| { | |
| "best_metric": 0.7588818073272705, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.408450704225352, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 25.043020248413086, | |
| "learning_rate": 5e-05, | |
| "loss": 12.3344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "eval_loss": 12.388128280639648, | |
| "eval_runtime": 1.3454, | |
| "eval_samples_per_second": 89.192, | |
| "eval_steps_per_second": 11.149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 22.335596084594727, | |
| "learning_rate": 0.0001, | |
| "loss": 12.412, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 21.580015182495117, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.2237, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 16.71055030822754, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.442, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": 15.653229713439941, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 8.3925, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 14.434592247009277, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.7109, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.39436619718309857, | |
| "grad_norm": 12.084268569946289, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.9095, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 14.198653221130371, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.1487, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": 13.856998443603516, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.039, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 13.335588455200195, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1799, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6197183098591549, | |
| "grad_norm": 6.2130608558654785, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.3482, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": 5.610598564147949, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3538, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7323943661971831, | |
| "grad_norm": 4.826842784881592, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5145, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7887323943661971, | |
| "grad_norm": 3.8220436573028564, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.057, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8450704225352113, | |
| "grad_norm": 6.495180606842041, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9014084507042254, | |
| "grad_norm": 4.079573154449463, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1101, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9577464788732394, | |
| "grad_norm": 3.5554068088531494, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0183, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0140845070422535, | |
| "grad_norm": 4.620770454406738, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0595, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0704225352112675, | |
| "grad_norm": 2.241077423095703, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7834, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1267605633802817, | |
| "grad_norm": 3.594456434249878, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8131, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1830985915492958, | |
| "grad_norm": 1.6228787899017334, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.825, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2394366197183098, | |
| "grad_norm": 4.617722511291504, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8721, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.295774647887324, | |
| "grad_norm": 2.3542089462280273, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8546, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.352112676056338, | |
| "grad_norm": 1.9718202352523804, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7775, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "grad_norm": 1.1844096183776855, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "eval_loss": 0.7588818073272705, | |
| "eval_runtime": 1.3426, | |
| "eval_samples_per_second": 89.38, | |
| "eval_steps_per_second": 11.173, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.29768176943104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |