| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03610678581905987, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003610678581905987, | |
| "eval_loss": NaN, | |
| "eval_runtime": 967.2112, | |
| "eval_samples_per_second": 9.645, | |
| "eval_steps_per_second": 4.823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001083203574571796, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002166407149143592, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032496107237153884, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0032496107237153884, | |
| "eval_loss": NaN, | |
| "eval_runtime": 966.5276, | |
| "eval_samples_per_second": 9.652, | |
| "eval_steps_per_second": 4.827, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004332814298287184, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005416017872858981, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006499221447430777, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006499221447430777, | |
| "eval_loss": NaN, | |
| "eval_runtime": 965.8944, | |
| "eval_samples_per_second": 9.658, | |
| "eval_steps_per_second": 4.83, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007582425022002573, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999229036240723, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008665628596574368, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009748832171146166, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019624552364536473, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009748832171146166, | |
| "eval_loss": NaN, | |
| "eval_runtime": 965.839, | |
| "eval_samples_per_second": 9.659, | |
| "eval_steps_per_second": 4.83, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010832035745717962, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011915239320289758, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018724960070727972, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.012998442894861554, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012998442894861554, | |
| "eval_loss": NaN, | |
| "eval_runtime": 966.325, | |
| "eval_samples_per_second": 9.654, | |
| "eval_steps_per_second": 4.828, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01408164646943335, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017343225094356855, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015164850044005146, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01624805361857694, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01624805361857694, | |
| "eval_loss": NaN, | |
| "eval_runtime": 966.2642, | |
| "eval_samples_per_second": 9.655, | |
| "eval_steps_per_second": 4.828, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017331257193148736, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018414460767720534, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001346117057077493, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01949766434229233, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.01949766434229233, | |
| "eval_loss": NaN, | |
| "eval_runtime": 966.6085, | |
| "eval_samples_per_second": 9.651, | |
| "eval_steps_per_second": 4.826, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.020580867916864126, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011175373974578378, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.021664071491435923, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.022747275066007717, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.824626025421626e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.022747275066007717, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2050.9942, | |
| "eval_samples_per_second": 4.549, | |
| "eval_steps_per_second": 2.275, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.023830478640579515, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.66554636144095e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.02491368221515131, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.538829429225069e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.025996885789723107, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.025996885789723107, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2143.6207, | |
| "eval_samples_per_second": 4.352, | |
| "eval_steps_per_second": 2.176, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0270800893642949, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0281632929388667, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5055195166981645e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.029246496513438493, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6567749056431467e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.029246496513438493, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2143.4135, | |
| "eval_samples_per_second": 4.352, | |
| "eval_steps_per_second": 2.176, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.03032970008801029, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.031412903662582085, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2750399292720283e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.03249610723715388, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03249610723715388, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2144.3001, | |
| "eval_samples_per_second": 4.351, | |
| "eval_steps_per_second": 2.176, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03357931081172568, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7544763546352834e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.03466251438629747, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.03574571796086927, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.709637592770991e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.03574571796086927, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2143.4901, | |
| "eval_samples_per_second": 4.352, | |
| "eval_steps_per_second": 2.176, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.305284264198144e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |