| { | |
| "best_metric": 1.2876315116882324, | |
| "best_model_checkpoint": "./outputs/checkpoint-2000", | |
| "epoch": 2.6666666666666665, | |
| "eval_steps": 100, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3509, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.4751445055007935, | |
| "eval_runtime": 155.0414, | |
| "eval_samples_per_second": 12.448, | |
| "eval_steps_per_second": 1.561, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2006, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.441214680671692, | |
| "eval_runtime": 151.6424, | |
| "eval_samples_per_second": 12.727, | |
| "eval_steps_per_second": 1.596, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1801, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.4250988960266113, | |
| "eval_runtime": 151.7377, | |
| "eval_samples_per_second": 12.719, | |
| "eval_steps_per_second": 1.595, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1655, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.4099382162094116, | |
| "eval_runtime": 151.5335, | |
| "eval_samples_per_second": 12.736, | |
| "eval_steps_per_second": 1.597, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1486, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.3928134441375732, | |
| "eval_runtime": 151.678, | |
| "eval_samples_per_second": 12.724, | |
| "eval_steps_per_second": 1.595, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1421, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.379417896270752, | |
| "eval_runtime": 151.6496, | |
| "eval_samples_per_second": 12.727, | |
| "eval_steps_per_second": 1.596, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1333, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.3729456663131714, | |
| "eval_runtime": 151.5395, | |
| "eval_samples_per_second": 12.736, | |
| "eval_steps_per_second": 1.597, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1179, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.359381914138794, | |
| "eval_runtime": 151.6759, | |
| "eval_samples_per_second": 12.725, | |
| "eval_steps_per_second": 1.596, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1028, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.3538635969161987, | |
| "eval_runtime": 151.6567, | |
| "eval_samples_per_second": 12.726, | |
| "eval_steps_per_second": 1.596, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0936, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.3417681455612183, | |
| "eval_runtime": 151.5959, | |
| "eval_samples_per_second": 12.731, | |
| "eval_steps_per_second": 1.596, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1035, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.3373662233352661, | |
| "eval_runtime": 151.8187, | |
| "eval_samples_per_second": 12.713, | |
| "eval_steps_per_second": 1.594, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0896, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.331199288368225, | |
| "eval_runtime": 151.8209, | |
| "eval_samples_per_second": 12.712, | |
| "eval_steps_per_second": 1.594, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.076, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.3220014572143555, | |
| "eval_runtime": 151.7501, | |
| "eval_samples_per_second": 12.718, | |
| "eval_steps_per_second": 1.595, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0772, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.316821575164795, | |
| "eval_runtime": 151.7755, | |
| "eval_samples_per_second": 12.716, | |
| "eval_steps_per_second": 1.594, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0664, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.3105216026306152, | |
| "eval_runtime": 151.7617, | |
| "eval_samples_per_second": 12.717, | |
| "eval_steps_per_second": 1.595, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0539, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.307134985923767, | |
| "eval_runtime": 151.6647, | |
| "eval_samples_per_second": 12.725, | |
| "eval_steps_per_second": 1.596, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0507, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.3011658191680908, | |
| "eval_runtime": 151.5927, | |
| "eval_samples_per_second": 12.731, | |
| "eval_steps_per_second": 1.596, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0491, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.296440839767456, | |
| "eval_runtime": 151.7344, | |
| "eval_samples_per_second": 12.72, | |
| "eval_steps_per_second": 1.595, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.04, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.2911254167556763, | |
| "eval_runtime": 151.7717, | |
| "eval_samples_per_second": 12.716, | |
| "eval_steps_per_second": 1.595, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0341, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.2876315116882324, | |
| "eval_runtime": 151.8147, | |
| "eval_samples_per_second": 12.713, | |
| "eval_steps_per_second": 1.594, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.2745693497470976e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |