| { | |
| "best_metric": 11.023486137390137, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.006735367414292449, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000269414696571698, | |
| "grad_norm": 16.136512756347656, | |
| "learning_rate": 5e-05, | |
| "loss": 355.9254, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000269414696571698, | |
| "eval_loss": 11.11539077758789, | |
| "eval_runtime": 0.1036, | |
| "eval_samples_per_second": 482.852, | |
| "eval_steps_per_second": 125.542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000538829393143396, | |
| "grad_norm": 14.730152130126953, | |
| "learning_rate": 0.0001, | |
| "loss": 355.9424, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008082440897150939, | |
| "grad_norm": 13.098028182983398, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 355.703, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001077658786286792, | |
| "grad_norm": 13.016119003295898, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 355.6308, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00134707348285849, | |
| "grad_norm": 13.283241271972656, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 355.3417, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016164881794301878, | |
| "grad_norm": 13.466944694519043, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 355.0724, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001885902876001886, | |
| "grad_norm": 13.942754745483398, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 354.8557, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002155317572573584, | |
| "grad_norm": 14.429150581359863, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 354.657, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024247322691452818, | |
| "grad_norm": 14.377021789550781, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 354.3762, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00269414696571698, | |
| "grad_norm": 14.623111724853516, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 354.1872, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002963561662288678, | |
| "grad_norm": 14.844232559204102, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 354.0316, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0032329763588603757, | |
| "grad_norm": 15.304190635681152, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 353.7277, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003502391055432074, | |
| "grad_norm": 14.90652084350586, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 353.8779, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003771805752003772, | |
| "grad_norm": 16.498310089111328, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 353.7867, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00404122044857547, | |
| "grad_norm": 15.048145294189453, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 353.7025, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004310635145147168, | |
| "grad_norm": 14.494032859802246, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 353.4385, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004580049841718866, | |
| "grad_norm": 14.669879913330078, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 353.3502, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0048494645382905635, | |
| "grad_norm": 14.94941520690918, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 353.2106, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005118879234862261, | |
| "grad_norm": 15.098630905151367, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 353.1047, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00538829393143396, | |
| "grad_norm": 15.154767990112305, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 353.0648, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005657708628005658, | |
| "grad_norm": 15.328968048095703, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 352.9379, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005927123324577356, | |
| "grad_norm": 15.579107284545898, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 352.8666, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0061965380211490536, | |
| "grad_norm": 16.05657196044922, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 352.5973, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006465952717720751, | |
| "grad_norm": 16.275468826293945, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 352.5928, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006735367414292449, | |
| "grad_norm": 15.637100219726562, | |
| "learning_rate": 1e-05, | |
| "loss": 352.7601, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006735367414292449, | |
| "eval_loss": 11.023486137390137, | |
| "eval_runtime": 0.1033, | |
| "eval_samples_per_second": 484.26, | |
| "eval_steps_per_second": 125.908, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 19204433510400.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |