Hugging Face's logo

edpowers
/
data

Text Generation
PEFT
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
sft
conversational
Model card Files
xet
Community
edpowers commited on
Commit
f71549b
·
verified ·
1 Parent(s): d362f88

End of training

Browse files
Files changed (5) hide show
  1. adapter_config.json +1 -1
  2. all_results.json +6 -6
  3. eval_results.json +3 -3
  4. train_results.json +3 -3
  5. trainer_state.json +3 -3
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "gate_proj",
24
  "q_proj",
25
  "v_proj",
26
- "o_proj",
27
  "k_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "o_proj",
24
  "gate_proj",
25
  "q_proj",
26
  "v_proj",
 
27
  "k_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
all_results.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "epoch": 5.923076923076923,
3
  "eval_loss": 1.2003010511398315,
4
- "eval_runtime": 30.44,
5
  "eval_samples": 169,
6
- "eval_samples_per_second": 2.924,
7
- "eval_steps_per_second": 0.394,
8
  "total_flos": 1.7606154086724403e+17,
9
  "train_loss": 4.533969319902815e-05,
10
- "train_runtime": 4.4113,
11
  "train_samples": 1346,
12
- "train_samples_per_second": 906.752,
13
- "train_steps_per_second": 226.688
14
  }
 
1
  {
2
  "epoch": 5.923076923076923,
3
  "eval_loss": 1.2003010511398315,
4
+ "eval_runtime": 30.5409,
5
  "eval_samples": 169,
6
+ "eval_samples_per_second": 2.914,
7
+ "eval_steps_per_second": 0.393,
8
  "total_flos": 1.7606154086724403e+17,
9
  "train_loss": 4.533969319902815e-05,
10
+ "train_runtime": 4.5185,
11
  "train_samples": 1346,
12
+ "train_samples_per_second": 885.252,
13
+ "train_steps_per_second": 221.313
14
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.923076923076923,
3
  "eval_loss": 1.2003010511398315,
4
- "eval_runtime": 30.44,
5
  "eval_samples": 169,
6
- "eval_samples_per_second": 2.924,
7
- "eval_steps_per_second": 0.394
8
  }
 
1
  {
2
  "epoch": 5.923076923076923,
3
  "eval_loss": 1.2003010511398315,
4
+ "eval_runtime": 30.5409,
5
  "eval_samples": 169,
6
+ "eval_samples_per_second": 2.914,
7
+ "eval_steps_per_second": 0.393
8
  }
train_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 5.923076923076923,
3
  "total_flos": 1.7606154086724403e+17,
4
  "train_loss": 4.533969319902815e-05,
5
- "train_runtime": 4.4113,
6
  "train_samples": 1346,
7
- "train_samples_per_second": 906.752,
8
- "train_steps_per_second": 226.688
9
  }
 
2
  "epoch": 5.923076923076923,
3
  "total_flos": 1.7606154086724403e+17,
4
  "train_loss": 4.533969319902815e-05,
5
+ "train_runtime": 4.5185,
6
  "train_samples": 1346,
7
+ "train_samples_per_second": 885.252,
8
+ "train_steps_per_second": 221.313
9
  }
trainer_state.json CHANGED
@@ -613,9 +613,9 @@
613
  "step": 1001,
614
  "total_flos": 1.7606154086724403e+17,
615
  "train_loss": 4.533969319902815e-05,
616
- "train_runtime": 4.4113,
617
- "train_samples_per_second": 906.752,
618
- "train_steps_per_second": 226.688
619
  }
620
  ],
621
  "logging_steps": 25,
 
613
  "step": 1001,
614
  "total_flos": 1.7606154086724403e+17,
615
  "train_loss": 4.533969319902815e-05,
616
+ "train_runtime": 4.5185,
617
+ "train_samples_per_second": 885.252,
618
+ "train_steps_per_second": 221.313
619
  }
620
  ],
621
  "logging_steps": 25,