| { | |
| "best_metric": 1.1186692714691162, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-300", | |
| "epoch": 0.20949720670391062, | |
| "eval_steps": 50, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006983240223463687, | |
| "eval_loss": 1.370945930480957, | |
| "eval_runtime": 52.3088, | |
| "eval_samples_per_second": 11.528, | |
| "eval_steps_per_second": 2.887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006983240223463687, | |
| "grad_norm": 0.8107507228851318, | |
| "learning_rate": 4.22e-05, | |
| "loss": 1.0747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013966480446927373, | |
| "grad_norm": 0.5126632452011108, | |
| "learning_rate": 8.44e-05, | |
| "loss": 0.9055, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02094972067039106, | |
| "grad_norm": 0.6242287158966064, | |
| "learning_rate": 0.0001266, | |
| "loss": 0.9136, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027932960893854747, | |
| "grad_norm": 0.6027160882949829, | |
| "learning_rate": 0.0001688, | |
| "loss": 0.8772, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.034916201117318434, | |
| "grad_norm": 1.1633682250976562, | |
| "learning_rate": 0.000211, | |
| "loss": 2.2737, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.034916201117318434, | |
| "eval_loss": 1.2990323305130005, | |
| "eval_runtime": 52.3291, | |
| "eval_samples_per_second": 11.523, | |
| "eval_steps_per_second": 2.886, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04189944134078212, | |
| "grad_norm": 0.47972574830055237, | |
| "learning_rate": 0.00021074300730241147, | |
| "loss": 0.9318, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04888268156424581, | |
| "grad_norm": 0.447611004114151, | |
| "learning_rate": 0.00020997328125223568, | |
| "loss": 0.8635, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.055865921787709494, | |
| "grad_norm": 0.48597830533981323, | |
| "learning_rate": 0.0002086945718774165, | |
| "loss": 0.9055, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06284916201117319, | |
| "grad_norm": 0.6027791500091553, | |
| "learning_rate": 0.00020691310892149265, | |
| "loss": 0.9913, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06983240223463687, | |
| "grad_norm": 1.350448489189148, | |
| "learning_rate": 0.00020463757149291335, | |
| "loss": 2.3175, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06983240223463687, | |
| "eval_loss": 1.2746367454528809, | |
| "eval_runtime": 52.113, | |
| "eval_samples_per_second": 11.571, | |
| "eval_steps_per_second": 2.898, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07681564245810056, | |
| "grad_norm": 0.5767949223518372, | |
| "learning_rate": 0.0002018790457812944, | |
| "loss": 0.9637, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08379888268156424, | |
| "grad_norm": 0.4701750576496124, | |
| "learning_rate": 0.0001986509710466168, | |
| "loss": 0.945, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09078212290502793, | |
| "grad_norm": 0.5360428690910339, | |
| "learning_rate": 0.00019496907414450293, | |
| "loss": 0.867, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09776536312849161, | |
| "grad_norm": 0.5477281212806702, | |
| "learning_rate": 0.00019085129290655697, | |
| "loss": 0.848, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.10474860335195531, | |
| "grad_norm": 1.3646817207336426, | |
| "learning_rate": 0.00018631768874905217, | |
| "loss": 2.1608, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10474860335195531, | |
| "eval_loss": 1.219596028327942, | |
| "eval_runtime": 52.3452, | |
| "eval_samples_per_second": 11.52, | |
| "eval_steps_per_second": 2.885, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11173184357541899, | |
| "grad_norm": 0.4920892119407654, | |
| "learning_rate": 0.0001813903489357277, | |
| "loss": 0.9284, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11871508379888268, | |
| "grad_norm": 0.45749855041503906, | |
| "learning_rate": 0.00017609327897085954, | |
| "loss": 0.8539, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12569832402234637, | |
| "grad_norm": 0.4445869028568268, | |
| "learning_rate": 0.00017045228564685694, | |
| "loss": 0.8592, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13268156424581007, | |
| "grad_norm": 0.5051153302192688, | |
| "learning_rate": 0.0001644948513161638, | |
| "loss": 0.7785, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13966480446927373, | |
| "grad_norm": 1.2540266513824463, | |
| "learning_rate": 0.00015825, | |
| "loss": 1.9825, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13966480446927373, | |
| "eval_loss": 1.1976240873336792, | |
| "eval_runtime": 52.2387, | |
| "eval_samples_per_second": 11.543, | |
| "eval_steps_per_second": 2.891, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14664804469273743, | |
| "grad_norm": 0.44770610332489014, | |
| "learning_rate": 0.00015174815598624768, | |
| "loss": 0.91, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15363128491620112, | |
| "grad_norm": 0.4289681613445282, | |
| "learning_rate": 0.00014502099560537873, | |
| "loss": 0.9587, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.16061452513966482, | |
| "grad_norm": 0.4543539583683014, | |
| "learning_rate": 0.00013810129290655696, | |
| "loss": 0.7476, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.16759776536312848, | |
| "grad_norm": 0.6141102313995361, | |
| "learning_rate": 0.00013102275998576495, | |
| "loss": 0.9607, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.17458100558659218, | |
| "grad_norm": 1.0941569805145264, | |
| "learning_rate": 0.00012381988274386116, | |
| "loss": 2.2834, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17458100558659218, | |
| "eval_loss": 1.150519847869873, | |
| "eval_runtime": 52.3046, | |
| "eval_samples_per_second": 11.529, | |
| "eval_steps_per_second": 2.887, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.18156424581005587, | |
| "grad_norm": 0.5020606517791748, | |
| "learning_rate": 0.00011652775287473745, | |
| "loss": 0.9043, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18854748603351956, | |
| "grad_norm": 0.4165470004081726, | |
| "learning_rate": 0.00010918189690211387, | |
| "loss": 1.2468, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.19553072625698323, | |
| "grad_norm": 0.4466763138771057, | |
| "learning_rate": 0.00010181810309788618, | |
| "loss": 0.772, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.20251396648044692, | |
| "grad_norm": 0.5462682247161865, | |
| "learning_rate": 9.447224712526258e-05, | |
| "loss": 0.8108, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.20949720670391062, | |
| "grad_norm": 1.6482914686203003, | |
| "learning_rate": 8.718011725613886e-05, | |
| "loss": 1.9559, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.20949720670391062, | |
| "eval_loss": 1.1186692714691162, | |
| "eval_runtime": 52.2511, | |
| "eval_samples_per_second": 11.54, | |
| "eval_steps_per_second": 2.89, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 8.48689809063936e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |