Kawon commited on
Commit
47561cf
1 Parent(s): d3f36df

Upload 8 files

Browse files
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "k_proj",
24
  "v_proj",
25
- "q_proj",
26
- "o_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "o_proj",
24
  "k_proj",
25
  "v_proj",
26
+ "q_proj"
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91758a67c2d36dbe7b908bdb1ff9fa5b8d840bedcaefaf23349f1c612cbf68de
3
  size 109086416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68aa2b1c7c2e51a56f45109f3e6b536bc5583635b1c919a7b6fed5f01f8ba2ca
3
  size 109086416
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dfd5128ec3327bedd3f04ce7709fcb8344e84908fb24337165220dfc0c42934
3
  size 54937428
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c86c41d5d224348b3694d7c40a2b212ccc4d94532a1609f88a532b7574e3edb
3
  size 54937428
trainer_state.json CHANGED
@@ -10,32 +10,32 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "grad_norm": 0.566752016544342,
14
  "learning_rate": 0.00020029985007496252,
15
- "loss": 0.7277,
16
  "step": 334
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_loss": 0.6203442811965942,
21
- "eval_runtime": 18.8339,
22
- "eval_samples_per_second": 7.911,
23
- "eval_steps_per_second": 1.009,
24
  "step": 334
25
  },
26
  {
27
  "epoch": 2.0,
28
- "grad_norm": 1.7554653882980347,
29
  "learning_rate": 0.0,
30
- "loss": 0.5489,
31
  "step": 668
32
  },
33
  {
34
  "epoch": 2.0,
35
- "eval_loss": 0.5755637884140015,
36
- "eval_runtime": 18.8718,
37
- "eval_samples_per_second": 7.895,
38
- "eval_steps_per_second": 1.007,
39
  "step": 668
40
  }
41
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "grad_norm": 0.5824499130249023,
14
  "learning_rate": 0.00020029985007496252,
15
+ "loss": 0.7207,
16
  "step": 334
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_loss": 0.6183570027351379,
21
+ "eval_runtime": 19.1158,
22
+ "eval_samples_per_second": 7.795,
23
+ "eval_steps_per_second": 0.994,
24
  "step": 334
25
  },
26
  {
27
  "epoch": 2.0,
28
+ "grad_norm": 1.8464447259902954,
29
  "learning_rate": 0.0,
30
+ "loss": 0.5474,
31
  "step": 668
32
  },
33
  {
34
  "epoch": 2.0,
35
+ "eval_loss": 0.5748867392539978,
36
+ "eval_runtime": 19.0049,
37
+ "eval_samples_per_second": 7.84,
38
+ "eval_steps_per_second": 1.0,
39
  "step": 668
40
  }
41
  ],