| { | |
| "best_metric": 0.6053406596183777, | |
| "best_model_checkpoint": "output/checkpoint-500", | |
| "epoch": 0.8018442417560389, | |
| "eval_steps": 50, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.3333333333333332e-06, | |
| "loss": 0.6133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.61, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.6895522388059702, | |
| "eval_loss": 0.6718239784240723, | |
| "eval_runtime": 61.4305, | |
| "eval_samples_per_second": 5.453, | |
| "eval_steps_per_second": 1.367, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00012666666666666666, | |
| "loss": 0.6233, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.6835820895522388, | |
| "eval_loss": 0.695776641368866, | |
| "eval_runtime": 61.5801, | |
| "eval_samples_per_second": 5.44, | |
| "eval_steps_per_second": 1.364, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019333333333333333, | |
| "loss": 0.6187, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.6895522388059702, | |
| "eval_loss": 0.6547008156776428, | |
| "eval_runtime": 61.4876, | |
| "eval_samples_per_second": 5.448, | |
| "eval_steps_per_second": 1.366, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00026, | |
| "loss": 0.667, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.6686567164179105, | |
| "eval_loss": 0.7339211702346802, | |
| "eval_runtime": 61.0301, | |
| "eval_samples_per_second": 5.489, | |
| "eval_steps_per_second": 1.376, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002941291585127201, | |
| "loss": 0.6896, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.6388059701492538, | |
| "eval_loss": 0.6455020904541016, | |
| "eval_runtime": 61.0356, | |
| "eval_samples_per_second": 5.489, | |
| "eval_steps_per_second": 1.376, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002794520547945205, | |
| "loss": 0.6732, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.6388059701492538, | |
| "eval_loss": 0.8866483569145203, | |
| "eval_runtime": 61.5006, | |
| "eval_samples_per_second": 5.447, | |
| "eval_steps_per_second": 1.366, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002647749510763209, | |
| "loss": 0.6255, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.6746268656716418, | |
| "eval_loss": 0.6250954866409302, | |
| "eval_runtime": 61.4499, | |
| "eval_samples_per_second": 5.452, | |
| "eval_steps_per_second": 1.367, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002500978473581213, | |
| "loss": 0.6522, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.6925373134328359, | |
| "eval_loss": 0.7217190861701965, | |
| "eval_runtime": 61.1569, | |
| "eval_samples_per_second": 5.478, | |
| "eval_steps_per_second": 1.374, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00023542074363992171, | |
| "loss": 0.6592, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.6417910447761194, | |
| "eval_loss": 0.636791467666626, | |
| "eval_runtime": 61.431, | |
| "eval_samples_per_second": 5.453, | |
| "eval_steps_per_second": 1.367, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00022074363992172208, | |
| "loss": 0.624, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.7044776119402985, | |
| "eval_loss": 0.6053406596183777, | |
| "eval_runtime": 61.4573, | |
| "eval_samples_per_second": 5.451, | |
| "eval_steps_per_second": 1.367, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002060665362035225, | |
| "loss": 0.6098, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.6477611940298508, | |
| "eval_loss": 0.8857873678207397, | |
| "eval_runtime": 61.4645, | |
| "eval_samples_per_second": 5.45, | |
| "eval_steps_per_second": 1.367, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00019138943248532287, | |
| "loss": 0.6357, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.7074626865671642, | |
| "eval_loss": 0.607388436794281, | |
| "eval_runtime": 61.4941, | |
| "eval_samples_per_second": 5.448, | |
| "eval_steps_per_second": 1.366, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001767123287671233, | |
| "loss": 0.6103, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.6746268656716418, | |
| "eval_loss": 0.6098934412002563, | |
| "eval_runtime": 56.4929, | |
| "eval_samples_per_second": 5.93, | |
| "eval_steps_per_second": 1.487, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00016203522504892366, | |
| "loss": 0.6025, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.6895522388059702, | |
| "eval_loss": 0.6117912530899048, | |
| "eval_runtime": 61.1994, | |
| "eval_samples_per_second": 5.474, | |
| "eval_steps_per_second": 1.373, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00014735812133072405, | |
| "loss": 0.5837, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.6925373134328359, | |
| "eval_loss": 0.6470033526420593, | |
| "eval_runtime": 61.3513, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 1.369, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00013268101761252445, | |
| "loss": 0.623, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.6776119402985075, | |
| "eval_loss": 0.7178429365158081, | |
| "eval_runtime": 56.5122, | |
| "eval_samples_per_second": 5.928, | |
| "eval_steps_per_second": 1.486, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00011800391389432484, | |
| "loss": 0.6285, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.6805970149253732, | |
| "eval_loss": 0.7012776732444763, | |
| "eval_runtime": 61.0309, | |
| "eval_samples_per_second": 5.489, | |
| "eval_steps_per_second": 1.376, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00010332681017612522, | |
| "loss": 0.609, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.6656716417910448, | |
| "eval_loss": 0.6416519284248352, | |
| "eval_runtime": 56.5079, | |
| "eval_samples_per_second": 5.928, | |
| "eval_steps_per_second": 1.487, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.864970645792562e-05, | |
| "loss": 0.6, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.6835820895522388, | |
| "eval_loss": 0.6628562808036804, | |
| "eval_runtime": 61.1667, | |
| "eval_samples_per_second": 5.477, | |
| "eval_steps_per_second": 1.373, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.397260273972601e-05, | |
| "loss": 0.6142, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.6805970149253732, | |
| "eval_loss": 0.635610044002533, | |
| "eval_runtime": 61.6579, | |
| "eval_samples_per_second": 5.433, | |
| "eval_steps_per_second": 1.362, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1247, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 3.745803772140749e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |