Hugging Face's logo

dball
/
zephyr-tiny-dpo-qlora

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
Generated from Trainer
trl
dpo
Model card Files
xet
Metrics Community
1
dball commited on
Commit
eb0e803
路
verified 路
1 Parent(s): 26da6c2

Model save

Browse files
Files changed (8) hide show
  1. README.md +0 -0
  2. adapter_model.safetensors +1 -1
  3. all_results.json +21 -0
  4. eval_results.json +16 -0
  5. runs/Feb13_18-35-35_5be93f7a41ea/events.out.tfevents.1707849728.5be93f7a41ea.4072.0 +2 -2
  6. runs/Feb13_18-35-35_5be93f7a41ea/events.out.tfevents.1708021634.5be93f7a41ea.4072.1 +3 -0
  7. train_results.json +8 -0
  8. trainer_state.json +0 -0
README.md ADDED
The diff for this file is too large to render. See raw diff
 
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2740700c073c4bf4a67ab3f7acfa4ced715fd96a0d0d3d2114ade663f134d8a8
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe3fdc7e6a925b7060f55fca07f6e0117aecdaeb5f6a1ba6d176ca7dc0b1848
3
  size 50503544
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -2.2347500324249268,
4
+ "eval_logits/rejected": -2.242765188217163,
5
+ "eval_logps/chosen": -481.0046691894531,
6
+ "eval_logps/rejected": -493.4847717285156,
7
+ "eval_loss": 0.5999384522438049,
8
+ "eval_rewards/accuracies": 0.6735000014305115,
9
+ "eval_rewards/chosen": -1.482552409172058,
10
+ "eval_rewards/margins": 0.4411955773830414,
11
+ "eval_rewards/rejected": -1.9237478971481323,
12
+ "eval_runtime": 197.0628,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 10.149,
15
+ "eval_steps_per_second": 5.075,
16
+ "train_loss": 0.6145847465156994,
17
+ "train_runtime": 171708.6447,
18
+ "train_samples": 61135,
19
+ "train_samples_per_second": 0.356,
20
+ "train_steps_per_second": 0.044
21
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -2.2347500324249268,
4
+ "eval_logits/rejected": -2.242765188217163,
5
+ "eval_logps/chosen": -481.0046691894531,
6
+ "eval_logps/rejected": -493.4847717285156,
7
+ "eval_loss": 0.5999384522438049,
8
+ "eval_rewards/accuracies": 0.6735000014305115,
9
+ "eval_rewards/chosen": -1.482552409172058,
10
+ "eval_rewards/margins": 0.4411955773830414,
11
+ "eval_rewards/rejected": -1.9237478971481323,
12
+ "eval_runtime": 197.0628,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 10.149,
15
+ "eval_steps_per_second": 5.075
16
+ }
runs/Feb13_18-35-35_5be93f7a41ea/events.out.tfevents.1707849728.5be93f7a41ea.4072.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9714527b0d662d2f6a8e402bad1af5010b9824b5fe5ff5a4a6cdd9930f87b48
3
- size 1049183
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:600f25d563b482fdb962b845c106bb37f7cb7d8aba5b29ec7a5d4cd1d2b1c8aa
3
+ size 1055033
runs/Feb13_18-35-35_5be93f7a41ea/events.out.tfevents.1708021634.5be93f7a41ea.4072.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaee89a68d21b33992a1b2a0c22d6fffd7c026d2a8834bc472d49a7cd8c6b0b1
3
+ size 828
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6145847465156994,
4
+ "train_runtime": 171708.6447,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 0.356,
7
+ "train_steps_per_second": 0.044
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff