mistral_4o_cot_sky_o1_5_1_epoch_full

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.8626

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.8418	0.3945	100	0.8020
0.8032	0.7890	200	0.7767
0.6517	1.1834	300	0.7796
0.4992	1.5779	400	0.7618
0.4853	1.9724	500	0.7492
0.1987	2.3669	600	0.8611
0.1652	2.7613	700	0.8624

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1