---
license: gemma
base_model: google/gemma-2-27b
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: collapse_gemma-2-27b_hs2_accumulate_iter1_sftsd2
  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. -->

# collapse_gemma-2-27b_hs2_accumulate_iter1_sftsd2

This model is a fine-tuned version of [google/gemma-2-27b](https://huggingface.co/google/gemma-2-27b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9056
- Num Input Tokens Seen: 5236236

## 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: 8e-06
- train_batch_size: 4
- eval_batch_size: 16
- seed: 2
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Input Tokens Seen |
|:-------------:|:------:|:----:|:---------------:|:-----------------:|
| No log        | 0      | 0    | 1.1282          | 0                 |
| 0.9652        | 0.0511 | 5    | 0.9817          | 270332            |
| 0.9707        | 0.1021 | 10   | 0.9530          | 541500            |
| 0.9592        | 0.1532 | 15   | 0.9413          | 812584            |
| 0.9301        | 0.2043 | 20   | 0.9341          | 1083956           |
| 0.9111        | 0.2553 | 25   | 0.9296          | 1356232           |
| 0.9056        | 0.3064 | 30   | 0.9263          | 1618536           |
| 0.9533        | 0.3575 | 35   | 0.9235          | 1882576           |
| 0.926         | 0.4086 | 40   | 0.9205          | 2154872           |
| 0.8827        | 0.4596 | 45   | 0.9183          | 2423272           |
| 0.8874        | 0.5107 | 50   | 0.9162          | 2695312           |
| 0.9546        | 0.5618 | 55   | 0.9150          | 2965956           |
| 0.8911        | 0.6128 | 60   | 0.9133          | 3236124           |
| 0.8428        | 0.6639 | 65   | 0.9119          | 3504696           |
| 0.9158        | 0.7150 | 70   | 0.9108          | 3779560           |
| 0.9392        | 0.7660 | 75   | 0.9097          | 4047404           |
| 0.9049        | 0.8171 | 80   | 0.9091          | 4319468           |
| 0.8697        | 0.8682 | 85   | 0.9082          | 4590728           |
| 0.9536        | 0.9192 | 90   | 0.9067          | 4860344           |
| 0.9586        | 0.9703 | 95   | 0.9057          | 5128848           |


### Framework versions

- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1