chchen commited on
Commit
c62ebd1
·
verified ·
1 Parent(s): 257f8db

Training in progress, step 50

Browse files
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "o_proj",
24
  "up_proj",
25
- "v_proj",
26
  "down_proj",
27
- "k_proj",
28
  "q_proj",
29
- "gate_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "up_proj",
 
24
  "down_proj",
25
+ "o_proj",
26
  "q_proj",
27
+ "gate_proj",
28
+ "v_proj",
29
+ "k_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:befa4743074c2e4c6e4d8307b8a4f07454c0a3a089fd6a2d420f67e5110e3b58
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66308727f5324fc611537bde1ee06047e1ff9fd4877aa000fb4c5b738c9589f7
3
  size 83945296
llama3_lora_sft.yaml CHANGED
@@ -32,7 +32,7 @@ load_best_model_at_end: true
32
  per_device_train_batch_size: 1
33
  gradient_accumulation_steps: 16
34
  learning_rate: 1.0e-4
35
- num_train_epochs: 10.0
36
  lr_scheduler_type: cosine
37
  warmup_ratio: 0.1
38
  bf16: true
 
32
  per_device_train_batch_size: 1
33
  gradient_accumulation_steps: 16
34
  learning_rate: 1.0e-4
35
+ num_train_epochs: 5.0
36
  lr_scheduler_type: cosine
37
  warmup_ratio: 0.1
38
  bf16: true
trainer_log.jsonl CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f611d41792e5bb5b9e0318681d9b9f2b3da4bc00a7a497b4e52d25683732f89e
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d30032dcce2ecb3fb1beac38c4eab9fd77919717b940d3de1b61bf5c192772d
3
  size 5624