metadata

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
  - GaetanMichelet/chat-60_ft_task-3
  - GaetanMichelet/chat-120_ft_task-3
  - GaetanMichelet/chat-180_ft_task-3
library_name: peft
license: llama3.1
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: Llama-31-8B_task-3_180-samples_config-3
    results: []

Llama-31-8B_task-3_180-samples_config-3

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the GaetanMichelet/chat-60_ft_task-3, the GaetanMichelet/chat-120_ft_task-3 and the GaetanMichelet/chat-180_ft_task-3 datasets. It achieves the following results on the evaluation set:

Loss: 0.4813

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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 150

Training results

Training Loss	Epoch	Step	Validation Loss
2.3708	1.0	17	2.4982
2.4065	2.0	34	2.4397
2.3549	3.0	51	2.3147
2.0578	4.0	68	2.0850
1.8089	5.0	85	1.7080
1.3018	6.0	102	1.2347
1.0212	7.0	119	0.8016
0.4899	8.0	136	0.6475
0.6106	9.0	153	0.5890
0.5388	10.0	170	0.5729
0.7245	11.0	187	0.5585
0.3568	12.0	204	0.5533
0.4165	13.0	221	0.5353
0.6226	14.0	238	0.5420
0.3284	15.0	255	0.5026
0.4813	16.0	272	0.5214
0.3015	17.0	289	0.5116
0.3513	18.0	306	0.5071
0.3638	19.0	323	0.5486
0.5246	20.0	340	0.4813
0.4751	21.0	357	0.5369
0.2074	22.0	374	0.5177
0.2513	23.0	391	0.5109
0.3019	24.0	408	0.5100
0.2039	25.0	425	0.5429
0.228	26.0	442	0.5161
0.2127	27.0	459	0.5206

Framework versions

PEFT 0.12.0
Transformers 4.44.0
Pytorch 2.1.2+cu121
Datasets 2.20.0
Tokenizers 0.19.1