| { | |
| "best_metric": 0.9151530265808105, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0005423993577991604, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.1695974311966415e-05, | |
| "grad_norm": 4.097023963928223, | |
| "learning_rate": 2e-05, | |
| "loss": 5.8127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.1695974311966415e-05, | |
| "eval_loss": 1.6199195384979248, | |
| "eval_runtime": 1737.2804, | |
| "eval_samples_per_second": 11.171, | |
| "eval_steps_per_second": 5.586, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.339194862393283e-05, | |
| "grad_norm": 4.3636322021484375, | |
| "learning_rate": 4e-05, | |
| "loss": 6.1582, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.508792293589925e-05, | |
| "grad_norm": 4.94938325881958, | |
| "learning_rate": 6e-05, | |
| "loss": 6.7703, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.678389724786566e-05, | |
| "grad_norm": 5.043676853179932, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3356, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00010847987155983208, | |
| "grad_norm": 5.224648952484131, | |
| "learning_rate": 0.0001, | |
| "loss": 6.5504, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010847987155983208, | |
| "eval_loss": 1.5288199186325073, | |
| "eval_runtime": 1712.4871, | |
| "eval_samples_per_second": 11.333, | |
| "eval_steps_per_second": 5.667, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001301758458717985, | |
| "grad_norm": 4.700260162353516, | |
| "learning_rate": 0.00012, | |
| "loss": 5.732, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001518718201837649, | |
| "grad_norm": 5.391965866088867, | |
| "learning_rate": 0.00014, | |
| "loss": 6.2198, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00017356779449573132, | |
| "grad_norm": 4.917740821838379, | |
| "learning_rate": 0.00016, | |
| "loss": 5.3235, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00019526376880769772, | |
| "grad_norm": 5.1631598472595215, | |
| "learning_rate": 0.00018, | |
| "loss": 5.8306, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00021695974311966416, | |
| "grad_norm": 3.9763195514678955, | |
| "learning_rate": 0.0002, | |
| "loss": 5.4326, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00021695974311966416, | |
| "eval_loss": 1.2067017555236816, | |
| "eval_runtime": 1705.1446, | |
| "eval_samples_per_second": 11.381, | |
| "eval_steps_per_second": 5.691, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00023865571743163057, | |
| "grad_norm": 5.8415374755859375, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.639, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000260351691743597, | |
| "grad_norm": 4.822943210601807, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.8134, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002820476660555634, | |
| "grad_norm": 4.433187484741211, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 4.3497, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0003037436403675298, | |
| "grad_norm": 5.982097148895264, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 5.1374, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0003254396146794962, | |
| "grad_norm": 5.101588249206543, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.4414, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003254396146794962, | |
| "eval_loss": 1.0443052053451538, | |
| "eval_runtime": 1757.1215, | |
| "eval_samples_per_second": 11.045, | |
| "eval_steps_per_second": 5.523, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00034713558899146263, | |
| "grad_norm": 4.684109210968018, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.1763, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00036883156330342904, | |
| "grad_norm": 4.625067710876465, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.4839, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00039052753761539545, | |
| "grad_norm": 5.083712577819824, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.2659, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00041222351192736186, | |
| "grad_norm": 3.9180216789245605, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.9517, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0004339194862393283, | |
| "grad_norm": 3.9014394283294678, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.7442, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004339194862393283, | |
| "eval_loss": 0.9340419769287109, | |
| "eval_runtime": 1708.7785, | |
| "eval_samples_per_second": 11.357, | |
| "eval_steps_per_second": 5.679, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004556154605512947, | |
| "grad_norm": 4.069162368774414, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.6392, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00047731143486326113, | |
| "grad_norm": 4.433424472808838, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 4.2692, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0004990074091752275, | |
| "grad_norm": 4.288788318634033, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.7456, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000520703383487194, | |
| "grad_norm": 5.057470321655273, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.965, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005423993577991604, | |
| "grad_norm": 5.0678277015686035, | |
| "learning_rate": 0.0, | |
| "loss": 3.955, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005423993577991604, | |
| "eval_loss": 0.9151530265808105, | |
| "eval_runtime": 1779.2107, | |
| "eval_samples_per_second": 10.908, | |
| "eval_steps_per_second": 5.454, | |
| "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": 1632373309440000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |