| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009321401938851604, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003728560775540641, | |
| "grad_norm": 14.098886489868164, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 14.0719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003728560775540641, | |
| "eval_loss": 1.8703862428665161, | |
| "eval_runtime": 509.0913, | |
| "eval_samples_per_second": 4.437, | |
| "eval_steps_per_second": 2.22, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007457121551081282, | |
| "grad_norm": 17.57554054260254, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 16.0438, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011185682326621924, | |
| "grad_norm": 14.289568901062012, | |
| "learning_rate": 0.0002, | |
| "loss": 14.013, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014914243102162564, | |
| "grad_norm": 16.104290008544922, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 12.8257, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018642803877703207, | |
| "grad_norm": 21.064966201782227, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 10.156, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022371364653243847, | |
| "grad_norm": 15.340848922729492, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 7.2449, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002609992542878449, | |
| "grad_norm": 18.457630157470703, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 6.17, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002982848620432513, | |
| "grad_norm": 13.35014820098877, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 5.0583, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003355704697986577, | |
| "grad_norm": 32.16826629638672, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 5.1311, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0037285607755406414, | |
| "grad_norm": 19.90258026123047, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 4.7855, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004101416853094705, | |
| "grad_norm": 19.41876792907715, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 4.0821, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0044742729306487695, | |
| "grad_norm": 32.109249114990234, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 4.0448, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004847129008202834, | |
| "grad_norm": 33.09053421020508, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 5.074, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005219985085756898, | |
| "grad_norm": 12.651711463928223, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 3.5618, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005592841163310962, | |
| "grad_norm": 10.729059219360352, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.2738, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005965697240865026, | |
| "grad_norm": 17.2890567779541, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 2.7353, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00633855331841909, | |
| "grad_norm": 23.347806930541992, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 2.7702, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006711409395973154, | |
| "grad_norm": 22.53374481201172, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 3.9281, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0070842654735272185, | |
| "grad_norm": 7.728074550628662, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 2.3155, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007457121551081283, | |
| "grad_norm": 11.007797241210938, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 2.4846, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007829977628635347, | |
| "grad_norm": 7.158455848693848, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9451, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00820283370618941, | |
| "grad_norm": 7.924790382385254, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 1.974, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008575689783743476, | |
| "grad_norm": 10.626357078552246, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 2.9784, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008948545861297539, | |
| "grad_norm": 8.380443572998047, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.9285, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009321401938851604, | |
| "grad_norm": 8.995612144470215, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 2.5047, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009321401938851604, | |
| "eval_loss": 0.322700172662735, | |
| "eval_runtime": 512.0454, | |
| "eval_samples_per_second": 4.412, | |
| "eval_steps_per_second": 2.207, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.347789697024e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |