metadata
library_name: transformers
license: apache-2.0
base_model: pszemraj/tFINE-850m-24x24-v0.5-instruct-L1
tags:
- generated_from_trainer
model-index:
- name: tFINE-850m-24x24-v0.5-instruct-L1-infinity-instruct-7m-T2T_en-1024-v2
results: []
tFINE-850m-24x24-v0.5-instruct-L1-infinity-instruct-7m-T2T_en-1024-v2
This model is a fine-tuned version of pszemraj/tFINE-850m-24x24-v0.5-instruct-L1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2595
- Num Input Tokens Seen: 568955808
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: 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|---|---|---|---|---|
| 1.32 | 0.2527 | 2000 | 1.3214 | 189801824 |
| 1.2614 | 0.5053 | 4000 | 1.2815 | 379241088 |
| 1.2367 | 0.7580 | 6000 | 1.2595 | 568955808 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.1