{ "best_metric": 1.4441759586334229, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.00039357682619647357, "eval_steps": 5, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.574307304785894e-05, "grad_norm": 8.58763599395752, "learning_rate": 2e-05, "loss": 9.7472, "step": 1 }, { "epoch": 1.574307304785894e-05, "eval_loss": 2.4229915142059326, "eval_runtime": 2890.0247, "eval_samples_per_second": 9.255, "eval_steps_per_second": 4.627, "step": 1 }, { "epoch": 3.148614609571788e-05, "grad_norm": 9.369941711425781, "learning_rate": 4e-05, "loss": 9.131, "step": 2 }, { "epoch": 4.7229219143576825e-05, "grad_norm": 12.158150672912598, "learning_rate": 6e-05, "loss": 11.3888, "step": 3 }, { "epoch": 6.297229219143577e-05, "grad_norm": 6.522123336791992, "learning_rate": 8e-05, "loss": 8.1658, "step": 4 }, { "epoch": 7.871536523929471e-05, "grad_norm": 13.439884185791016, "learning_rate": 0.0001, "loss": 10.9821, "step": 5 }, { "epoch": 7.871536523929471e-05, "eval_loss": 2.3780176639556885, "eval_runtime": 2899.413, "eval_samples_per_second": 9.225, "eval_steps_per_second": 4.612, "step": 5 }, { "epoch": 9.445843828715365e-05, "grad_norm": 11.283020973205566, "learning_rate": 0.00012, "loss": 13.785, "step": 6 }, { "epoch": 0.00011020151133501259, "grad_norm": 10.101272583007812, "learning_rate": 0.00014, "loss": 9.2138, "step": 7 }, { "epoch": 0.00012594458438287153, "grad_norm": 9.228546142578125, "learning_rate": 0.00016, "loss": 8.7801, "step": 8 }, { "epoch": 0.00014168765743073047, "grad_norm": 13.293570518493652, "learning_rate": 0.00018, "loss": 10.5249, "step": 9 }, { "epoch": 0.00015743073047858942, "grad_norm": 8.277302742004395, "learning_rate": 0.0002, "loss": 6.2849, "step": 10 }, { "epoch": 0.00015743073047858942, "eval_loss": 1.8342094421386719, "eval_runtime": 2885.2071, "eval_samples_per_second": 9.27, "eval_steps_per_second": 4.635, "step": 10 }, { "epoch": 0.00017317380352644836, "grad_norm": 7.459911823272705, "learning_rate": 0.00019781476007338058, "loss": 5.8751, "step": 11 }, { "epoch": 0.0001889168765743073, "grad_norm": 6.928237438201904, "learning_rate": 0.0001913545457642601, "loss": 5.749, "step": 12 }, { "epoch": 0.00020465994962216624, "grad_norm": 7.434017181396484, "learning_rate": 0.00018090169943749476, "loss": 6.5052, "step": 13 }, { "epoch": 0.00022040302267002518, "grad_norm": 10.980093002319336, "learning_rate": 0.00016691306063588583, "loss": 8.7775, "step": 14 }, { "epoch": 0.00023614609571788412, "grad_norm": 5.352643966674805, "learning_rate": 0.00015000000000000001, "loss": 3.7138, "step": 15 }, { "epoch": 0.00023614609571788412, "eval_loss": 1.5234931707382202, "eval_runtime": 2884.8217, "eval_samples_per_second": 9.271, "eval_steps_per_second": 4.636, "step": 15 }, { "epoch": 0.00025188916876574307, "grad_norm": 7.328005313873291, "learning_rate": 0.00013090169943749476, "loss": 6.5667, "step": 16 }, { "epoch": 0.00026763224181360204, "grad_norm": 7.550777912139893, "learning_rate": 0.00011045284632676536, "loss": 5.6812, "step": 17 }, { "epoch": 0.00028337531486146095, "grad_norm": 6.579277038574219, "learning_rate": 8.954715367323468e-05, "loss": 5.7069, "step": 18 }, { "epoch": 0.0002991183879093199, "grad_norm": 7.71389102935791, "learning_rate": 6.909830056250527e-05, "loss": 7.9642, "step": 19 }, { "epoch": 0.00031486146095717883, "grad_norm": 4.719141483306885, "learning_rate": 5.000000000000002e-05, "loss": 5.1321, "step": 20 }, { "epoch": 0.00031486146095717883, "eval_loss": 1.4616883993148804, "eval_runtime": 2912.6548, "eval_samples_per_second": 9.183, "eval_steps_per_second": 4.591, "step": 20 }, { "epoch": 0.0003306045340050378, "grad_norm": 6.7112016677856445, "learning_rate": 3.308693936411421e-05, "loss": 4.0752, "step": 21 }, { "epoch": 0.0003463476070528967, "grad_norm": 5.199258327484131, "learning_rate": 1.9098300562505266e-05, "loss": 4.6156, "step": 22 }, { "epoch": 0.0003620906801007557, "grad_norm": 9.658928871154785, "learning_rate": 8.645454235739903e-06, "loss": 9.0947, "step": 23 }, { "epoch": 0.0003778337531486146, "grad_norm": 5.810834884643555, "learning_rate": 2.1852399266194314e-06, "loss": 3.6453, "step": 24 }, { "epoch": 0.00039357682619647357, "grad_norm": 5.152379035949707, "learning_rate": 0.0, "loss": 4.1136, "step": 25 }, { "epoch": 0.00039357682619647357, "eval_loss": 1.4441759586334229, "eval_runtime": 2886.351, "eval_samples_per_second": 9.266, "eval_steps_per_second": 4.633, "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": 3075143815397376.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }