| { | |
| "best_metric": 2.195878505706787, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.00924898261191269, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003699593044765076, | |
| "grad_norm": 0.40353071689605713, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7556, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003699593044765076, | |
| "eval_loss": 2.596755027770996, | |
| "eval_runtime": 144.7535, | |
| "eval_samples_per_second": 7.869, | |
| "eval_steps_per_second": 3.938, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007399186089530152, | |
| "grad_norm": 0.378619909286499, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6214, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011098779134295228, | |
| "grad_norm": 0.5606754422187805, | |
| "learning_rate": 6e-05, | |
| "loss": 2.641, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014798372179060304, | |
| "grad_norm": 0.30437085032463074, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6036, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001849796522382538, | |
| "grad_norm": 0.3493916988372803, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001849796522382538, | |
| "eval_loss": 2.587604284286499, | |
| "eval_runtime": 137.0587, | |
| "eval_samples_per_second": 8.31, | |
| "eval_steps_per_second": 4.159, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022197558268590455, | |
| "grad_norm": 0.541628360748291, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2904, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002589715131335553, | |
| "grad_norm": 0.4091279208660126, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5181, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029596744358120607, | |
| "grad_norm": 0.5294743776321411, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5261, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003329633740288568, | |
| "grad_norm": 0.6014209389686584, | |
| "learning_rate": 0.00018, | |
| "loss": 2.621, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003699593044765076, | |
| "grad_norm": 0.608256459236145, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003699593044765076, | |
| "eval_loss": 2.4349887371063232, | |
| "eval_runtime": 139.861, | |
| "eval_samples_per_second": 8.144, | |
| "eval_steps_per_second": 4.075, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004069552349241583, | |
| "grad_norm": 0.683988630771637, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.2553, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004439511653718091, | |
| "grad_norm": 0.6252261400222778, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.2496, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004809470958194599, | |
| "grad_norm": 0.5618606805801392, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.1804, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005179430262671106, | |
| "grad_norm": 0.6698136925697327, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.4199, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005549389567147614, | |
| "grad_norm": 0.6190295219421387, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.2062, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005549389567147614, | |
| "eval_loss": 2.2569127082824707, | |
| "eval_runtime": 139.8151, | |
| "eval_samples_per_second": 8.146, | |
| "eval_steps_per_second": 4.077, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0059193488716241215, | |
| "grad_norm": 0.5969918370246887, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2917, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006289308176100629, | |
| "grad_norm": 0.6747704744338989, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.3536, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006659267480577136, | |
| "grad_norm": 0.6725971102714539, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.1611, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007029226785053644, | |
| "grad_norm": 0.6665031313896179, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.1477, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007399186089530152, | |
| "grad_norm": 0.6256259679794312, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.1298, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007399186089530152, | |
| "eval_loss": 2.2063357830047607, | |
| "eval_runtime": 142.6573, | |
| "eval_samples_per_second": 7.984, | |
| "eval_steps_per_second": 3.996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00776914539400666, | |
| "grad_norm": 0.712395966053009, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.1747, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008139104698483167, | |
| "grad_norm": 0.6240229606628418, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.9213, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008509064002959674, | |
| "grad_norm": 0.9065861701965332, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.2728, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008879023307436182, | |
| "grad_norm": 0.587542712688446, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 2.0188, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00924898261191269, | |
| "grad_norm": 0.7155807018280029, | |
| "learning_rate": 0.0, | |
| "loss": 2.307, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00924898261191269, | |
| "eval_loss": 2.195878505706787, | |
| "eval_runtime": 142.3012, | |
| "eval_samples_per_second": 8.004, | |
| "eval_steps_per_second": 4.006, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2050121662464000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |