happii commited on
Commit
0573214
1 Parent(s): 5dc1ddb

End of training

Browse files
README.md CHANGED
@@ -2,9 +2,15 @@
2
  license: apache-2.0
3
  base_model: alignment-handbook/zephyr-7b-sft-full
4
  tags:
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
 
 
 
 
 
8
  model-index:
9
  - name: zephyr-7b-dpo-full
10
  results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # zephyr-7b-dpo-full
17
 
18
- This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5280
21
- - Rewards/chosen: -0.0160
22
- - Rewards/rejected: -1.2503
23
- - Rewards/accuracies: 0.7798
24
- - Rewards/margins: 1.2343
25
- - Logps/rejected: -272.7223
26
- - Logps/chosen: -282.1141
27
- - Logits/rejected: -2.5362
28
- - Logits/chosen: -2.5901
29
 
30
  ## Model description
31
 
 
2
  license: apache-2.0
3
  base_model: alignment-handbook/zephyr-7b-sft-full
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - dpo
8
  - generated_from_trainer
9
+ - trl
10
+ - dpo
11
+ - generated_from_trainer
12
+ datasets:
13
+ - HuggingFaceH4/ultrafeedback_binarized
14
  model-index:
15
  - name: zephyr-7b-dpo-full
16
  results: []
 
21
 
22
  # zephyr-7b-dpo-full
23
 
24
+ This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
25
  It achieves the following results on the evaluation set:
26
+ - Loss: 0.5283
27
+ - Rewards/chosen: -0.0163
28
+ - Rewards/rejected: -1.2467
29
+ - Rewards/accuracies: 0.7738
30
+ - Rewards/margins: 1.2304
31
+ - Logps/rejected: -272.6863
32
+ - Logps/chosen: -282.1169
33
+ - Logits/rejected: -2.5360
34
+ - Logits/chosen: -2.5900
35
 
36
  ## Model description
37
 
all_results.json CHANGED
@@ -1,5 +1,18 @@
1
  {
2
  "epoch": 0.9994767137624281,
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "total_flos": 0.0,
4
  "train_loss": 0.528570184657711,
5
  "train_runtime": 17823.4182,
 
1
  {
2
  "epoch": 0.9994767137624281,
3
+ "eval_logits/chosen": -2.5900135040283203,
4
+ "eval_logits/rejected": -2.5359914302825928,
5
+ "eval_logps/chosen": -282.1169128417969,
6
+ "eval_logps/rejected": -272.686279296875,
7
+ "eval_loss": 0.5283266305923462,
8
+ "eval_rewards/accuracies": 0.773809552192688,
9
+ "eval_rewards/chosen": -0.016292406246066093,
10
+ "eval_rewards/margins": 1.2304461002349854,
11
+ "eval_rewards/rejected": -1.2467385530471802,
12
+ "eval_runtime": 205.7802,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 9.719,
15
+ "eval_steps_per_second": 0.306,
16
  "total_flos": 0.0,
17
  "train_loss": 0.528570184657711,
18
  "train_runtime": 17823.4182,
config.json CHANGED
@@ -21,6 +21,6 @@
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.2",
24
- "use_cache": false,
25
  "vocab_size": 32000
26
  }
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.2",
24
+ "use_cache": true,
25
  "vocab_size": 32000
26
  }
eval_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "epoch": 2.998430141287284,
3
- "eval_logits/chosen": -1.6524701118469238,
4
- "eval_logits/rejected": -1.3897571563720703,
5
- "eval_logps/chosen": -346.02056884765625,
6
- "eval_logps/rejected": -366.2360534667969,
7
- "eval_loss": 0.910855770111084,
8
- "eval_rewards/accuracies": 0.7658730149269104,
9
- "eval_rewards/chosen": -6.40665864944458,
10
- "eval_rewards/margins": 4.195058822631836,
11
- "eval_rewards/rejected": -10.601717948913574,
12
- "eval_runtime": 196.377,
13
  "eval_samples": 2000,
14
- "eval_samples_per_second": 10.184,
15
- "eval_steps_per_second": 0.321
16
  }
 
1
  {
2
+ "epoch": 0.9994767137624281,
3
+ "eval_logits/chosen": -2.5900135040283203,
4
+ "eval_logits/rejected": -2.5359914302825928,
5
+ "eval_logps/chosen": -282.1169128417969,
6
+ "eval_logps/rejected": -272.686279296875,
7
+ "eval_loss": 0.5283266305923462,
8
+ "eval_rewards/accuracies": 0.773809552192688,
9
+ "eval_rewards/chosen": -0.016292406246066093,
10
+ "eval_rewards/margins": 1.2304461002349854,
11
+ "eval_rewards/rejected": -1.2467385530471802,
12
+ "eval_runtime": 205.7802,
13
  "eval_samples": 2000,
14
+ "eval_samples_per_second": 9.719,
15
+ "eval_steps_per_second": 0.306
16
  }
runs/May20_07-04-40_ubuntu/events.out.tfevents.1716207476.ubuntu.3046003.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c2f0d2ed582128028d0141290fc61270e2b7293e6717dfe4fb0a20772b0182
3
+ size 828