| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 60.0, | |
| "global_step": 18720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 34.136592864990234, | |
| "eval_runtime": 6.7811, | |
| "eval_samples_per_second": 40.849, | |
| "eval_steps_per_second": 5.161, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00048664529914529915, | |
| "loss": 34.4899, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4981949458483754, | |
| "eval_loss": 31.61578369140625, | |
| "eval_runtime": 6.7976, | |
| "eval_samples_per_second": 40.75, | |
| "eval_steps_per_second": 5.149, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.4981949458483754, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 29.7502498626709, | |
| "eval_runtime": 6.8777, | |
| "eval_samples_per_second": 40.275, | |
| "eval_steps_per_second": 5.089, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.4981949458483754, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0004732905982905983, | |
| "loss": 31.3598, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5018050541516246, | |
| "eval_loss": 29.3625545501709, | |
| "eval_runtime": 6.7502, | |
| "eval_samples_per_second": 41.036, | |
| "eval_steps_per_second": 5.185, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5018050541516246, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0004599358974358974, | |
| "loss": 29.6767, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 29.12201690673828, | |
| "eval_runtime": 6.7799, | |
| "eval_samples_per_second": 40.856, | |
| "eval_steps_per_second": 5.162, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5018050541516246, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 28.767154693603516, | |
| "eval_runtime": 6.9678, | |
| "eval_samples_per_second": 39.754, | |
| "eval_steps_per_second": 5.023, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.0004465811965811966, | |
| "loss": 29.2217, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5126353790613718, | |
| "eval_loss": 27.22684097290039, | |
| "eval_runtime": 6.9403, | |
| "eval_samples_per_second": 39.912, | |
| "eval_steps_per_second": 5.043, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4981949458483754, | |
| "eval_loss": 23.78185272216797, | |
| "eval_runtime": 6.9311, | |
| "eval_samples_per_second": 39.965, | |
| "eval_steps_per_second": 5.05, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.00043322649572649576, | |
| "loss": 27.2285, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 20.265117645263672, | |
| "eval_runtime": 6.8588, | |
| "eval_samples_per_second": 40.386, | |
| "eval_steps_per_second": 5.103, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0004198717948717949, | |
| "loss": 23.6907, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 17.834997177124023, | |
| "eval_runtime": 6.854, | |
| "eval_samples_per_second": 40.414, | |
| "eval_steps_per_second": 5.107, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 16.79086685180664, | |
| "eval_runtime": 6.875, | |
| "eval_samples_per_second": 40.291, | |
| "eval_steps_per_second": 5.091, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00040651709401709403, | |
| "loss": 21.0475, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 16.18973159790039, | |
| "eval_runtime": 6.8215, | |
| "eval_samples_per_second": 40.607, | |
| "eval_steps_per_second": 5.131, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.00039316239316239317, | |
| "loss": 20.1309, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 15.723366737365723, | |
| "eval_runtime": 6.8805, | |
| "eval_samples_per_second": 40.259, | |
| "eval_steps_per_second": 5.087, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 15.408354759216309, | |
| "eval_runtime": 6.7385, | |
| "eval_samples_per_second": 41.107, | |
| "eval_steps_per_second": 5.194, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.0003798076923076923, | |
| "loss": 19.6553, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 15.165691375732422, | |
| "eval_runtime": 6.8564, | |
| "eval_samples_per_second": 40.4, | |
| "eval_steps_per_second": 5.105, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.971611022949219, | |
| "eval_runtime": 6.7476, | |
| "eval_samples_per_second": 41.052, | |
| "eval_steps_per_second": 5.187, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.00036645299145299145, | |
| "loss": 19.3496, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.78799819946289, | |
| "eval_runtime": 6.8718, | |
| "eval_samples_per_second": 40.31, | |
| "eval_steps_per_second": 5.093, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.00035309829059829064, | |
| "loss": 19.122, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.632237434387207, | |
| "eval_runtime": 6.7256, | |
| "eval_samples_per_second": 41.186, | |
| "eval_steps_per_second": 5.204, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.542409896850586, | |
| "eval_runtime": 6.8507, | |
| "eval_samples_per_second": 40.434, | |
