| { | |
| "best_metric": 1.115118145942688, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.002863278453829635, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014316392269148176, | |
| "grad_norm": 7.716362476348877, | |
| "learning_rate": 2e-05, | |
| "loss": 17.7316, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014316392269148176, | |
| "eval_loss": 1.1126166582107544, | |
| "eval_runtime": 446.8987, | |
| "eval_samples_per_second": 6.583, | |
| "eval_steps_per_second": 3.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002863278453829635, | |
| "grad_norm": 33.65132141113281, | |
| "learning_rate": 4e-05, | |
| "loss": 17.57, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00042949176807444524, | |
| "grad_norm": 8.676011085510254, | |
| "learning_rate": 6e-05, | |
| "loss": 19.574, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000572655690765927, | |
| "grad_norm": 10.423348426818848, | |
| "learning_rate": 8e-05, | |
| "loss": 20.9523, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007158196134574087, | |
| "grad_norm": 6.775657653808594, | |
| "learning_rate": 0.0001, | |
| "loss": 14.5383, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007158196134574087, | |
| "eval_loss": 1.1102972030639648, | |
| "eval_runtime": 445.2813, | |
| "eval_samples_per_second": 6.607, | |
| "eval_steps_per_second": 3.304, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008589835361488905, | |
| "grad_norm": 13.472702026367188, | |
| "learning_rate": 0.00012, | |
| "loss": 13.4677, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010021474588403723, | |
| "grad_norm": 9.272212028503418, | |
| "learning_rate": 0.00014, | |
| "loss": 14.8927, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001145311381531854, | |
| "grad_norm": 7.397126197814941, | |
| "learning_rate": 0.00016, | |
| "loss": 13.2153, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012884753042233356, | |
| "grad_norm": 18.572072982788086, | |
| "learning_rate": 0.00018, | |
| "loss": 10.533, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014316392269148174, | |
| "grad_norm": 8.253515243530273, | |
| "learning_rate": 0.0002, | |
| "loss": 13.0524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014316392269148174, | |
| "eval_loss": 1.115118145942688, | |
| "eval_runtime": 446.5087, | |
| "eval_samples_per_second": 6.589, | |
| "eval_steps_per_second": 3.294, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015748031496062992, | |
| "grad_norm": 13.856171607971191, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 15.7511, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001717967072297781, | |
| "grad_norm": 12.846494674682617, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 12.6877, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018611309949892628, | |
| "grad_norm": 18.605619430541992, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 10.9035, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0020042949176807445, | |
| "grad_norm": 16.605167388916016, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 17.4268, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0021474588403722263, | |
| "grad_norm": 9.639287948608398, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 9.6034, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0021474588403722263, | |
| "eval_loss": 1.1374800205230713, | |
| "eval_runtime": 445.0599, | |
| "eval_samples_per_second": 6.61, | |
| "eval_steps_per_second": 3.305, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002290622763063708, | |
| "grad_norm": 14.398244857788086, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.8691, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00243378668575519, | |
| "grad_norm": 12.246084213256836, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 9.336, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0025769506084466712, | |
| "grad_norm": 11.735007286071777, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 11.1932, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002720114531138153, | |
| "grad_norm": 9.10404109954834, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 10.207, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002863278453829635, | |
| "grad_norm": 12.01398754119873, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 11.9392, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002863278453829635, | |
| "eval_loss": 1.1486986875534058, | |
| "eval_runtime": 449.1578, | |
| "eval_samples_per_second": 6.55, | |
| "eval_steps_per_second": 3.275, | |
| "step": 20 | |
| } | |
| ], | |
| "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": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2753438762926080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |