You can deploy this model and start earning money today!

RichardErkhov/
tsavage68_-_Na_M2_100steps_1e7rate_03beta_cSFTDPO-gguf

Name: tsavage68_-_Na_M2_100steps_1e7rate_03beta_cSFTDPO-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Na_M2_100steps_1e7rate_03beta_cSFTDPO - GGUF

Model creator: https://huggingface.co/tsavage68/
Original model: https://huggingface.co/tsavage68/Na_M2_100steps_1e7rate_03beta_cSFTDPO/

Name	Quant method	Size
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q2_K.gguf	Q2_K	2.53GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.IQ3_XS.gguf	IQ3_XS	2.81GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.IQ3_S.gguf	IQ3_S	2.96GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q3_K_S.gguf	Q3_K_S	2.95GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.IQ3_M.gguf	IQ3_M	3.06GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q3_K.gguf	Q3_K	3.28GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q3_K_M.gguf	Q3_K_M	3.28GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q3_K_L.gguf	Q3_K_L	3.56GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.IQ4_XS.gguf	IQ4_XS	3.67GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q4_0.gguf	Q4_0	3.83GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.IQ4_NL.gguf	IQ4_NL	3.87GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q4_K_S.gguf	Q4_K_S	3.86GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q4_K.gguf	Q4_K	4.07GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q4_K_M.gguf	Q4_K_M	4.07GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q4_1.gguf	Q4_1	4.24GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q5_0.gguf	Q5_0	4.65GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q5_K_S.gguf	Q5_K_S	4.65GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q5_K.gguf	Q5_K	4.78GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q5_K_M.gguf	Q5_K_M	4.78GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q5_1.gguf	Q5_1	5.07GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q6_K.gguf	Q6_K	5.53GB
Na_M2_100steps_1e7rate_03beta_cSFTDPO.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: apache-2.0 base_model: tsavage68/Na_M2_1000steps_1e7_SFT tags:

trl
dpo
generated_from_trainer model-index:
name: Na_M2_100steps_1e7rate_03beta_cSFTDPO results: []

Na_M2_100steps_1e7rate_03beta_cSFTDPO

This model is a fine-tuned version of tsavage68/Na_M2_1000steps_1e7_SFT on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0000
Rewards/chosen: 2.8383
Rewards/rejected: -9.2541
Rewards/accuracies: 1.0
Rewards/margins: 12.0924
Logps/rejected: -110.7703
Logps/chosen: -38.6713
Logits/rejected: -2.5103
Logits/chosen: -2.5250

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: 1e-07
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.0004	0.2667	50	0.0000	2.3360	-8.0685	1.0	10.4045	-106.8185	-40.3458	-2.5169	-2.5309
0.0	0.5333	100	0.0000	2.8383	-9.2541	1.0	12.0924	-110.7703	-38.6713	-2.5103	-2.5250

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

RichardErkhov/tsavage68_-_Na_M2_100steps_1e7rate_03beta_cSFTDPO-gguf

Original model description:

Na_M2_100steps_1e7rate_03beta_cSFTDPO

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
tsavage68_-_Na_M2_100steps_1e7rate_03beta_cSFTDPO-gguf