Hugging Face's logo

LaoRay
/
zephyr-7b-dpo-lora-r16-20k

PEFT
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
Model card Files Community
LaoRay commited on
Commit
3d66330
•
1 Parent(s): 82af11b

Model save

Browse files
Files changed (6) hide show
  1. README.md +1 -0
  2. adapter_config.json +2 -2
  3. all_results.json +3 -3
  4. train_results.json +3 -3
  5. trainer_state.json +3 -3
  6. training_args.bin +1 -1
README.md CHANGED
@@ -5,6 +5,7 @@ license: apache-2.0
5
  tags:
6
  - trl
7
  - dpo
 
8
  - generated_from_trainer
9
  model-index:
10
  - name: zephyr-7b-dpo-lora-r16-20k
 
5
  tags:
6
  - trl
7
  - dpo
8
+ - alignment-handbook
9
  - generated_from_trainer
10
  model-index:
11
  - name: zephyr-7b-dpo-lora-r16-20k
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "o_proj",
 
24
  "down_proj",
25
  "up_proj",
26
  "q_proj",
27
- "k_proj",
28
- "v_proj",
29
  "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
24
  "o_proj",
25
+ "k_proj",
26
  "down_proj",
27
  "up_proj",
28
  "q_proj",
 
 
29
  "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
all_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.0,
5
- "train_runtime": 0.007,
6
  "train_samples": 20000,
7
- "train_samples_per_second": 2851328.348,
8
- "train_steps_per_second": 178208.022
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.0,
5
+ "train_runtime": 0.0069,
6
  "train_samples": 20000,
7
+ "train_samples_per_second": 2900725.475,
8
+ "train_steps_per_second": 181295.342
9
  }
train_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.0,
5
- "train_runtime": 0.007,
6
  "train_samples": 20000,
7
- "train_samples_per_second": 2851328.348,
8
- "train_steps_per_second": 178208.022
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.0,
5
+ "train_runtime": 0.0069,
6
  "train_samples": 20000,
7
+ "train_samples_per_second": 2900725.475,
8
+ "train_steps_per_second": 181295.342
9
  }
trainer_state.json CHANGED
@@ -3970,9 +3970,9 @@
3970
  "step": 1250,
3971
  "total_flos": 0.0,
3972
  "train_loss": 0.0,
3973
- "train_runtime": 0.007,
3974
- "train_samples_per_second": 2851328.348,
3975
- "train_steps_per_second": 178208.022
3976
  }
3977
  ],
3978
  "logging_steps": 5,
 
3970
  "step": 1250,
3971
  "total_flos": 0.0,
3972
  "train_loss": 0.0,
3973
+ "train_runtime": 0.0069,
3974
+ "train_samples_per_second": 2900725.475,
3975
+ "train_steps_per_second": 181295.342
3976
  }
3977
  ],
3978
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1be4d7d17cad82502d0bb662ad8f3519df18c33c47b46c125a7d71e70f88371f
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2a38aa27b8c8dede634e556cdce1523f6cce7ce69726d505dc21c0ad9a1925
3
  size 6200