| "eval_steps_per_second": 5.109, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0003397435897435898, | |
| "loss": 18.9517, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.4177885055542, | |
| "eval_runtime": 6.7527, | |
| "eval_samples_per_second": 41.021, | |
| "eval_steps_per_second": 5.183, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0003263888888888889, | |
| "loss": 18.7994, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.27253532409668, | |
| "eval_runtime": 6.7896, | |
| "eval_samples_per_second": 40.798, | |
| "eval_steps_per_second": 5.155, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.213791847229004, | |
| "eval_runtime": 6.7633, | |
| "eval_samples_per_second": 40.956, | |
| "eval_steps_per_second": 5.175, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.00031303418803418806, | |
| "loss": 18.6835, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.106380462646484, | |
| "eval_runtime": 6.8943, | |
| "eval_samples_per_second": 40.178, | |
| "eval_steps_per_second": 5.077, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.040120124816895, | |
| "eval_runtime": 6.8791, | |
| "eval_samples_per_second": 40.267, | |
| "eval_steps_per_second": 5.088, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0002996794871794872, | |
| "loss": 18.59, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.947840690612793, | |
| "eval_runtime": 6.8835, | |
| "eval_samples_per_second": 40.241, | |
| "eval_steps_per_second": 5.085, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.00028632478632478634, | |
| "loss": 18.504, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.915633201599121, | |
| "eval_runtime": 6.9102, | |
| "eval_samples_per_second": 40.086, | |
| "eval_steps_per_second": 5.065, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.833467483520508, | |
| "eval_runtime": 6.8108, | |
| "eval_samples_per_second": 40.67, | |
| "eval_steps_per_second": 5.139, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0002729700854700855, | |
| "loss": 18.4387, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.77609634399414, | |
| "eval_runtime": 6.7793, | |
| "eval_samples_per_second": 40.86, | |
| "eval_steps_per_second": 5.163, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.00025961538461538467, | |
| "loss": 18.3758, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.73122787475586, | |
| "eval_runtime": 6.8795, | |
| "eval_samples_per_second": 40.264, | |
| "eval_steps_per_second": 5.088, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.67911148071289, | |
| "eval_runtime": 6.7675, | |
| "eval_samples_per_second": 40.931, | |
| "eval_steps_per_second": 5.172, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0002462606837606838, | |
| "loss": 18.3264, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.645761489868164, | |
| "eval_runtime": 6.8407, | |
| "eval_samples_per_second": 40.493, | |
| "eval_steps_per_second": 5.116, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.599126815795898, | |
| "eval_runtime": 6.7517, | |
| "eval_samples_per_second": 41.027, | |
| "eval_steps_per_second": 5.184, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.00023290598290598292, | |
| "loss": 18.2808, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.576165199279785, | |
| "eval_runtime": 6.7501, | |
| "eval_samples_per_second": 41.037, | |
| "eval_steps_per_second": 5.185, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.00021955128205128206, | |
| "loss": 18.2355, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.52829360961914, | |
| "eval_runtime": 6.9163, | |
| "eval_samples_per_second": 40.05, | |
| "eval_steps_per_second": 5.06, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.491928100585938, | |
| "eval_runtime": 6.9079, | |
| "eval_samples_per_second": 40.099, | |
| "eval_steps_per_second": 5.067, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0002061965811965812, | |
| "loss": 18.2071, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.472068786621094, | |
| "eval_runtime": 6.8267, | |
| "eval_samples_per_second": 40.576, | |
| "eval_steps_per_second": 5.127, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.00019284188034188036, | |
| "loss": 18.1831, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.437543869018555, | |
| "eval_runtime": 6.9295, | |
| "eval_samples_per_second": 39.974, | |
| "eval_steps_per_second": 5.051, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.409741401672363, | |
| "eval_runtime": 6.8497, | |
| "eval_samples_per_second": 40.44, | |
| "eval_steps_per_second": 5.11, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0001794871794871795, | |
| "loss": 18.1448, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.400425910949707, | |
| "eval_runtime": 6.818, | |
| "eval_samples_per_second": 40.628, | |
| "eval_steps_per_second": 5.133, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.369094848632812, | |
| "eval_runtime": 6.8893, | |
| "eval_samples_per_second": 40.207, | |
| "eval_steps_per_second": 5.08, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.00016613247863247864, | |
