Hugging Face's logo

kyryl-opens-ml
/
doplhin-dpo

PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
Model card Files Metrics Community
kyryl-opens-ml commited on
Commit
045e322
•
1 Parent(s): d39eb7b

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -1
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. all_results.json +3 -3
  5. runs/Jun10_01-23-48_ip-172-31-4-18/events.out.tfevents.1717982674.ip-172-31-4-18.3691.0 +3 -0
  6. train_results.json +3 -3
  7. training_args.bin +1 -1
README.md CHANGED
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.1
47
- - num_epochs: 0.0001
48
 
49
  ### Training results
50
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 0.001
48
 
49
  ### Training results
50
 
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "gate_proj",
 
23
  "q_proj",
 
24
  "o_proj",
25
- "up_proj",
26
- "k_proj",
27
- "v_proj",
28
- "down_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "k_proj",
23
+ "up_proj",
24
  "q_proj",
25
+ "gate_proj",
26
  "o_proj",
27
+ "down_proj",
28
+ "v_proj"
 
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d895935c1e1d8f12fefcd1d610474ba982c26505088a4b0e47648c07feea196
3
  size 1342239008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c779faaa234dbbafeff29bdb376c83f9a6bc1447175a45fefa70063b5f9cf5
3
  size 1342239008
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
- "train_runtime": 22.7564,
5
- "train_samples_per_second": 0.04,
6
- "train_steps_per_second": 0.044
7
  }
 
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
+ "train_runtime": 56.9215,
5
+ "train_samples_per_second": 0.158,
6
+ "train_steps_per_second": 0.035
7
  }
runs/Jun10_01-23-48_ip-172-31-4-18/events.out.tfevents.1717982674.ip-172-31-4-18.3691.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b49debb792440c288cb33381a56059da6d222c21caf5575eeadd17349714e483
3
+ size 5097
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
- "train_runtime": 22.7564,
5
- "train_samples_per_second": 0.04,
6
- "train_steps_per_second": 0.044
7
  }
 
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
+ "train_runtime": 56.9215,
5
+ "train_samples_per_second": 0.158,
6
+ "train_steps_per_second": 0.035
7
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc85119d32ecf4f56e19f8b3bd35e80173ca9a792cd584d0d6d5711a53eba9de
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28bfb9a5bbdffcd64328629d7bbfbceb92c2aff89d5f6a691365e856daa9f5fd
3
  size 4664