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
b966215
•
1 Parent(s): 045e322

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -1
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. all_results.json +3 -3
  5. runs/Jun10_17-49-08_modal/events.out.tfevents.1718041798.modal.2.0 +3 -0
  6. train_results.json +3 -3
  7. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # doplhin-dpo
18
 
19
- This model is a fine-tuned version of [cognitivecomputations/dolphin-2.1-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.1-mistral-7b) on an unknown dataset.
20
 
21
  ## Model description
22
 
 
16
 
17
  # doplhin-dpo
18
 
19
+ This model is a fine-tuned version of [cognitivecomputations/dolphin-2.1-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.1-mistral-7b) on the None dataset.
20
 
21
  ## Model description
22
 
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
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
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "up_proj",
23
+ "down_proj",
24
+ "k_proj",
25
+ "v_proj",
26
  "gate_proj",
27
  "o_proj",
28
+ "q_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 sha256:08c779faaa234dbbafeff29bdb376c83f9a6bc1447175a45fefa70063b5f9cf5
3
  size 1342239008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb6ca5eb120e83a91223b16522505af5c59ceb33d62e45f062833d3968373bb0
3
  size 1342239008
all_results.json CHANGED
@@ -1,7 +1,7 @@
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
  }
 
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
+ "train_runtime": 19.2786,
5
+ "train_samples_per_second": 0.467,
6
+ "train_steps_per_second": 0.104
7
  }
runs/Jun10_17-49-08_modal/events.out.tfevents.1718041798.modal.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc201409e897688bbda60330bcfc439532638a09426ecc9e198f364908aaf66
3
+ size 5088
train_results.json CHANGED
@@ -1,7 +1,7 @@
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
  }
 
1
  {
2
  "epoch": 0.0,
3
  "train_loss": 0.6931471824645996,
4
+ "train_runtime": 19.2786,
5
+ "train_samples_per_second": 0.467,
6
+ "train_steps_per_second": 0.104
7
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28bfb9a5bbdffcd64328629d7bbfbceb92c2aff89d5f6a691365e856daa9f5fd
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b47597d3887e98bc9e79d15aa1922861c944ec0ab372dfe4c118f4f496533bf
3
  size 4664