| { | |
| "best_metric": 1.4766654968261719, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07929428089999009, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015858856179998017, | |
| "grad_norm": 17.070512771606445, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015858856179998017, | |
| "eval_loss": 5.90218448638916, | |
| "eval_runtime": 3.3307, | |
| "eval_samples_per_second": 15.012, | |
| "eval_steps_per_second": 3.903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031717712359996034, | |
| "grad_norm": 19.348953247070312, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7538, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004757656853999405, | |
| "grad_norm": 13.42625617980957, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.2714, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006343542471999207, | |
| "grad_norm": 2.2228305339813232, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0772, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007929428089999009, | |
| "grad_norm": 1.0048638582229614, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00951531370799881, | |
| "grad_norm": 1.0425435304641724, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.876, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011101199325998613, | |
| "grad_norm": 1.0215988159179688, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.8797, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012687084943998414, | |
| "grad_norm": 0.8580153584480286, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8136, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014272970561998216, | |
| "grad_norm": 0.6667729616165161, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7673, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015858856179998018, | |
| "grad_norm": 0.701425313949585, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7358, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01744474179799782, | |
| "grad_norm": 0.7387133836746216, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.6905, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01903062741599762, | |
| "grad_norm": 1.0632332563400269, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.7093, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020616513033997422, | |
| "grad_norm": 0.7202914953231812, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6132, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022202398651997225, | |
| "grad_norm": 0.7657666206359863, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6596, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.023788284269997028, | |
| "grad_norm": 0.6034996509552002, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.668, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025374169887996827, | |
| "grad_norm": 0.5026582479476929, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.7384, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02696005550599663, | |
| "grad_norm": 0.42584991455078125, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.6253, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028545941123996433, | |
| "grad_norm": 0.4252493381500244, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.6889, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030131826741996232, | |
| "grad_norm": 0.4458921551704407, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.6895, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.031717712359996035, | |
| "grad_norm": 0.4872418940067291, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.6197, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.033303597977995834, | |
| "grad_norm": 0.4587940573692322, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.622, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03488948359599564, | |
| "grad_norm": 0.48748770356178284, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.6673, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03647536921399544, | |
| "grad_norm": 0.5389514565467834, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.6634, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03806125483199524, | |
| "grad_norm": 0.6838032603263855, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.6041, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.039647140449995046, | |
| "grad_norm": 1.1133662462234497, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.5255, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.039647140449995046, | |
| "eval_loss": 1.4964512586593628, | |
| "eval_runtime": 3.4121, | |
| "eval_samples_per_second": 14.654, | |
| "eval_steps_per_second": 3.81, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.041233026067994845, | |
| "grad_norm": 0.40284931659698486, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.5774, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.042818911685994644, | |
| "grad_norm": 0.38245460391044617, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.6014, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04440479730399445, | |
| "grad_norm": 0.4388914108276367, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.597, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04599068292199425, | |
| "grad_norm": 0.42553648352622986, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.5929, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.047576568539994056, | |
| "grad_norm": 0.4502233862876892, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.6029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.049162454157993855, | |
| "grad_norm": 0.4477775990962982, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.6697, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.050748339775993655, | |
| "grad_norm": 0.47372493147850037, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.6562, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05233422539399346, | |
| "grad_norm": 0.46918997168540955, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.6332, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05392011101199326, | |
| "grad_norm": 0.4643358290195465, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.6086, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05550599662999306, | |
| "grad_norm": 0.4862658679485321, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.6013, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.057091882247992866, | |
| "grad_norm": 0.506260871887207, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.6465, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.058677767865992665, | |
| "grad_norm": 0.594947099685669, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.5712, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.060263653483992465, | |
| "grad_norm": 0.5527778267860413, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.4738, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06184953910199227, | |
| "grad_norm": 0.33043065667152405, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.5579, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06343542471999207, | |
| "grad_norm": 0.374056875705719, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.5702, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06502131033799187, | |
| "grad_norm": 0.36577755212783813, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.6545, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06660719595599167, | |
| "grad_norm": 0.33573096990585327, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.6232, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06819308157399148, | |
| "grad_norm": 0.364795058965683, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.5976, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06977896719199128, | |
| "grad_norm": 0.40120968222618103, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.6431, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07136485280999108, | |
| "grad_norm": 0.4092036783695221, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.6469, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07295073842799088, | |
| "grad_norm": 0.420834481716156, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.6295, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07453662404599068, | |
| "grad_norm": 0.4343208372592926, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.6405, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07612250966399048, | |
| "grad_norm": 0.4775432050228119, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.6059, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07770839528199029, | |
| "grad_norm": 0.5238398313522339, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.5927, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07929428089999009, | |
| "grad_norm": 0.7994441390037537, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07929428089999009, | |
| "eval_loss": 1.4766654968261719, | |
| "eval_runtime": 3.4247, | |
| "eval_samples_per_second": 14.6, | |
| "eval_steps_per_second": 3.796, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |