| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009379763160980185, | |
| "eval_steps": 5, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023449407902450463, | |
| "eval_loss": 1.0330525636672974, | |
| "eval_runtime": 1094.0868, | |
| "eval_samples_per_second": 6.564, | |
| "eval_steps_per_second": 0.821, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007034822370735139, | |
| "grad_norm": 3.4436771869659424, | |
| "learning_rate": 3e-05, | |
| "loss": 4.3657, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011724703951225231, | |
| "eval_loss": 0.9120507836341858, | |
| "eval_runtime": 1097.6215, | |
| "eval_samples_per_second": 6.543, | |
| "eval_steps_per_second": 0.818, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014069644741470278, | |
| "grad_norm": 3.4235165119171143, | |
| "learning_rate": 6e-05, | |
| "loss": 3.8288, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002110446711220542, | |
| "grad_norm": 2.5789833068847656, | |
| "learning_rate": 9e-05, | |
| "loss": 2.9521, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0023449407902450463, | |
| "eval_loss": 0.611504077911377, | |
| "eval_runtime": 1097.4338, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 0.818, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028139289482940555, | |
| "grad_norm": 1.891883134841919, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.4376, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0035174111853675696, | |
| "grad_norm": 1.4731217622756958, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1727, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0035174111853675696, | |
| "eval_loss": 0.5438524484634399, | |
| "eval_runtime": 1097.8515, | |
| "eval_samples_per_second": 6.542, | |
| "eval_steps_per_second": 0.818, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004220893422441084, | |
| "grad_norm": 1.4727015495300293, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.0787, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0046898815804900925, | |
| "eval_loss": 0.5278410911560059, | |
| "eval_runtime": 1097.7064, | |
| "eval_samples_per_second": 6.543, | |
| "eval_steps_per_second": 0.818, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004924375659514597, | |
| "grad_norm": 1.5371854305267334, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 2.1324, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005627857896588111, | |
| "grad_norm": 1.4840267896652222, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.9502, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005862351975612616, | |
| "eval_loss": 0.5124460458755493, | |
| "eval_runtime": 1097.1769, | |
| "eval_samples_per_second": 6.546, | |
| "eval_steps_per_second": 0.818, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006331340133661625, | |
| "grad_norm": 1.4862679243087769, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 2.346, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007034822370735139, | |
| "grad_norm": 1.4574503898620605, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2429, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007034822370735139, | |
| "eval_loss": 0.5047998428344727, | |
| "eval_runtime": 1097.4525, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 0.818, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007738304607808653, | |
| "grad_norm": 1.3703689575195312, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.875, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008207292765857662, | |
| "eval_loss": 0.49850761890411377, | |
| "eval_runtime": 1097.4891, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 0.818, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008441786844882167, | |
| "grad_norm": 1.2534970045089722, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 1.8852, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009145269081955681, | |
| "grad_norm": 1.3424217700958252, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 1.8502, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009379763160980185, | |
| "eval_loss": 0.4948474168777466, | |
| "eval_runtime": 1097.3227, | |
| "eval_samples_per_second": 6.545, | |
| "eval_steps_per_second": 0.818, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.030418891538432e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |