You can deploy this model and start earning money today!

RichardErkhov/
tsavage68_-_IE_L3_150steps_1e7rate_01beta_cSFTDPO-gguf

Name: tsavage68_-_IE_L3_150steps_1e7rate_01beta_cSFTDPO-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

IE_L3_150steps_1e7rate_01beta_cSFTDPO - GGUF

Model creator: https://huggingface.co/tsavage68/
Original model: https://huggingface.co/tsavage68/IE_L3_150steps_1e7rate_01beta_cSFTDPO/

Name	Quant method	Size
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q2_K.gguf	Q2_K	2.96GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.IQ3_XS.gguf	IQ3_XS	3.28GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.IQ3_S.gguf	IQ3_S	3.43GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q3_K_S.gguf	Q3_K_S	3.41GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.IQ3_M.gguf	IQ3_M	3.52GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q3_K.gguf	Q3_K	3.74GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q3_K_M.gguf	Q3_K_M	3.74GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q3_K_L.gguf	Q3_K_L	4.03GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.IQ4_XS.gguf	IQ4_XS	4.18GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q4_0.gguf	Q4_0	4.34GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.IQ4_NL.gguf	IQ4_NL	4.38GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q4_K_S.gguf	Q4_K_S	4.37GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q4_K.gguf	Q4_K	4.58GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q4_K_M.gguf	Q4_K_M	4.58GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q4_1.gguf	Q4_1	4.78GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q5_0.gguf	Q5_0	5.21GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q5_K_S.gguf	Q5_K_S	5.21GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q5_K.gguf	Q5_K	5.34GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q5_K_M.gguf	Q5_K_M	5.34GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q5_1.gguf	Q5_1	5.65GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q6_K.gguf	Q6_K	6.14GB
IE_L3_150steps_1e7rate_01beta_cSFTDPO.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers license: llama3 base_model: tsavage68/IE_L3_1000steps_1e6rate_SFT tags:

trl
dpo
generated_from_trainer model-index:
name: IE_L3_150steps_1e7rate_01beta_cSFTDPO results: []

IE_L3_150steps_1e7rate_01beta_cSFTDPO

This model is a fine-tuned version of tsavage68/IE_L3_1000steps_1e6rate_SFT on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2049
Rewards/chosen: -0.3084
Rewards/rejected: -2.8821
Rewards/accuracies: 0.7400
Rewards/margins: 2.5737
Logps/rejected: -104.4487
Logps/chosen: -85.8823
Logits/rejected: -0.7993
Logits/chosen: -0.7183

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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6292	0.4	50	0.5972	-0.0178	-0.2247	0.7400	0.2070	-77.8745	-82.9754	-0.7952	-0.7369
0.2432	0.8	100	0.2531	-0.1984	-1.9084	0.7400	1.7099	-94.7109	-84.7823	-0.7935	-0.7222
0.1679	1.2	150	0.2049	-0.3084	-2.8821	0.7400	2.5737	-104.4487	-85.8823	-0.7993	-0.7183

Framework versions

Transformers 4.44.2
Pytorch 2.0.0+cu117
Datasets 3.0.0
Tokenizers 0.19.1

RichardErkhov/tsavage68_-_IE_L3_150steps_1e7rate_01beta_cSFTDPO-gguf

Original model description:

IE_L3_150steps_1e7rate_01beta_cSFTDPO

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
tsavage68_-_IE_L3_150steps_1e7rate_01beta_cSFTDPO-gguf