---
library_name: transformers
language:
- en
license: apache-2.0
base_model: BEE-spoke-data/tFINE-680m-e32-d16-infinity_instruct-L1
tags:
- generated_from_trainer
model-index:
- name: tFINE-680m-e32-d16-infinity_instruct-L1-infinity-instruct-7m-T2T_en-1024
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# tFINE-680m-e32-d16-infinity_instruct-L1-infinity-instruct-7m-T2T_en-1024

This model is a fine-tuned version of [BEE-spoke-data/tFINE-680m-e32-d16-infinity_instruct-L1](https://huggingface.co/BEE-spoke-data/tFINE-680m-e32-d16-infinity_instruct-L1) on the pszemraj/infinity-instruct-7m-T2T_en dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3139
- Num Input Tokens Seen: 361724696

## 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: 2.5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 17868
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- total_eval_batch_size: 8
- optimizer: Use paged_ademamix_32bit and the args are:
No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 1.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Input Tokens Seen |
|:-------------:|:------:|:----:|:---------------:|:-----------------:|
| 1.4008        | 0.2534 | 1000 | 1.4020          | 91375832          |
| 1.3456        | 0.5068 | 2000 | 1.3669          | 182939052         |
| 1.3437        | 0.7602 | 3000 | 1.3378          | 274855796         |


### Framework versions

- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1