End of training
Browse files
README.md
CHANGED
@@ -2,9 +2,15 @@
|
|
2 |
license: gemma
|
3 |
base_model: tanliboy/zephyr-gemma-2-9b-sft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: zephyr-gemma-2-9b-dpo-2
|
10 |
results: []
|
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tanliboy/huggingface/runs/igf2ndcz)
|
17 |
# zephyr-gemma-2-9b-dpo-2
|
18 |
|
19 |
-
This model is a fine-tuned version of [tanliboy/zephyr-gemma-2-9b-sft](https://huggingface.co/tanliboy/zephyr-gemma-2-9b-sft) on
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Rewards/chosen: -0.
|
23 |
-
- Rewards/rejected: -1.
|
24 |
-
- Rewards/accuracies: 0.
|
25 |
-
- Rewards/margins: 0.
|
26 |
-
- Logps/rejected: -407.
|
27 |
-
- Logps/chosen: -
|
28 |
-
- Logits/rejected: -14.
|
29 |
-
- Logits/chosen: -14.
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
2 |
license: gemma
|
3 |
base_model: tanliboy/zephyr-gemma-2-9b-sft
|
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-gemma-2-9b-dpo-2
|
16 |
results: []
|
|
|
22 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tanliboy/huggingface/runs/igf2ndcz)
|
23 |
# zephyr-gemma-2-9b-dpo-2
|
24 |
|
25 |
+
This model is a fine-tuned version of [tanliboy/zephyr-gemma-2-9b-sft](https://huggingface.co/tanliboy/zephyr-gemma-2-9b-sft) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
26 |
It achieves the following results on the evaluation set:
|
27 |
+
- Loss: 0.5277
|
28 |
+
- Rewards/chosen: -0.6084
|
29 |
+
- Rewards/rejected: -1.2304
|
30 |
+
- Rewards/accuracies: 0.6880
|
31 |
+
- Rewards/margins: 0.6220
|
32 |
+
- Logps/rejected: -407.4499
|
33 |
+
- Logps/chosen: -375.1572
|
34 |
+
- Logits/rejected: -14.2928
|
35 |
+
- Logits/chosen: -14.1056
|
36 |
|
37 |
## Model description
|
38 |
|
all_results.json
CHANGED
@@ -1,5 +1,18 @@
|
|
1 |
{
|
2 |
"epoch": 0.9997382884061764,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 0.0,
|
4 |
"train_loss": 0.560625178402007,
|
5 |
"train_runtime": 12630.0326,
|
|
|
1 |
{
|
2 |
"epoch": 0.9997382884061764,
|
3 |
+
"eval_logits/chosen": -14.105589866638184,
|
4 |
+
"eval_logits/rejected": -14.292818069458008,
|
5 |
+
"eval_logps/chosen": -375.1571960449219,
|
6 |
+
"eval_logps/rejected": -407.44989013671875,
|
7 |
+
"eval_loss": 0.5276930332183838,
|
8 |
+
"eval_rewards/accuracies": 0.6880000233650208,
|
9 |
+
"eval_rewards/chosen": -0.6083627939224243,
|
10 |
+
"eval_rewards/margins": 0.6220458149909973,
|
11 |
+
"eval_rewards/rejected": -1.2304086685180664,
|
12 |
+
"eval_runtime": 148.4787,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 13.47,
|
15 |
+
"eval_steps_per_second": 0.842,
|
16 |
"total_flos": 0.0,
|
17 |
"train_loss": 0.560625178402007,
|
18 |
"train_runtime": 12630.0326,
|
config.json
CHANGED
@@ -29,6 +29,6 @@
|
|
29 |
"sliding_window_size": 4096,
|
30 |
"torch_dtype": "bfloat16",
|
31 |
"transformers_version": "4.43.1",
|
32 |
-
"use_cache":
|
33 |
"vocab_size": 256000
|
34 |
}
|
|
|
29 |
"sliding_window_size": 4096,
|
30 |
"torch_dtype": "bfloat16",
|
31 |
"transformers_version": "4.43.1",
|
32 |
+
"use_cache": true,
|
33 |
"vocab_size": 256000
|
34 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9997382884061764,
|
3 |
+
"eval_logits/chosen": -14.105589866638184,
|
4 |
+
"eval_logits/rejected": -14.292818069458008,
|
5 |
+
"eval_logps/chosen": -375.1571960449219,
|
6 |
+
"eval_logps/rejected": -407.44989013671875,
|
7 |
+
"eval_loss": 0.5276930332183838,
|
8 |
+
"eval_rewards/accuracies": 0.6880000233650208,
|
9 |
+
"eval_rewards/chosen": -0.6083627939224243,
|
10 |
+
"eval_rewards/margins": 0.6220458149909973,
|
11 |
+
"eval_rewards/rejected": -1.2304086685180664,
|
12 |
+
"eval_runtime": 148.4787,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 13.47,
|
15 |
+
"eval_steps_per_second": 0.842
|
16 |
+
}
|
runs/Jul24_07-13-12_action-graph-trainer/events.out.tfevents.1721818858.action-graph-trainer.576983.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fdc71b8eef9caecadac21ec5659a7e65acb893053a8eacdcab16cdf09c06837
|
3 |
+
size 828
|