| { | |
| "best_metric": 11.087183952331543, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0018803000958953048, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.52120038358122e-05, | |
| "grad_norm": 0.36072683334350586, | |
| "learning_rate": 2e-05, | |
| "loss": 44.346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.52120038358122e-05, | |
| "eval_loss": 11.091547012329102, | |
| "eval_runtime": 33.385, | |
| "eval_samples_per_second": 167.71, | |
| "eval_steps_per_second": 83.87, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001504240076716244, | |
| "grad_norm": 0.4462735056877136, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3785, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00022563601150743658, | |
| "grad_norm": 0.4180746078491211, | |
| "learning_rate": 6e-05, | |
| "loss": 44.3626, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003008480153432488, | |
| "grad_norm": 0.47067514061927795, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3849, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00037606001917906096, | |
| "grad_norm": 0.42163482308387756, | |
| "learning_rate": 0.0001, | |
| "loss": 44.34, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00037606001917906096, | |
| "eval_loss": 11.091147422790527, | |
| "eval_runtime": 33.0735, | |
| "eval_samples_per_second": 169.29, | |
| "eval_steps_per_second": 84.66, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00045127202301487317, | |
| "grad_norm": 0.4386148154735565, | |
| "learning_rate": 0.00012, | |
| "loss": 44.3591, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005264840268506853, | |
| "grad_norm": 0.44034865498542786, | |
| "learning_rate": 0.00014, | |
| "loss": 44.3773, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006016960306864976, | |
| "grad_norm": 0.4439011216163635, | |
| "learning_rate": 0.00016, | |
| "loss": 44.3517, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006769080345223098, | |
| "grad_norm": 0.4867452383041382, | |
| "learning_rate": 0.00018, | |
| "loss": 44.3733, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007521200383581219, | |
| "grad_norm": 0.447224885225296, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007521200383581219, | |
| "eval_loss": 11.089957237243652, | |
| "eval_runtime": 32.0032, | |
| "eval_samples_per_second": 174.951, | |
| "eval_steps_per_second": 87.491, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008273320421939342, | |
| "grad_norm": 0.45152103900909424, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.3847, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0009025440460297463, | |
| "grad_norm": 0.44679462909698486, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.3532, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009777560498655585, | |
| "grad_norm": 0.4625109136104584, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.3487, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0010529680537013707, | |
| "grad_norm": 0.4054245948791504, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.3355, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001128180057537183, | |
| "grad_norm": 0.5683387517929077, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.3519, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001128180057537183, | |
| "eval_loss": 11.088563919067383, | |
| "eval_runtime": 31.7762, | |
| "eval_samples_per_second": 176.201, | |
| "eval_steps_per_second": 88.116, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012033920613729952, | |
| "grad_norm": 0.4704050123691559, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.3352, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012786040652088073, | |
| "grad_norm": 0.5483019948005676, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.3667, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0013538160690446195, | |
| "grad_norm": 0.45486849546432495, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.332, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0014290280728804317, | |
| "grad_norm": 0.5051968097686768, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.3673, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0015042400767162438, | |
| "grad_norm": 0.5607341527938843, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.3484, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015042400767162438, | |
| "eval_loss": 11.087431907653809, | |
| "eval_runtime": 31.7877, | |
| "eval_samples_per_second": 176.138, | |
| "eval_steps_per_second": 88.084, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015794520805520562, | |
| "grad_norm": 0.43907225131988525, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 44.3608, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0016546640843878684, | |
| "grad_norm": 0.4424779713153839, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 44.3532, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0017298760882236805, | |
| "grad_norm": 0.42851531505584717, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 44.3578, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0018050880920594927, | |
| "grad_norm": 0.46363070607185364, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 44.3265, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0018803000958953048, | |
| "grad_norm": 0.48294517397880554, | |
| "learning_rate": 0.0, | |
| "loss": 44.3581, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018803000958953048, | |
| "eval_loss": 11.087183952331543, | |
| "eval_runtime": 31.7918, | |
| "eval_samples_per_second": 176.115, | |
| "eval_steps_per_second": 88.073, | |
| "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": 19238092800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |