| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6101694915254238, | |
| "eval_steps": 9, | |
| "global_step": 99, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0061633281972265025, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.6376, | |
| "eval_samples_per_second": 51.942, | |
| "eval_steps_per_second": 13.27, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01848998459167951, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03697996918335902, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05546995377503852, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05546995377503852, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2322, | |
| "eval_samples_per_second": 61.375, | |
| "eval_steps_per_second": 15.68, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07395993836671803, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09244992295839753, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11093990755007704, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11093990755007704, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2477, | |
| "eval_samples_per_second": 60.952, | |
| "eval_steps_per_second": 15.572, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12942989214175654, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14791987673343607, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16640986132511557, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16640986132511557, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2706, | |
| "eval_samples_per_second": 60.337, | |
| "eval_steps_per_second": 15.415, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.18489984591679506, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2218798151001541, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2218798151001541, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2512, | |
| "eval_samples_per_second": 60.858, | |
| "eval_steps_per_second": 15.548, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24036979969183359, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2588597842835131, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2773497688751926, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2773497688751926, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.254, | |
| "eval_samples_per_second": 60.78, | |
| "eval_steps_per_second": 15.528, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.29583975346687214, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31432973805855163, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.33281972265023113, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.33281972265023113, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2596, | |
| "eval_samples_per_second": 60.629, | |
| "eval_steps_per_second": 15.489, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.35130970724191063, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3697996918335901, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3882896764252696, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3882896764252696, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2511, | |
| "eval_samples_per_second": 60.86, | |
| "eval_steps_per_second": 15.548, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4252696456086287, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.4437596302003082, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4437596302003082, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2311, | |
| "eval_samples_per_second": 61.406, | |
| "eval_steps_per_second": 15.688, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4622496147919877, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.48073959938366717, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.49922958397534667, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.49922958397534667, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2511, | |
| "eval_samples_per_second": 60.858, | |
| "eval_steps_per_second": 15.548, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5177195685670262, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5362095531587057, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5546995377503852, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5546995377503852, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2389, | |
| "eval_samples_per_second": 61.19, | |
| "eval_steps_per_second": 15.633, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5731895223420647, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.5916795069337443, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2387, | |
| "eval_samples_per_second": 61.197, | |
| "eval_steps_per_second": 15.634, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3893223025016832.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |