abgoswam commited on
Commit
d9c1301
1 Parent(s): 1b22adc

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 the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5000
21
- - Rewards/chosen: -2.3681
22
- - Rewards/rejected: -3.4811
23
  - Rewards/accuracies: 0.7695
24
- - Rewards/margins: 1.1129
25
- - Logps/rejected: -610.7911
26
- - Logps/chosen: -499.4172
27
- - Logits/rejected: -0.0390
28
- - Logits/chosen: -0.5081
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: 0.4983
27
+ - Rewards/chosen: -2.4880
28
+ - Rewards/rejected: -3.6063
29
  - Rewards/accuracies: 0.7695
30
+ - Rewards/margins: 1.1182
31
+ - Logps/rejected: -623.3074
32
+ - Logps/chosen: -511.4043
33
+ - Logits/rejected: 0.0233
34
+ - Logits/chosen: -0.4369
35
 
36
  ## Model description
37
 
all_results.json CHANGED
@@ -1,5 +1,18 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "train_loss": 0.535196884905444,
4
  "train_runtime": 3527.4214,
5
  "train_samples": 61135,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_logits/chosen": -0.43692123889923096,
4
+ "eval_logits/rejected": 0.023339029401540756,
5
+ "eval_logps/chosen": -511.4042663574219,
6
+ "eval_logps/rejected": -623.3074340820312,
7
+ "eval_loss": 0.49832019209861755,
8
+ "eval_rewards/accuracies": 0.76953125,
9
+ "eval_rewards/chosen": -2.488020420074463,
10
+ "eval_rewards/margins": 1.118230938911438,
11
+ "eval_rewards/rejected": -3.6062512397766113,
12
+ "eval_runtime": 42.6828,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 46.857,
15
+ "eval_steps_per_second": 0.75,
16
  "train_loss": 0.535196884905444,
17
  "train_runtime": 3527.4214,
18
  "train_samples": 61135,
config.json CHANGED
@@ -21,6 +21,6 @@
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.38.2",
24
- "use_cache": false,
25
  "vocab_size": 32000
26
  }
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
  "vocab_size": 32000
26
  }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -0.43692123889923096,
4
+ "eval_logits/rejected": 0.023339029401540756,
5
+ "eval_logps/chosen": -511.4042663574219,
6
+ "eval_logps/rejected": -623.3074340820312,
7
+ "eval_loss": 0.49832019209861755,
8
+ "eval_rewards/accuracies": 0.76953125,
9
+ "eval_rewards/chosen": -2.488020420074463,
10
+ "eval_rewards/margins": 1.118230938911438,
11
+ "eval_rewards/rejected": -3.6062512397766113,
12
+ "eval_runtime": 42.6828,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 46.857,
15
+ "eval_steps_per_second": 0.75
16
+ }
runs/Mar11_14-59-16_node-0/events.out.tfevents.1710198135.node-0.16413.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f15a68e2eaadb637b18dc932a4db90560c6ba856003edcf2c46c44666d1381c
3
+ size 828