metadata

license: other
base_model: boun-tabi-LMG/TURNA
tags:
  - generated_from_trainer
metrics:
  - rouge
  - bleu
model-index:
  - name: TURNA_TSATweets_cond_gen_no_instruction
    results: []

TURNA_TSATweets_cond_gen_no_instruction

This model is a fine-tuned version of boun-tabi-LMG/TURNA on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0704
Rouge1: 0.705
Rouge2: 0.095
Rougel: 0.705
Rougelsum: 0.705
Bleu: 0.0
Precisions: [0.705, 0.0, 0.0, 0.0]
Brevity Penalty: 1.0
Length Ratio: 1.0
Translation Length: 200
Reference Length: 200
Meteor: 0.3525
Score: 29.5
Num Edits: 59
Ref Length: 200.0

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Precisions	Brevity Penalty	Length Ratio	Translation Length	Reference Length	Meteor	Score	Num Edits	Ref Length
No log	0.5	82	0.0794	0.6569	0.0586	0.6552	0.6569	[0.656896551724138, 0.0, 0.0, 0.0]	1.0	1.0	580	580	0.3284	34.3103	199	580.0
1.7625	1.0	164	0.0707	0.6897	0.0638	0.6897	0.6879	[0.6896551724137931, 0.0, 0.0, 0.0]	1.0	1.0	580	580	0.3448	31.0345	180	580.0
1.7625	1.5	246	0.0778	0.7017	0.0284	0.7017	0.7	[0.7017241379310345, 0.0, 0.0, 0.0]	1.0	1.0	580	580	0.3509	29.8276	173	580.0
0.0921	2.0	328	0.0724	0.7259	0.0362	0.7241	0.7224	[0.7241379310344828, 0.0, 0.0, 0.0]	1.0	1.0	580	580	0.3621	27.5862	160	580.0
0.0921	2.5	410	0.0948	0.6845	0.1224	0.6828	0.6828	[0.6827586206896552, 0.0, 0.0, 0.0]	1.0	1.0	580	580	0.3414	31.7241	184	580.0

Framework versions

Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1