Hugging Face's logo

David-Xu
/
cira-7b-dpo-lora

PEFT
TensorBoard
Safetensors
llama
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
David-Xu commited on
Commit
f4a89a5
·
verified ·
1 Parent(s): 4c7509c

Model save

Browse files
Files changed (8) hide show
  1. adapter_config.json +3 -3
  2. all_results.json +6 -6
  3. eval_results.json +3 -3
  4. runs/Mar11_07-16-34_b89f062cf3e1/events.out.tfevents.1710141453.b89f062cf3e1.24911.0 +3 -0
  5. runs/Mar11_07-16-34_b89f062cf3e1/events.out.tfevents.1710142031.b89f062cf3e1.24911.1 +3 -0
  6. train_results.json +3 -3
  7. trainer_state.json +3 -3
  8. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "o_proj",
23
  "up_proj",
24
- "down_proj",
25
  "k_proj",
26
  "v_proj",
27
  "gate_proj",
28
- "q_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "up_proj",
23
+ "q_proj",
24
  "k_proj",
25
  "v_proj",
26
  "gate_proj",
27
+ "down_proj",
28
+ "o_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
all_results.json CHANGED
@@ -9,13 +9,13 @@
9
  "eval_rewards/chosen": 0.5534913539886475,
10
  "eval_rewards/margins": 0.214975506067276,
11
  "eval_rewards/rejected": 0.33851587772369385,
12
- "eval_runtime": 181.731,
13
  "eval_samples": 398,
14
- "eval_samples_per_second": 2.19,
15
- "eval_steps_per_second": 2.19,
16
  "train_loss": 0.06080360662445443,
17
- "train_runtime": 395.7009,
18
  "train_samples": 3588,
19
- "train_samples_per_second": 9.067,
20
- "train_steps_per_second": 2.267
21
  }
 
9
  "eval_rewards/chosen": 0.5534913539886475,
10
  "eval_rewards/margins": 0.214975506067276,
11
  "eval_rewards/rejected": 0.33851587772369385,
12
+ "eval_runtime": 182.0633,
13
  "eval_samples": 398,
14
+ "eval_samples_per_second": 2.186,
15
+ "eval_steps_per_second": 2.186,
16
  "train_loss": 0.06080360662445443,
17
+ "train_runtime": 396.0244,
18
  "train_samples": 3588,
19
+ "train_samples_per_second": 9.06,
20
+ "train_steps_per_second": 2.265
21
  }
eval_results.json CHANGED
@@ -9,8 +9,8 @@
9
  "eval_rewards/chosen": 0.5534913539886475,
10
  "eval_rewards/margins": 0.214975506067276,
11
  "eval_rewards/rejected": 0.33851587772369385,
12
- "eval_runtime": 181.731,
13
  "eval_samples": 398,
14
- "eval_samples_per_second": 2.19,
15
- "eval_steps_per_second": 2.19
16
  }
 
9
  "eval_rewards/chosen": 0.5534913539886475,
10
  "eval_rewards/margins": 0.214975506067276,
11
  "eval_rewards/rejected": 0.33851587772369385,
12
+ "eval_runtime": 182.0633,
13
  "eval_samples": 398,
14
+ "eval_samples_per_second": 2.186,
15
+ "eval_steps_per_second": 2.186
16
  }
runs/Mar11_07-16-34_b89f062cf3e1/events.out.tfevents.1710141453.b89f062cf3e1.24911.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65749c701d749b19f74028d18f861599db841d2cf63df4f00bf4e3e127bbd9c
3
+ size 11021
runs/Mar11_07-16-34_b89f062cf3e1/events.out.tfevents.1710142031.b89f062cf3e1.24911.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4312817dd381f1ce94651c8da6e3424b36b99cc5961f48015fd28c2d779a4e65
3
+ size 828
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.06080360662445443,
4
- "train_runtime": 395.7009,
5
  "train_samples": 3588,
6
- "train_samples_per_second": 9.067,
7
- "train_steps_per_second": 2.267
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.06080360662445443,
4
+ "train_runtime": 396.0244,
5
  "train_samples": 3588,
6
+ "train_samples_per_second": 9.06,
7
+ "train_steps_per_second": 2.265
8
  }
trainer_state.json CHANGED
@@ -1401,9 +1401,9 @@
1401
  "step": 897,
1402
  "total_flos": 0.0,
1403
  "train_loss": 0.06080360662445443,
1404
- "train_runtime": 395.7009,
1405
- "train_samples_per_second": 9.067,
1406
- "train_steps_per_second": 2.267
1407
  }
1408
  ],
1409
  "logging_steps": 10,
 
1401
  "step": 897,
1402
  "total_flos": 0.0,
1403
  "train_loss": 0.06080360662445443,
1404
+ "train_runtime": 396.0244,
1405
+ "train_samples_per_second": 9.06,
1406
+ "train_steps_per_second": 2.265
1407
  }
1408
  ],
1409
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb9bb8efdb9c6841452004c47a87a4862f6eeb584a1259066be691727e36b983
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08158f8de09de548b5fa100048a5c91d786e4bd87dbf7215b24a3082f6775961
3
  size 4856