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
1.0668	0.3922	50	0.9147	0.5648	0.6855	0.5648	0.4637
0.6872	0.7843	100	0.4339	0.8384	0.8374	0.8384	0.8369
0.3677	1.1725	150	0.3228	0.8802	0.8803	0.8802	0.8800
0.2966	1.5647	200	0.3345	0.8816	0.8827	0.8816	0.8798
0.3005	1.9569	250	0.3261	0.8762	0.8806	0.8762	0.8728
0.2175	2.3451	300	0.2999	0.8919	0.8922	0.8919	0.8905
0.2136	2.7373	350	0.3109	0.8846	0.8856	0.8846	0.8850
0.1841	3.1255	400	0.3765	0.8821	0.8824	0.8821	0.8818
0.1327	3.5176	450	0.3523	0.8900	0.8900	0.8900	0.8900

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

intfloat-e5-large-v2-english-fp16