| { | |
| "best_metric": 11.04233169555664, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.051759834368530024, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002070393374741201, | |
| "grad_norm": 6.086023807525635, | |
| "learning_rate": 5e-05, | |
| "loss": 177.6369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002070393374741201, | |
| "eval_loss": 11.103808403015137, | |
| "eval_runtime": 0.5591, | |
| "eval_samples_per_second": 89.431, | |
| "eval_steps_per_second": 23.252, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004140786749482402, | |
| "grad_norm": 4.320464134216309, | |
| "learning_rate": 0.0001, | |
| "loss": 177.827, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006211180124223602, | |
| "grad_norm": 3.7203009128570557, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 177.7243, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008281573498964804, | |
| "grad_norm": 3.6285226345062256, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 177.6228, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010351966873706004, | |
| "grad_norm": 3.561692237854004, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 177.7155, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012422360248447204, | |
| "grad_norm": 3.790656089782715, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 177.6258, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014492753623188406, | |
| "grad_norm": 3.853480339050293, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 177.5562, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016563146997929608, | |
| "grad_norm": 4.005135536193848, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 177.6082, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018633540372670808, | |
| "grad_norm": 4.643294334411621, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 177.568, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020703933747412008, | |
| "grad_norm": 5.119444370269775, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 177.4234, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022774327122153208, | |
| "grad_norm": 5.751838207244873, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 177.2939, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024844720496894408, | |
| "grad_norm": 7.102801322937012, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 177.3568, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026915113871635612, | |
| "grad_norm": 8.331995964050293, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 176.9811, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 5.497199535369873, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 177.014, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.031055900621118012, | |
| "grad_norm": 4.23492956161499, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 177.209, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033126293995859216, | |
| "grad_norm": 4.067819595336914, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 177.2137, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.035196687370600416, | |
| "grad_norm": 3.9193811416625977, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 177.1131, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.037267080745341616, | |
| "grad_norm": 3.8284318447113037, | |
| "learning_rate": 7.75e-05, | |
| "loss": 177.1983, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.039337474120082816, | |
| "grad_norm": 4.166711807250977, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 177.0419, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.041407867494824016, | |
| "grad_norm": 4.264215469360352, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 177.0668, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043478260869565216, | |
| "grad_norm": 4.3174943923950195, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 177.1095, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.045548654244306416, | |
| "grad_norm": 5.148275375366211, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 177.0244, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 5.267536640167236, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 176.8738, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.049689440993788817, | |
| "grad_norm": 6.1932902336120605, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 176.6368, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.051759834368530024, | |
| "grad_norm": 8.919533729553223, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 176.5659, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.051759834368530024, | |
| "eval_loss": 11.04233169555664, | |
| "eval_runtime": 0.0849, | |
| "eval_samples_per_second": 588.797, | |
| "eval_steps_per_second": 153.087, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 19055561932800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |