aengusl commited on
Commit
ec5edb2
1 Parent(s): 0e2a591

Model save

Browse files
README.md CHANGED
@@ -37,10 +37,10 @@ The following hyperparameters were used during training:
37
  - eval_batch_size: 8
38
  - seed: 4
39
  - distributed_type: multi-GPU
40
- - num_devices: 8
41
  - gradient_accumulation_steps: 4
42
- - total_train_batch_size: 128
43
- - total_eval_batch_size: 64
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - num_epochs: 1
 
37
  - eval_batch_size: 8
38
  - seed: 4
39
  - distributed_type: multi-GPU
40
+ - num_devices: 4
41
  - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 64
43
+ - total_eval_batch_size: 32
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - num_epochs: 1
adapter_config.json CHANGED
@@ -16,11 +16,11 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "down_proj",
20
  "o_proj",
 
21
  "q_proj",
 
22
  "v_proj",
23
- "up_proj",
24
  "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
19
  "o_proj",
20
+ "up_proj",
21
  "q_proj",
22
+ "down_proj",
23
  "v_proj",
 
24
  "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
runs/May16_11-30-42_cdc34a7ce3be/events.out.tfevents.1715859120.cdc34a7ce3be.45452.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a419360961e22e6620c66b4b0ba1506f47d17e8fd535cfa4007c2d2c211d65a
3
+ size 4308
step_0/README.md CHANGED
@@ -204,11 +204,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
204
  ### Framework versions
205
 
206
 
207
- - PEFT 0.6.1
208
- ## Training procedure
209
-
210
-
211
- ### Framework versions
212
-
213
-
214
  - PEFT 0.6.1
 
204
  ### Framework versions
205
 
206
 
 
 
 
 
 
 
 
207
  - PEFT 0.6.1
step_0/adapter_config.json CHANGED
@@ -16,11 +16,11 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "down_proj",
20
  "o_proj",
 
21
  "q_proj",
 
22
  "v_proj",
23
- "up_proj",
24
  "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
19
  "o_proj",
20
+ "up_proj",
21
  "q_proj",
22
+ "down_proj",
23
  "v_proj",
 
24
  "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
step_0/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc4fa0818cb86f43a40da60f9e06070f0ea42d8c3818c25b6d434c49cf50f658
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bbca23412ec822d5964bbd3e1ca1096066165d9488f55efb9fa1a7dd885945e
3
  size 5560
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc4fa0818cb86f43a40da60f9e06070f0ea42d8c3818c25b6d434c49cf50f658
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bbca23412ec822d5964bbd3e1ca1096066165d9488f55efb9fa1a7dd885945e
3
  size 5560