learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.3
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.0807	0.3636	50	0.9715	0.5777	0.7072	0.5777	0.4953
0.8958	0.7273	100	0.7766	0.6836	0.6848	0.6836	0.6548
0.8091	1.0873	150	0.7413	0.6959	0.6882	0.6959	0.6763
0.76	1.4509	200	0.7037	0.7177	0.7123	0.7177	0.7075
0.7426	1.8145	250	0.7449	0.6959	0.6974	0.6959	0.6900
0.7371	2.1745	300	0.7117	0.6968	0.6983	0.6968	0.6949
0.7083	2.5382	350	0.6896	0.715	0.7152	0.715	0.7150
0.6937	2.9018	400	0.6967	0.7259	0.7289	0.7259	0.7083
0.6792	3.2618	450	0.6680	0.7341	0.7363	0.7341	0.7238
0.6646	3.6255	500	0.7275	0.69	0.7101	0.69	0.6945
0.6654	3.9891	550	0.6666	0.7309	0.7315	0.7309	0.7212
0.6065	4.3491	600	0.6592	0.7391	0.7362	0.7391	0.7359
0.6112	4.7127	650	0.6468	0.7395	0.7392	0.7395	0.7392
0.592	5.0727	700	0.6657	0.7336	0.7324	0.7336	0.7317
0.5624	5.4364	750	0.6740	0.73	0.7404	0.73	0.7306
0.5333	5.8	800	0.6732	0.7423	0.7397	0.7423	0.7404

abdulrahman-nuzha/intfloat-e5-large-v2-arabic-fp16

intfloat-e5-large-v2-arabic-fp16