Hugging Face's logo

meixiang123
/
zephyr-7b-dpo-lora

Transformers
Safetensors
Generated from Trainer
dpo
trl
Model card Files Community
meixiang123 commited on
Commit
efe6a57
·
verified ·
1 Parent(s): e098d3a

Training in progress, step 100

Browse files
Files changed (6) hide show
  1. adapter_config.json +4 -4
  2. adapter_model.safetensors +1 -1
  3. all_results.json +2 -2
  4. train_results.json +2 -2
  5. trainer_state.json +2 -2
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -25,13 +25,13 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "q_proj",
29
  "down_proj",
 
30
  "k_proj",
31
- "gate_proj",
32
  "v_proj",
33
- "o_proj",
34
- "up_proj"
35
  ],
36
  "task_type": "CAUSAL_LM",
37
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "gate_proj",
29
  "down_proj",
30
+ "o_proj",
31
  "k_proj",
32
+ "up_proj",
33
  "v_proj",
34
+ "q_proj"
 
35
  ],
36
  "task_type": "CAUSAL_LM",
37
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a1c7da1f07cbd4eed6e35953ffce095d5bf2f5e9d5a48f8140ed925991ca7e
3
  size 1342238560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3107cfa632df771183c34d8afd8c580e00d766c56e0b1c640e99e3b62f7964
3
  size 1342238560
all_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.3465735912322998,
5
- "train_runtime": 120.8001,
6
  "train_samples": 7,
7
- "train_samples_per_second": 0.058,
8
  "train_steps_per_second": 0.008
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.3465735912322998,
5
+ "train_runtime": 122.0397,
6
  "train_samples": 7,
7
+ "train_samples_per_second": 0.057,
8
  "train_steps_per_second": 0.008
9
  }
train_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.3465735912322998,
5
- "train_runtime": 120.8001,
6
  "train_samples": 7,
7
- "train_samples_per_second": 0.058,
8
  "train_steps_per_second": 0.008
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.3465735912322998,
5
+ "train_runtime": 122.0397,
6
  "train_samples": 7,
7
+ "train_samples_per_second": 0.057,
8
  "train_steps_per_second": 0.008
9
  }
trainer_state.json CHANGED
@@ -14,8 +14,8 @@
14
  "step": 1,
15
  "total_flos": 0.0,
16
  "train_loss": 0.3465735912322998,
17
- "train_runtime": 120.8001,
18
- "train_samples_per_second": 0.058,
19
  "train_steps_per_second": 0.008
20
  }
21
  ],
 
14
  "step": 1,
15
  "total_flos": 0.0,
16
  "train_loss": 0.3465735912322998,
17
+ "train_runtime": 122.0397,
18
+ "train_samples_per_second": 0.057,
19
  "train_steps_per_second": 0.008
20
  }
21
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:636717151805b56ca76323fd7e128591cab7bbaba01b1816fd53545c6ccef488
3
  size 6737
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6fdc41add0791e3395c395f37f19db7e7ba829e695c98a385c94299c7278470
3
  size 6737