Hugging Face's logo

CriteriaPO
/
llama3.2-3b-orpo-vanilla

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
trl
orpo
conversational
text-generation-inference
Model card Files Community
obiwit commited on
Commit
122b490
·
verified ·
1 Parent(s): ffaa77f

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +3 -3
  2. config.json +1 -1
  3. eval_results.json +3 -3
all_results.json CHANGED
@@ -12,10 +12,10 @@
12
  "eval_rewards/chosen": -0.07526461780071259,
13
  "eval_rewards/margins": 0.02905045822262764,
14
  "eval_rewards/rejected": -0.10431348532438278,
15
- "eval_runtime": 2433.1431,
16
  "eval_samples": 189840,
17
- "eval_samples_per_second": 78.014,
18
- "eval_steps_per_second": 1.219,
19
  "total_flos": 0.0,
20
  "train_loss": 0.0,
21
  "train_runtime": 23.1532,
 
12
  "eval_rewards/chosen": -0.07526461780071259,
13
  "eval_rewards/margins": 0.02905045822262764,
14
  "eval_rewards/rejected": -0.10431348532438278,
15
+ "eval_runtime": 2395.4247,
16
  "eval_samples": 189840,
17
+ "eval_samples_per_second": 79.242,
18
+ "eval_steps_per_second": 1.238,
19
  "total_flos": 0.0,
20
  "train_loss": 0.0,
21
  "train_runtime": 23.1532,
config.json CHANGED
@@ -31,6 +31,6 @@
31
  "tie_word_embeddings": true,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.46.3",
34
- "use_cache": false,
35
  "vocab_size": 128256
36
  }
 
31
  "tie_word_embeddings": true,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.46.3",
34
+ "use_cache": true,
35
  "vocab_size": 128256
36
  }
eval_results.json CHANGED
@@ -12,8 +12,8 @@
12
  "eval_rewards/chosen": -0.07526461780071259,
13
  "eval_rewards/margins": 0.02905045822262764,
14
  "eval_rewards/rejected": -0.10431348532438278,
15
- "eval_runtime": 2433.1431,
16
  "eval_samples": 189840,
17
- "eval_samples_per_second": 78.014,
18
- "eval_steps_per_second": 1.219
19
  }
 
12
  "eval_rewards/chosen": -0.07526461780071259,
13
  "eval_rewards/margins": 0.02905045822262764,
14
  "eval_rewards/rejected": -0.10431348532438278,
15
+ "eval_runtime": 2395.4247,
16
  "eval_samples": 189840,
17
+ "eval_samples_per_second": 79.242,
18
+ "eval_steps_per_second": 1.238
19
  }