End of training
Browse files- README.md +16 -10
- all_results.json +13 -0
- config.json +1 -1
- eval_results.json +16 -0
- runs/May21_16-27-14_660111d13776/events.out.tfevents.1716308216.660111d13776.3123315.1 +3 -0
README.md
CHANGED
@@ -2,9 +2,15 @@
|
|
2 |
license: other
|
3 |
base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: zephyr-7b-gemma-kto-2
|
10 |
results: []
|
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# zephyr-7b-gemma-kto-2
|
17 |
|
18 |
-
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Rewards/chosen: 1.
|
22 |
-
- Rewards/rejected: -0.
|
23 |
-
- Rewards/accuracies: 0.
|
24 |
-
- Rewards/margins: 1.
|
25 |
-
- Logps/rejected: -365.
|
26 |
-
- Logps/chosen: -333.
|
27 |
-
- Logits/rejected: 108.
|
28 |
-
- Logits/chosen: 113.
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
2 |
license: other
|
3 |
base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
9 |
+
- trl
|
10 |
+
- dpo
|
11 |
+
- generated_from_trainer
|
12 |
+
datasets:
|
13 |
+
- argilla/dpo-mix-7k
|
14 |
model-index:
|
15 |
- name: zephyr-7b-gemma-kto-2
|
16 |
results: []
|
|
|
21 |
|
22 |
# zephyr-7b-gemma-kto-2
|
23 |
|
24 |
+
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the argilla/dpo-mix-7k dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
+
- Loss: 0.2953
|
27 |
+
- Rewards/chosen: 1.5010
|
28 |
+
- Rewards/rejected: -0.1766
|
29 |
+
- Rewards/accuracies: 0.6875
|
30 |
+
- Rewards/margins: 1.6776
|
31 |
+
- Logps/rejected: -365.6023
|
32 |
+
- Logps/chosen: -333.6483
|
33 |
+
- Logits/rejected: 108.5893
|
34 |
+
- Logits/chosen: 113.8158
|
35 |
|
36 |
## Model description
|
37 |
|
all_results.json
CHANGED
@@ -1,5 +1,18 @@
|
|
1 |
{
|
2 |
"epoch": 1.971563981042654,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 0.0,
|
4 |
"train_loss": 0.2986852119748409,
|
5 |
"train_runtime": 2293.3212,
|
|
|
1 |
{
|
2 |
"epoch": 1.971563981042654,
|
3 |
+
"eval_logits/chosen": 113.8158187866211,
|
4 |
+
"eval_logits/rejected": 108.58926391601562,
|
5 |
+
"eval_logps/chosen": -333.64825439453125,
|
6 |
+
"eval_logps/rejected": -365.6023254394531,
|
7 |
+
"eval_loss": 0.2953260540962219,
|
8 |
+
"eval_rewards/accuracies": 0.6875,
|
9 |
+
"eval_rewards/chosen": 1.500998854637146,
|
10 |
+
"eval_rewards/margins": 1.6775684356689453,
|
11 |
+
"eval_rewards/rejected": -0.17656946182250977,
|
12 |
+
"eval_runtime": 122.5277,
|
13 |
+
"eval_samples": 750,
|
14 |
+
"eval_samples_per_second": 6.121,
|
15 |
+
"eval_steps_per_second": 0.196,
|
16 |
"total_flos": 0.0,
|
17 |
"train_loss": 0.2986852119748409,
|
18 |
"train_runtime": 2293.3212,
|
config.json
CHANGED
@@ -24,6 +24,6 @@
|
|
24 |
"rope_theta": 10000.0,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.40.1",
|
27 |
-
"use_cache":
|
28 |
"vocab_size": 256000
|
29 |
}
|
|
|
24 |
"rope_theta": 10000.0,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.40.1",
|
27 |
+
"use_cache": true,
|
28 |
"vocab_size": 256000
|
29 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.971563981042654,
|
3 |
+
"eval_logits/chosen": 113.8158187866211,
|
4 |
+
"eval_logits/rejected": 108.58926391601562,
|
5 |
+
"eval_logps/chosen": -333.64825439453125,
|
6 |
+
"eval_logps/rejected": -365.6023254394531,
|
7 |
+
"eval_loss": 0.2953260540962219,
|
8 |
+
"eval_rewards/accuracies": 0.6875,
|
9 |
+
"eval_rewards/chosen": 1.500998854637146,
|
10 |
+
"eval_rewards/margins": 1.6775684356689453,
|
11 |
+
"eval_rewards/rejected": -0.17656946182250977,
|
12 |
+
"eval_runtime": 122.5277,
|
13 |
+
"eval_samples": 750,
|
14 |
+
"eval_samples_per_second": 6.121,
|
15 |
+
"eval_steps_per_second": 0.196
|
16 |
+
}
|
runs/May21_16-27-14_660111d13776/events.out.tfevents.1716308216.660111d13776.3123315.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb8a9ceb5deb937dbee4c9e500bda30e2bb75d9596ac686eefb85a338ef075a4
|
3 |
+
size 815
|