README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: es_fi_all_quy
    results: []

es_fi_all_quy

This model is a fine-tuned version of nouman-10/es_fi_all_quy on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4779
• Bleu: 1.6745
• Chrf: 32.4462
• Gen Len: 42.4789

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Chrf	Gen Len
0.2977	0.09	1000	0.4895	1.4944	31.8832	41.2596
0.2977	0.17	2000	0.4870	1.3779	31.419	44.5825
0.2851	0.26	3000	0.4849	1.1958	30.8243	48.3773
0.2829	0.34	4000	0.4828	1.7102	31.6821	43.6841
0.2881	0.43	5000	0.4822	1.8438	32.6924	39.0855
0.2847	0.51	6000	0.4796	1.2714	31.2343	49.8511
0.2812	0.6	7000	0.4799	1.7161	32.2005	46.3149
0.2753	0.68	8000	0.4790	1.2392	32.7687	40.1841
0.282	0.77	9000	0.4804	1.3175	32.1637	41.4537
0.2743	0.85	10000	0.4784	1.4782	32.5727	42.0936
0.2719	0.94	11000	0.4781	1.5137	31.9548	44.4477
0.2668	1.02	12000	0.4797	1.1151	31.5602	43.9336
0.2638	1.11	13000	0.4779	1.6745	32.4462	42.4789

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu117
• Datasets 2.11.0
• Tokenizers 0.13.3