| "loss": 18.1182, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.343010902404785, | |
| "eval_runtime": 6.7253, | |
| "eval_samples_per_second": 41.188, | |
| "eval_steps_per_second": 5.204, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0001527777777777778, | |
| "loss": 18.1006, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.351433753967285, | |
| "eval_runtime": 6.84, | |
| "eval_samples_per_second": 40.497, | |
| "eval_steps_per_second": 5.117, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.301740646362305, | |
| "eval_runtime": 6.7737, | |
| "eval_samples_per_second": 40.893, | |
| "eval_steps_per_second": 5.167, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.00013942307692307694, | |
| "loss": 18.0785, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.283843040466309, | |
| "eval_runtime": 6.9371, | |
| "eval_samples_per_second": 39.93, | |
| "eval_steps_per_second": 5.045, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.00012606837606837608, | |
| "loss": 18.0562, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.268693923950195, | |
| "eval_runtime": 6.9575, | |
| "eval_samples_per_second": 39.813, | |
| "eval_steps_per_second": 5.031, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.255533218383789, | |
| "eval_runtime": 6.7526, | |
| "eval_samples_per_second": 41.021, | |
| "eval_steps_per_second": 5.183, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.00011271367521367522, | |
| "loss": 18.0454, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.250981330871582, | |
| "eval_runtime": 6.7857, | |
| "eval_samples_per_second": 40.821, | |
| "eval_steps_per_second": 5.158, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.238372802734375, | |
| "eval_runtime": 6.8653, | |
| "eval_samples_per_second": 40.348, | |
| "eval_steps_per_second": 5.098, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 9.935897435897436e-05, | |
| "loss": 18.0293, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.209638595581055, | |
| "eval_runtime": 6.8821, | |
| "eval_samples_per_second": 40.249, | |
| "eval_steps_per_second": 5.086, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 8.600427350427351e-05, | |
| "loss": 18.0221, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.201277732849121, | |
| "eval_runtime": 6.8957, | |
| "eval_samples_per_second": 40.17, | |
| "eval_steps_per_second": 5.076, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.193614959716797, | |
| "eval_runtime": 6.91, | |
| "eval_samples_per_second": 40.087, | |
| "eval_steps_per_second": 5.065, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 7.264957264957266e-05, | |
| "loss": 17.9969, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.18133544921875, | |
| "eval_runtime": 6.7708, | |
| "eval_samples_per_second": 40.911, | |
| "eval_steps_per_second": 5.169, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 5.929487179487179e-05, | |
| "loss": 17.9919, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.173555374145508, | |
| "eval_runtime": 6.8778, | |
| "eval_samples_per_second": 40.275, | |
| "eval_steps_per_second": 5.089, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.168095588684082, | |
| "eval_runtime": 7.0746, | |
| "eval_samples_per_second": 39.154, | |
| "eval_steps_per_second": 4.947, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 4.5940170940170944e-05, | |
| "loss": 17.9823, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.155855178833008, | |
| "eval_runtime": 6.8206, | |
| "eval_samples_per_second": 40.612, | |
| "eval_steps_per_second": 5.131, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.153690338134766, | |
| "eval_runtime": 6.7644, | |
| "eval_samples_per_second": 40.95, | |
| "eval_steps_per_second": 5.174, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 3.258547008547009e-05, | |
| "loss": 17.9804, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.149040222167969, | |
| "eval_runtime": 6.8337, | |
| "eval_samples_per_second": 40.535, | |
| "eval_steps_per_second": 5.122, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 17.9743, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.146079063415527, | |
| "eval_runtime": 7.0014, | |
| "eval_samples_per_second": 39.563, | |
| "eval_steps_per_second": 4.999, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.142921447753906, | |
| "eval_runtime": 6.9188, | |
| "eval_samples_per_second": 40.036, | |
| "eval_steps_per_second": 5.059, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 5.876068376068376e-06, | |
| "loss": 17.9703, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.142366409301758, | |
| "eval_runtime": 6.8158, | |
| "eval_samples_per_second": 40.641, | |
| "eval_steps_per_second": 5.135, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 20.21760963374733, | |
| "train_runtime": 6217.2634, | |
| "train_samples_per_second": 24.03, | |
| "train_steps_per_second": 3.011 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |