| { | |
| "best_metric": 2.3307483196258545, | |
| "best_model_checkpoint": "add_BERT_no_pretrain_stsb/checkpoint-270", | |
| "epoch": 11.0, | |
| "global_step": 495, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 2.4937, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.03484396955490256, | |
| "eval_loss": 2.637270927429199, | |
| "eval_pearson": 0.041015241553137224, | |
| "eval_runtime": 2.7912, | |
| "eval_samples_per_second": 537.4, | |
| "eval_spearmanr": 0.028672697556667882, | |
| "eval_steps_per_second": 4.299, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 2.22, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.06629060639069365, | |
| "eval_loss": 2.4288177490234375, | |
| "eval_pearson": 0.07402195261812716, | |
| "eval_runtime": 2.8138, | |
| "eval_samples_per_second": 533.087, | |
| "eval_spearmanr": 0.058559260163260116, | |
| "eval_steps_per_second": 4.265, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 2.1554, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.055355126341372324, | |
| "eval_loss": 2.3868918418884277, | |
| "eval_pearson": 0.06089199058890605, | |
| "eval_runtime": 2.8061, | |
| "eval_samples_per_second": 534.558, | |
| "eval_spearmanr": 0.04981826209383859, | |
| "eval_steps_per_second": 4.276, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 2.0556, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.07587737081449714, | |
| "eval_loss": 2.5739591121673584, | |
| "eval_pearson": 0.0800115043320288, | |
| "eval_runtime": 2.8092, | |
| "eval_samples_per_second": 533.959, | |
| "eval_spearmanr": 0.07174323729696545, | |
| "eval_steps_per_second": 4.272, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 2.0221, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.07517103861970047, | |
| "eval_loss": 2.465646266937256, | |
| "eval_pearson": 0.08491360492393328, | |
| "eval_runtime": 2.8092, | |
| "eval_samples_per_second": 533.96, | |
| "eval_spearmanr": 0.06542847231546765, | |
| "eval_steps_per_second": 4.272, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 2.0403, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.06472344315426198, | |
| "eval_loss": 2.3307483196258545, | |
| "eval_pearson": 0.07194759835590063, | |
| "eval_runtime": 2.8052, | |
| "eval_samples_per_second": 534.716, | |
| "eval_spearmanr": 0.05749928795262334, | |
| "eval_steps_per_second": 4.278, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 2.1732, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": 0.06413160396195583, | |
| "eval_loss": 2.5174152851104736, | |
| "eval_pearson": 0.06991174129088629, | |
| "eval_runtime": 2.8054, | |
| "eval_samples_per_second": 534.68, | |
| "eval_spearmanr": 0.058351466633025366, | |
| "eval_steps_per_second": 4.277, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 2.0399, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_combined_score": 0.06615269419943948, | |
| "eval_loss": 2.5648128986358643, | |
| "eval_pearson": 0.07178384296600182, | |
| "eval_runtime": 2.8071, | |
| "eval_samples_per_second": 534.35, | |
| "eval_spearmanr": 0.06052154543287713, | |
| "eval_steps_per_second": 4.275, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.28e-05, | |
| "loss": 2.0765, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_combined_score": 0.05558546651483845, | |
| "eval_loss": 2.3373327255249023, | |
| "eval_pearson": 0.06209781802846023, | |
| "eval_runtime": 2.8097, | |
| "eval_samples_per_second": 533.863, | |
| "eval_spearmanr": 0.04907311500121666, | |
| "eval_steps_per_second": 4.271, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 2.0538, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_combined_score": 0.04471248717433318, | |
| "eval_loss": 2.6402227878570557, | |
| "eval_pearson": 0.04634878343613905, | |
| "eval_runtime": 2.8018, | |
| "eval_samples_per_second": 535.361, | |
| "eval_spearmanr": 0.04307619091252732, | |
| "eval_steps_per_second": 4.283, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.1200000000000006e-05, | |
| "loss": 2.0147, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_combined_score": 0.05055556341697049, | |
| "eval_loss": 2.4726502895355225, | |
| "eval_pearson": 0.05397516518599763, | |
| "eval_runtime": 2.8161, | |
| "eval_samples_per_second": 532.645, | |
| "eval_spearmanr": 0.04713596164794335, | |
| "eval_steps_per_second": 4.261, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "step": 495, | |
| "total_flos": 9031970478620672.0, | |
| "train_loss": 2.1222905785146384, | |
| "train_runtime": 469.3728, | |
| "train_samples_per_second": 612.413, | |
| "train_steps_per_second": 4.794 | |
| } | |
| ], | |
| "max_steps": 2250, | |
| "num_train_epochs": 50, | |
| "total_flos": 9031970478620672.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |