4f29f92eacb112a39c779bcbab81dd0a966e50759226c048173df3ec0
3
+ size 4712
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbd2f1ef498e93094a0ce00de27829921f4592d024d9a6f82dffa6af10ec9bd1
3
  size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256c32577978daf1314879c1a40d5d309652be85248145f60cc9352f169e81a8
3
  size 5880