Hugging Face's logo

nnheui
/
zephyr-7b-kto-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
nnheui commited on
Commit
d8e1435
•
1 Parent(s): 8056d21

Model save

Browse files
Files changed (5) hide show
  1. adapter_model.safetensors +1 -1
  2. all_results.json +4 -4
  3. runs/Apr18_13-47-18_104-171-203-159/events.out.tfevents.1713470028.104-171-203-159.3738534.0 +2 -2
  4. train_results.json +4 -4
  5. trainer_state.json +0 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd31e771370ffa02b7c3d72ff7f745eab2cf7a8daadc19ce61fea03a473d5594
3
  size 671150064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa2435a2bb2f24cc8f05ef2a4d674543331948e8b65cb5dcf070b68f6c97117
3
  size 671150064
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.5000961124897003,
4
- "train_runtime": 87.0205,
5
- "train_samples": 61,
6
- "train_samples_per_second": 0.701,
7
  "train_steps_per_second": 0.023
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.4411179514611579,
4
+ "train_runtime": 83930.2059,
5
+ "train_samples": 61134,
6
+ "train_samples_per_second": 0.728,
7
  "train_steps_per_second": 0.023
8
  }
runs/Apr18_13-47-18_104-171-203-159/events.out.tfevents.1713470028.104-171-203-159.3738534.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1831f3f73a53d3fd77d968d33cb637599831b9d4a19a596a137f968836ed8a48
3
- size 136631
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a29799a39bec92c0c77eaf0c1e7acab45f5f9d19ca7e0daadda264bf967f20
3
+ size 137673
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.5000961124897003,
4
- "train_runtime": 87.0205,
5
- "train_samples": 61,
6
- "train_samples_per_second": 0.701,
7
  "train_steps_per_second": 0.023
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.4411179514611579,
4
+ "train_runtime": 83930.2059,
5
+ "train_samples": 61134,
6
+ "train_samples_per_second": 0.728,
7
  "train_steps_per_second": 0.023
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff