Hugging Face's logo

NicholasCorrado
/
zephyr-7b-uf-rlced-conifer-1e2e-group-dpo-2e

Text Generation
Transformers
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
NicholasCorrado commited on
Commit
7b74dfa
•
1 Parent(s): 694c223

Model save

Browse files
Files changed (4) hide show
  1. README.md +100 -0
  2. all_results.json +9 -0
  3. generation_config.json +6 -0
  4. train_results.json +9 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: alignment-handbook/zephyr-7b-sft-full
5
+ tags:
6
+ - trl
7
+ - dpo
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: zephyr-7b-uf-rlced-conifer-1e2e-group-dpo-2e
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # zephyr-7b-uf-rlced-conifer-1e2e-group-dpo-2e
18
+
19
+ 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.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2626
22
+ - Rewards/chosen: -2.1843
23
+ - Rewards/rejected: -5.4288
24
+ - Rewards/accuracies: 0.8684
25
+ - Rewards/margins: 3.2445
26
+ - Logps/rejected: -946.6157
27
+ - Logps/chosen: -610.9032
28
+ - Logits/rejected: 1.2318
29
+ - Logits/chosen: -0.7806
30
+ - Excess Loss: 0.0374
31
+ - Alpha 0 Uf: 0.8470
32
+ - Alpha 1 Rlced Conifer: 0.1530
33
+ - Rewards/chosen 1 Rlced Conifer: -2.2281
34
+ - Rewards/rejected 1 Rlced Conifer: -6.0246
35
+ - Rewards/accuracies 1 Rlced Conifer: 0.8987
36
+ - Rewards/margins 1 Rlced Conifer: 3.7965
37
+ - Logps/rejected 1 Rlced Conifer: -1049.9939
38
+ - Logps/chosen 1 Rlced Conifer: -646.3860
39
+ - Logits/rejected 1 Rlced Conifer: 1.1158
40
+ - Logits/chosen 1 Rlced Conifer: -0.9982
41
+ - Task Loss 1 Rlced Conifer: 0.2102
42
+ - Task Excess Loss 1 Rlced Conifer: 0.0475
43
+ - Rewards/chosen 0 Uf: -1.9978
44
+ - Rewards/rejected 0 Uf: -3.3091
45
+ - Rewards/accuracies 0 Uf: 0.7603
46
+ - Rewards/margins 0 Uf: 1.3113
47
+ - Logps/rejected 0 Uf: -572.5212
48
+ - Logps/chosen 0 Uf: -489.0419
49
+ - Logits/rejected 0 Uf: 1.8243
50
+ - Logits/chosen 0 Uf: -0.1004
51
+ - Task Loss 0 Uf: 0.4944
52
+ - Task Excess Loss 0 Uf: 0.0469
53
+
54
+ ## Model description
55
+
56
+ More information needed
57
+
58
+ ## Intended uses & limitations
59
+
60
+ More information needed
61
+
62
+ ## Training and evaluation data
63
+
64
+ More information needed
65
+
66
+ ## Training procedure
67
+
68
+ ### Training hyperparameters
69
+
70
+ The following hyperparameters were used during training:
71
+ - learning_rate: 5e-07
72
+ - train_batch_size: 8
73
+ - eval_batch_size: 8
74
+ - seed: 42
75
+ - distributed_type: multi-GPU
76
+ - num_devices: 8
77
+ - gradient_accumulation_steps: 4
78
+ - total_train_batch_size: 256
79
+ - total_eval_batch_size: 64
80
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
81
+ - lr_scheduler_type: cosine
82
+ - lr_scheduler_warmup_ratio: 0.1
83
+ - num_epochs: 2
84
+
85
+ ### Training results
86
+
87
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Excess Loss | Alpha 0 Uf | Alpha 1 Rlced Conifer | Rewards/chosen 1 Rlced Conifer | Rewards/rejected 1 Rlced Conifer | Rewards/accuracies 1 Rlced Conifer | Rewards/margins 1 Rlced Conifer | Logps/rejected 1 Rlced Conifer | Logps/chosen 1 Rlced Conifer | Logits/rejected 1 Rlced Conifer | Logits/chosen 1 Rlced Conifer | Task Loss 1 Rlced Conifer | Task Excess Loss 1 Rlced Conifer | Rewards/chosen 0 Uf | Rewards/rejected 0 Uf | Rewards/accuracies 0 Uf | Rewards/margins 0 Uf | Logps/rejected 0 Uf | Logps/chosen 0 Uf | Logits/rejected 0 Uf | Logits/chosen 0 Uf | Task Loss 0 Uf | Task Excess Loss 0 Uf |
88
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:-----------:|:----------:|:---------------------:|:------------------------------:|:--------------------------------:|:----------------------------------:|:-------------------------------:|:------------------------------:|:----------------------------:|:-------------------------------:|:-----------------------------:|:-------------------------:|:--------------------------------:|:-------------------:|:---------------------:|:-----------------------:|:--------------------:|:-------------------:|:-----------------:|:--------------------:|:------------------:|:--------------:|:---------------------:|
89
+ | 0.1953 | 0.4997 | 360 | 0.3535 | -1.5938 | -3.1996 | 0.8402 | 1.6058 | -723.6984 | -551.8521 | 0.1112 | -0.7863 | 0.1136 | 0.9694 | 0.0306 | -1.5989 | -3.4179 | 0.8677 | 1.8190 | -789.3262 | -583.4747 | -0.1145 | -0.9516 | 0.3087 | 0.1414 | -1.5520 | -2.3972 | 0.7448 | 0.8452 | -481.3242 | -444.4588 | 1.0137 | -0.2527 | 0.5289 | 0.0768 |
90
+ | 0.1537 | 0.9993 | 720 | 0.3329 | -1.4289 | -3.2979 | 0.8609 | 1.8690 | -733.5210 | -535.3586 | 0.6830 | -0.5276 | 0.0943 | 0.9852 | 0.0148 | -1.4038 | -3.4887 | 0.8869 | 2.0849 | -796.4048 | -563.9600 | 0.3914 | -0.7372 | 0.2955 | 0.1278 | -1.4972 | -2.5982 | 0.7618 | 1.1009 | -501.4233 | -438.9818 | 1.8477 | 0.1514 | 0.4804 | 0.0530 |
91
+ | 0.0667 | 1.4990 | 1080 | 0.2667 | -2.1402 | -5.1839 | 0.8656 | 3.0437 | -922.1221 | -606.4852 | 1.0002 | -0.7884 | 0.0408 | 0.8954 | 0.1046 | -2.1729 | -5.7323 | 0.8964 | 3.5594 | -1020.7665 | -640.8754 | 0.8903 | -0.9784 | 0.2150 | 0.0521 | -1.9916 | -3.2293 | 0.7574 | 1.2377 | -564.5363 | -488.4239 | 1.5582 | -0.1961 | 0.4940 | 0.0466 |
92
+ | 0.06 | 1.9986 | 1440 | 0.2626 | -2.1843 | -5.4288 | 0.8684 | 3.2445 | -946.6157 | -610.9032 | 1.2318 | -0.7806 | 0.0374 | 0.8470 | 0.1530 | -2.2281 | -6.0246 | 0.8987 | 3.7965 | -1049.9939 | -646.3860 | 1.1158 | -0.9982 | 0.2102 | 0.0475 | -1.9978 | -3.3091 | 0.7603 | 1.3113 | -572.5212 | -489.0419 | 1.8243 | -0.1004 | 0.4944 | 0.0469 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.44.1
98
+ - Pytorch 2.1.2+cu121
99
+ - Datasets 2.21.0
100
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.9986120749479528,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.15370953861210082,
5
+ "train_runtime": 41916.6173,
6
+ "train_samples": 184443,
7
+ "train_samples_per_second": 8.8,
8
+ "train_steps_per_second": 0.034
9
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.44.1"
6
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.9986120749479528,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.15370953861210082,
5
+ "train_runtime": 41916.6173,
6
+ "train_samples": 184443,
7
+ "train_samples_per_second": 8.8,
8
+ "train_steps_per_second": 0.034
9
+ }