You can deploy this model and start earning money today!

Kimory-X/
zephyr-7b-mypo3-full-beta0.01-lr5e-6

Name: zephyr-7b-mypo3-full-beta0.01-lr5e-6
Availability: InStock

generated_from_trainer

alignment-handbook/zephyr-7b-sft-full

finetune

apache-2.0

Views

No views yet

zephyr-7b-mypo3-full-beta0.01-lr5e-6

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3456
Rewards/chosen: -0.0126
Rewards/rejected: -0.3787
Rewards/accuracies: 0.7292
Rewards/margins: 0.3661
Logps/rejected: -280.8124
Logps/chosen: -270.1355
Logits/rejected: -2.0313
Logits/chosen: -2.1873

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 6
gradient_accumulation_steps: 2
total_train_batch_size: 48
total_eval_batch_size: 48
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
1.4246	0.0785	100	1.3713	-0.0918	-0.2291	0.6429	0.1374	-265.8606	-278.0529	-2.0399	-2.1142
1.3778	0.1570	200	1.3963	-0.1227	-0.3412	0.6458	0.2186	-277.0699	-281.1432	-1.8550	-1.9075
1.3731	0.2355	300	1.3832	-0.1196	-0.3109	0.6071	0.1913	-274.0366	-280.8384	-2.2696	-2.3344
1.3787	0.3140	400	1.3771	-0.0537	-0.1868	0.6339	0.1331	-261.6299	-274.2473	-2.3791	-2.4040
1.3626	0.3925	500	1.3659	-0.1322	-0.3895	0.6607	0.2573	-281.8958	-282.0998	-2.2285	-2.3412
1.3697	0.4710	600	1.3760	-0.0638	-0.2353	0.6488	0.1715	-266.4799	-275.2545	-2.1178	-2.2085
1.3594	0.5495	700	1.3808	-0.0361	-0.2292	0.6667	0.1932	-265.8686	-272.4826	-2.6151	-2.6350
1.3471	0.6279	800	1.3639	-0.0608	-0.3743	0.6935	0.3136	-280.3773	-274.9514	-2.2994	-2.3610
1.3454	0.7064	900	1.3620	-0.0486	-0.3824	0.7083	0.3338	-281.1889	-273.7345	-2.1191	-2.2235
1.3307	0.7849	1000	1.3478	-0.0322	-0.3968	0.7083	0.3646	-282.6237	-272.0977	-2.0394	-2.1868
1.3445	0.8634	1100	1.3465	-0.0067	-0.3360	0.7232	0.3293	-276.5467	-269.5432	-2.0826	-2.1949
1.3447	0.9419	1200	1.3456	-0.0126	-0.3787	0.7292	0.3661	-280.8124	-270.1355	-2.0313	-2.1873

Framework versions

Transformers 4.43.1
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.19.1

Kimory-X/zephyr-7b-mypo3-full-beta0.01-lr5e-6

zephyr-7b-mypo3-full-beta0.01-lr5e-6

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Kimory-X/
zephyr-7b-mypo3-full-beta0.01-lr5e-6