| { | |
| "best_metric": 1.1001967191696167, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01282051282051282, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005128205128205128, | |
| "grad_norm": 83.3856430053711, | |
| "learning_rate": 2e-05, | |
| "loss": 18.1214, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005128205128205128, | |
| "eval_loss": 3.848789930343628, | |
| "eval_runtime": 163.5876, | |
| "eval_samples_per_second": 5.025, | |
| "eval_steps_per_second": 2.512, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010256410256410256, | |
| "grad_norm": 81.46775817871094, | |
| "learning_rate": 4e-05, | |
| "loss": 16.6351, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015384615384615385, | |
| "grad_norm": 43.15898132324219, | |
| "learning_rate": 6e-05, | |
| "loss": 14.1424, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020512820512820513, | |
| "grad_norm": 55.812538146972656, | |
| "learning_rate": 8e-05, | |
| "loss": 14.6783, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002564102564102564, | |
| "grad_norm": 60.90127182006836, | |
| "learning_rate": 0.0001, | |
| "loss": 12.808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002564102564102564, | |
| "eval_loss": 3.2364771366119385, | |
| "eval_runtime": 162.4584, | |
| "eval_samples_per_second": 5.06, | |
| "eval_steps_per_second": 2.53, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003076923076923077, | |
| "grad_norm": 56.42252731323242, | |
| "learning_rate": 0.00012, | |
| "loss": 11.6162, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035897435897435897, | |
| "grad_norm": 57.55208206176758, | |
| "learning_rate": 0.00014, | |
| "loss": 15.2143, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0041025641025641026, | |
| "grad_norm": 51.99382400512695, | |
| "learning_rate": 0.00016, | |
| "loss": 8.6745, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004615384615384616, | |
| "grad_norm": 45.00162887573242, | |
| "learning_rate": 0.00018, | |
| "loss": 9.3495, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005128205128205128, | |
| "grad_norm": 67.10367584228516, | |
| "learning_rate": 0.0002, | |
| "loss": 9.9398, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005128205128205128, | |
| "eval_loss": 1.6150894165039062, | |
| "eval_runtime": 162.6046, | |
| "eval_samples_per_second": 5.055, | |
| "eval_steps_per_second": 2.528, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0056410256410256415, | |
| "grad_norm": 33.656070709228516, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.6186, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006153846153846154, | |
| "grad_norm": 40.63444900512695, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.8601, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006666666666666667, | |
| "grad_norm": 60.84493637084961, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 7.1667, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0071794871794871795, | |
| "grad_norm": 55.72742462158203, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 6.83, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007692307692307693, | |
| "grad_norm": 64.9698715209961, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.7428, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007692307692307693, | |
| "eval_loss": 1.326399326324463, | |
| "eval_runtime": 160.0094, | |
| "eval_samples_per_second": 5.137, | |
| "eval_steps_per_second": 2.569, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008205128205128205, | |
| "grad_norm": 44.965904235839844, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.7771, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008717948717948718, | |
| "grad_norm": 49.172630310058594, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 5.66, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009230769230769232, | |
| "grad_norm": 55.49378967285156, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 6.7375, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009743589743589744, | |
| "grad_norm": 29.15483283996582, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 4.1762, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010256410256410256, | |
| "grad_norm": 23.95218276977539, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.9373, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010256410256410256, | |
| "eval_loss": 1.1402697563171387, | |
| "eval_runtime": 169.094, | |
| "eval_samples_per_second": 4.861, | |
| "eval_steps_per_second": 2.431, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010769230769230769, | |
| "grad_norm": 32.67024230957031, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.6896, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011282051282051283, | |
| "grad_norm": 28.793724060058594, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 5.4251, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011794871794871795, | |
| "grad_norm": 52.28025817871094, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 4.2507, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012307692307692308, | |
| "grad_norm": 34.58713912963867, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 5.2803, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01282051282051282, | |
| "grad_norm": 41.41437911987305, | |
| "learning_rate": 0.0, | |
| "loss": 5.446, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01282051282051282, | |
| "eval_loss": 1.1001967191696167, | |
| "eval_runtime": 159.3672, | |
| "eval_samples_per_second": 5.158, | |
| "eval_steps_per_second": 2.579, | |
| "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": 4381674464870400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |