tomtseng commited on
Commit
bb35968
·
verified ·
1 Parent(s): bc51537

Model save

Browse files
README.md CHANGED
@@ -38,10 +38,10 @@ The following hyperparameters were used during training:
38
  - eval_batch_size: 2
39
  - seed: 42
40
  - distributed_type: multi-GPU
41
- - num_devices: 8
42
  - gradient_accumulation_steps: 4
43
- - total_train_batch_size: 32
44
- - total_eval_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - num_epochs: 1
 
38
  - eval_batch_size: 2
39
  - seed: 42
40
  - distributed_type: multi-GPU
41
+ - num_devices: 4
42
  - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
+ - total_eval_batch_size: 8
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - num_epochs: 1
adapter_config.json CHANGED
@@ -17,9 +17,9 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
  "q_proj",
22
- "o_proj"
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
 
20
  "q_proj",
21
+ "o_proj",
22
+ "k_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
runs/Feb02_02-31-29_r2d2-devbox-526kp/events.out.tfevents.1738463538.r2d2-devbox-526kp.5134.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c9d280afedbad93bd14ee7cbef5a98d8bbc166dcea4c53376673701568bec27
3
- size 4623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977bab48965b2642463a8661d46e775739bca53b047a4e2f98050324d33285df
3
+ size 4777
runs/Feb02_02-40-30_r2d2-devbox-526kp/events.out.tfevents.1738464121.r2d2-devbox-526kp.6439.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36f2eb54ffd28aec670411be5b819b3f998095f29ca3f9b9bfb2ec3086f99f8
3
+ size 4623
step_0/README.md CHANGED
@@ -210,4 +210,11 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
210
  ### Framework versions
211
 
212
 
 
 
 
 
 
 
 
213
  - PEFT 0.6.1
 
210
  ### Framework versions
211
 
212
 
213
+ - PEFT 0.6.1
214
+ ## Training procedure
215
+
216
+
217
+ ### Framework versions
218
+
219
+
220
  - PEFT 0.6.1
step_0/adapter_config.json CHANGED
@@ -17,9 +17,9 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
  "q_proj",
22
- "o_proj"
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
 
20
  "q_proj",
21
+ "o_proj",
22
+ "k_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
step_0/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd29f6ce8baa4403da6138b1ab6401e9f3f3e2e8b1f571f87bed547b2cef427f
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b7fa8c0100cd3ab2d2892a83d4076fea72c4ea1964bb99bf16a2e950e46ee1
3
  size 5816
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd29f6ce8baa4403da6138b1ab6401e9f3f3e2e8b1f571f87bed547b2cef427f
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b7fa8c0100cd3ab2d2892a83d4076fea72c4ea1964bb99bf16a2e950e46ee1
3
  size 5816