chchen commited on
Commit
ccb8fa9
·
verified ·
1 Parent(s): 7591e69

Training in progress, step 50

Browse files
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "o_proj",
24
  "k_proj",
25
  "q_proj",
26
  "up_proj",
27
  "down_proj",
28
- "gate_proj",
29
  "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "gate_proj",
24
  "o_proj",
25
  "k_proj",
26
  "q_proj",
27
  "up_proj",
28
  "down_proj",
 
29
  "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2a957f2151fb59259fc296276bff510193efabf0060dc2f5597ae0fdee27027
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28a428d4ca4666695cda63c0eb4ae5976c54c5a4d194d2a3836a381cc4cf908f
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:c580e02fc0aded5e2fc413f6d17b0eac654e57e5bdf12a61e03392930222696d
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3f0eca089fad8d8643b00136ba3927a79bc1f279ab4cb89ea19d292dae0a71
3
  size 5624