chchen commited on
Commit
22212e7
·
verified ·
1 Parent(s): 822a221

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
- "gate_proj",
24
  "o_proj",
25
- "q_proj",
26
- "up_proj",
27
  "k_proj",
 
28
  "down_proj",
29
- "v_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "o_proj",
 
 
24
  "k_proj",
25
+ "up_proj",
26
  "down_proj",
27
+ "q_proj",
28
+ "v_proj",
29
+ "gate_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 sha256:43a5a3399075aa2f36cbf8584d18a4ff7b2af7dcacf0b5653db3ea32a1c4404e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c634bd0177b4c51a862e0f6a658a788b8c63d65ac2963e5e6e928bf303aaa5b2
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 sha256:2c15b8734cf3e58328098763a7185d8c27ccb2dddcbe8c883ae5ff90a4efcc5a
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf66024eb705bc6bbbcf4556ab5af77e90f4c5052dc8d41db6eb8196951ab956
3
  size 5624