| { | |
| "best_metric": 2.3594415187835693, | |
| "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": 1.5243043899536133, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2261, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003699593044765076, | |
| "eval_loss": 3.100375175476074, | |
| "eval_runtime": 208.6635, | |
| "eval_samples_per_second": 5.459, | |
| "eval_steps_per_second": 2.732, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007399186089530152, | |
| "grad_norm": 1.4240329265594482, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9361, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011098779134295228, | |
| "grad_norm": 1.524584174156189, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1426, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014798372179060304, | |
| "grad_norm": 1.3952741622924805, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0211, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001849796522382538, | |
| "grad_norm": 1.4822412729263306, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0685, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001849796522382538, | |
| "eval_loss": 2.9944255352020264, | |
| "eval_runtime": 208.6838, | |
| "eval_samples_per_second": 5.458, | |
| "eval_steps_per_second": 2.731, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022197558268590455, | |
| "grad_norm": 1.499148964881897, | |
| "learning_rate": 0.00012, | |
| "loss": 2.7608, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002589715131335553, | |
| "grad_norm": 1.3574713468551636, | |
| "learning_rate": 0.00014, | |
| "loss": 2.8229, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029596744358120607, | |
| "grad_norm": 1.3877097368240356, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8343, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003329633740288568, | |
| "grad_norm": 1.3273413181304932, | |
| "learning_rate": 0.00018, | |
| "loss": 2.7683, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003699593044765076, | |
| "grad_norm": 1.4110333919525146, | |
| "learning_rate": 0.0002, | |
| "loss": 2.695, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003699593044765076, | |
| "eval_loss": 2.584866523742676, | |
| "eval_runtime": 208.6062, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 2.732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004069552349241583, | |
| "grad_norm": 1.2998981475830078, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.3709, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004439511653718091, | |
| "grad_norm": 1.5440006256103516, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.4366, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004809470958194599, | |
| "grad_norm": 1.5911710262298584, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.3136, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005179430262671106, | |
| "grad_norm": 1.6979089975357056, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.5733, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005549389567147614, | |
| "grad_norm": 1.5529507398605347, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.4157, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005549389567147614, | |
| "eval_loss": 2.445035219192505, | |
| "eval_runtime": 209.4732, | |
| "eval_samples_per_second": 5.437, | |
| "eval_steps_per_second": 2.721, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0059193488716241215, | |
| "grad_norm": 1.7018779516220093, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.5408, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006289308176100629, | |
| "grad_norm": 1.5621485710144043, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.5183, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006659267480577136, | |
| "grad_norm": 1.6603797674179077, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.4762, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007029226785053644, | |
| "grad_norm": 1.3905707597732544, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.348, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007399186089530152, | |
| "grad_norm": 1.3540409803390503, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.2931, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007399186089530152, | |
| "eval_loss": 2.3715481758117676, | |
| "eval_runtime": 209.4929, | |
| "eval_samples_per_second": 5.437, | |
| "eval_steps_per_second": 2.721, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00776914539400666, | |
| "grad_norm": 1.4555045366287231, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.6001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008139104698483167, | |
| "grad_norm": 1.2381263971328735, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.0214, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008509064002959674, | |
| "grad_norm": 1.2211942672729492, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.4515, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008879023307436182, | |
| "grad_norm": 1.1542309522628784, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 2.1478, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00924898261191269, | |
| "grad_norm": 1.333479404449463, | |
| "learning_rate": 0.0, | |
| "loss": 2.463, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00924898261191269, | |
| "eval_loss": 2.3594415187835693, | |
| "eval_runtime": 209.4161, | |
| "eval_samples_per_second": 5.439, | |
| "eval_steps_per_second": 2.722, | |
| "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": 1250243326771200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |