EllieS commited on
Commit
e1de556
1 Parent(s): 1b50c42

Model save

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ base_model: alignment-handbook/zephyr-7b-sft-full
9
+ model-index:
10
+ - name: zephyr-7b-dpo-lora-pubmedqa-selfgen-ultrafeedback2
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-dpo-lora-pubmedqa-selfgen-ultrafeedback2
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 the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.5869
22
+ - Rewards/chosen: -0.2480
23
+ - Rewards/rejected: -0.5522
24
+ - Rewards/accuracies: 0.7090
25
+ - Rewards/margins: 0.3042
26
+ - Logps/rejected: -306.5199
27
+ - Logps/chosen: -309.5233
28
+ - Logits/rejected: -2.5197
29
+ - Logits/chosen: -2.5501
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 5e-06
49
+ - train_batch_size: 2
50
+ - eval_batch_size: 2
51
+ - seed: 42
52
+ - distributed_type: multi-GPU
53
+ - num_devices: 2
54
+ - gradient_accumulation_steps: 2
55
+ - total_train_batch_size: 8
56
+ - total_eval_batch_size: 4
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: cosine
59
+ - lr_scheduler_warmup_ratio: 0.1
60
+ - num_epochs: 1
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
66
+ | 0.5526 | 0.39 | 3000 | 0.6013 | -0.1508 | -0.4054 | 0.7040 | 0.2546 | -291.8378 | -299.8007 | -2.5651 | -2.5923 |
67
+ | 0.5814 | 0.79 | 6000 | 0.5867 | -0.2418 | -0.5459 | 0.7080 | 0.3040 | -305.8824 | -308.9029 | -2.5202 | -2.5505 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - PEFT 0.7.1
73
+ - Transformers 4.36.2
74
+ - Pytorch 2.1.2+cu121
75
+ - Datasets 2.14.6
76
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cdb4a3b4efafaa9eebd5d55f14cbdd1d1fb0b2c60475912d0e8db5ca2f67f38
3
  size 83946192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bd684de86a24ed61026717cff9156da58f01d45190ad195da489d08dd7b3ab5
3
  size 83946192
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -2.550062417984009,
4
+ "eval_logits/rejected": -2.519716262817383,
5
+ "eval_logps/chosen": -309.5232849121094,
6
+ "eval_logps/rejected": -306.5199279785156,
7
+ "eval_loss": 0.5869344472885132,
8
+ "eval_rewards/accuracies": 0.7089999914169312,
9
+ "eval_rewards/chosen": -0.2480395883321762,
10
+ "eval_rewards/margins": 0.3042061924934387,
11
+ "eval_rewards/rejected": -0.5522457957267761,
12
+ "eval_runtime": 469.9661,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 4.256,
15
+ "eval_steps_per_second": 1.064,
16
+ "train_loss": 0.6071469678956156,
17
+ "train_runtime": 31823.939,
18
+ "train_samples": 61135,
19
+ "train_samples_per_second": 1.921,
20
+ "train_steps_per_second": 0.24
21
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -2.550062417984009,
4
+ "eval_logits/rejected": -2.519716262817383,
5
+ "eval_logps/chosen": -309.5232849121094,
6
+ "eval_logps/rejected": -306.5199279785156,
7
+ "eval_loss": 0.5869344472885132,
8
+ "eval_rewards/accuracies": 0.7089999914169312,
9
+ "eval_rewards/chosen": -0.2480395883321762,
10
+ "eval_rewards/margins": 0.3042061924934387,
11
+ "eval_rewards/rejected": -0.5522457957267761,
12
+ "eval_runtime": 469.9661,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 4.256,
15
+ "eval_steps_per_second": 1.064
16
+ }
runs/Feb22_06-18-14_586cb8b6da8c/events.out.tfevents.1708582835.586cb8b6da8c.10523.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:875ec6ba8a74774fb24a542d409498b54a736dd16d3a9d3e2f61d871d49181fd
3
- size 450446
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab03329ec1ec12141df5c2cd58513ea26296ec6f5046bebf450040d74babae57
3
+ size 491376
runs/Feb22_06-18-14_586cb8b6da8c/events.out.tfevents.1708615128.586cb8b6da8c.10523.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9587ea69d757dc8f60854cbbb4844ef61ade4e367344e7e514caef55adf0c46a
3
+ size 828
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6071469678956156,
4
+ "train_runtime": 31823.939,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 1.921,
7
+ "train_steps_per_second": 0.24
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff