| { | |
| "best_metric": 0.20686934888362885, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.013448090371167294, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005379236148466917, | |
| "grad_norm": 5.665757179260254, | |
| "learning_rate": 4e-05, | |
| "loss": 14.1149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005379236148466917, | |
| "eval_loss": 14.399935722351074, | |
| "eval_runtime": 480.3434, | |
| "eval_samples_per_second": 1.63, | |
| "eval_steps_per_second": 0.816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010758472296933835, | |
| "grad_norm": 6.0138421058654785, | |
| "learning_rate": 8e-05, | |
| "loss": 14.3315, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016137708445400753, | |
| "grad_norm": 5.68032169342041, | |
| "learning_rate": 0.00012, | |
| "loss": 14.4942, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002151694459386767, | |
| "grad_norm": 7.876317977905273, | |
| "learning_rate": 0.00016, | |
| "loss": 14.411, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0026896180742334587, | |
| "grad_norm": 8.77420425415039, | |
| "learning_rate": 0.0002, | |
| "loss": 14.3799, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032275416890801506, | |
| "grad_norm": 8.047574996948242, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 11.1861, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037654653039268424, | |
| "grad_norm": 8.94501781463623, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 9.831, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004303388918773534, | |
| "grad_norm": 9.489190101623535, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 7.9405, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004841312533620226, | |
| "grad_norm": 13.784337997436523, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 6.1143, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0053792361484669175, | |
| "grad_norm": 9.499981880187988, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 4.2967, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005917159763313609, | |
| "grad_norm": 9.118963241577148, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 2.7132, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006455083378160301, | |
| "grad_norm": 9.794291496276855, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 1.1106, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006993006993006993, | |
| "grad_norm": 5.810440540313721, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 1.0159, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007530930607853685, | |
| "grad_norm": 3.0343141555786133, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.3357, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008068854222700376, | |
| "grad_norm": 4.984272480010986, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.3256, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008606777837547068, | |
| "grad_norm": 8.477812767028809, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.4395, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00914470145239376, | |
| "grad_norm": 7.445779323577881, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.5309, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009682625067240451, | |
| "grad_norm": 5.090211391448975, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.2973, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010220548682087143, | |
| "grad_norm": 7.343393802642822, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.4837, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010758472296933835, | |
| "grad_norm": 2.520585536956787, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.1629, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011296395911780527, | |
| "grad_norm": 3.9465153217315674, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.1549, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011834319526627219, | |
| "grad_norm": 3.0971474647521973, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.2236, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01237224314147391, | |
| "grad_norm": 6.442452430725098, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.3162, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012910166756320602, | |
| "grad_norm": 4.07744026184082, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.1577, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013448090371167294, | |
| "grad_norm": 1.9578357934951782, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.1762, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013448090371167294, | |
| "eval_loss": 0.20686934888362885, | |
| "eval_runtime": 482.315, | |
| "eval_samples_per_second": 1.623, | |
| "eval_steps_per_second": 0.813, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 6.91090822791168e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |