| { | |
| "best_metric": 0.9542251825332642, | |
| "best_model_checkpoint": "./outputs/checkpoint-2100", | |
| "epoch": 2.9829545454545454, | |
| "eval_steps": 100, | |
| "global_step": 2100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5836, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.0926024913787842, | |
| "eval_runtime": 92.4288, | |
| "eval_samples_per_second": 16.142, | |
| "eval_steps_per_second": 2.023, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2272, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.071556806564331, | |
| "eval_runtime": 89.865, | |
| "eval_samples_per_second": 16.603, | |
| "eval_steps_per_second": 2.081, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2134, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.0566277503967285, | |
| "eval_runtime": 89.873, | |
| "eval_samples_per_second": 16.601, | |
| "eval_steps_per_second": 2.081, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1959, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.0465874671936035, | |
| "eval_runtime": 89.8186, | |
| "eval_samples_per_second": 16.611, | |
| "eval_steps_per_second": 2.082, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1861, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.0348858833312988, | |
| "eval_runtime": 89.7272, | |
| "eval_samples_per_second": 16.628, | |
| "eval_steps_per_second": 2.084, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1735, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.0253515243530273, | |
| "eval_runtime": 89.7076, | |
| "eval_samples_per_second": 16.632, | |
| "eval_steps_per_second": 2.085, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1615, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.0192995071411133, | |
| "eval_runtime": 89.8909, | |
| "eval_samples_per_second": 16.598, | |
| "eval_steps_per_second": 2.08, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1509, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.0122530460357666, | |
| "eval_runtime": 89.7843, | |
| "eval_samples_per_second": 16.618, | |
| "eval_steps_per_second": 2.083, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1265, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 1.0055540800094604, | |
| "eval_runtime": 89.7773, | |
| "eval_samples_per_second": 16.619, | |
| "eval_steps_per_second": 2.083, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1298, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 1.0025967359542847, | |
| "eval_runtime": 89.9303, | |
| "eval_samples_per_second": 16.591, | |
| "eval_steps_per_second": 2.079, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1323, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.9946721792221069, | |
| "eval_runtime": 90.1252, | |
| "eval_samples_per_second": 16.555, | |
| "eval_steps_per_second": 2.075, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1193, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.9902428984642029, | |
| "eval_runtime": 89.9449, | |
| "eval_samples_per_second": 16.588, | |
| "eval_steps_per_second": 2.079, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1111, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.9833947420120239, | |
| "eval_runtime": 90.3396, | |
| "eval_samples_per_second": 16.515, | |
| "eval_steps_per_second": 2.07, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1141, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.9805576205253601, | |
| "eval_runtime": 89.7687, | |
| "eval_samples_per_second": 16.62, | |
| "eval_steps_per_second": 2.083, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0911, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.9768579602241516, | |
| "eval_runtime": 89.855, | |
| "eval_samples_per_second": 16.605, | |
| "eval_steps_per_second": 2.081, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0919, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.9718981981277466, | |
| "eval_runtime": 89.8866, | |
| "eval_samples_per_second": 16.599, | |
| "eval_steps_per_second": 2.08, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.073, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.9693555235862732, | |
| "eval_runtime": 89.9595, | |
| "eval_samples_per_second": 16.585, | |
| "eval_steps_per_second": 2.079, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0759, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 0.9647061228752136, | |
| "eval_runtime": 90.1576, | |
| "eval_samples_per_second": 16.549, | |
| "eval_steps_per_second": 2.074, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0784, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.961346447467804, | |
| "eval_runtime": 89.8749, | |
| "eval_samples_per_second": 16.601, | |
| "eval_steps_per_second": 2.081, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0755, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 0.9575291275978088, | |
| "eval_runtime": 89.8309, | |
| "eval_samples_per_second": 16.609, | |
| "eval_steps_per_second": 2.082, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0721, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.9542251825332642, | |
| "eval_runtime": 89.9742, | |
| "eval_samples_per_second": 16.583, | |
| "eval_steps_per_second": 2.078, | |
| "step": 2100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2112, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.1673223042295808e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |