tFINE-850m-24x24-instruct-L2
This model is a fine-tuned version of pszemraj/tFINE-850m-24x24-v0.5-instruct-L1 on the pszemraj/infinity-instruct-7m-T2T_en dataset (config deduped-L2).
It achieves the following results on the evaluation set:
- Loss: 1.2542
- Num Input Tokens Seen: 750938410
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3.5e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 17868
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.PAGED_ADEMAMIX and the args are: No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1.0
- Downloads last month
- 14
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for pszemraj/tFINE-850m-24x24-instruct-L2
Base model
pszemraj/tFINE-850m-24x24-v0.4-flan_aug