| { | |
| "best_metric": 1.3710354566574097, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.005342451116572284, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021369804466289135, | |
| "grad_norm": 0.7776347994804382, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6473, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021369804466289135, | |
| "eval_loss": 1.8470208644866943, | |
| "eval_runtime": 275.941, | |
| "eval_samples_per_second": 7.143, | |
| "eval_steps_per_second": 3.573, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004273960893257827, | |
| "grad_norm": 0.9071603417396545, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8389, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000641094133988674, | |
| "grad_norm": 0.9546608328819275, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8896, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008547921786515654, | |
| "grad_norm": 0.8853360414505005, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9434, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010684902233144566, | |
| "grad_norm": 0.9135332703590393, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8046, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010684902233144566, | |
| "eval_loss": 1.8170785903930664, | |
| "eval_runtime": 274.4552, | |
| "eval_samples_per_second": 7.182, | |
| "eval_steps_per_second": 3.593, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001282188267977348, | |
| "grad_norm": 0.9748033881187439, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8187, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014958863126402393, | |
| "grad_norm": 1.0681061744689941, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7537, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017095843573031308, | |
| "grad_norm": 0.9694352746009827, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7455, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001923282401966022, | |
| "grad_norm": 0.8963027596473694, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6952, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021369804466289132, | |
| "grad_norm": 0.9051772952079773, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6015, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021369804466289132, | |
| "eval_loss": 1.5659117698669434, | |
| "eval_runtime": 275.0012, | |
| "eval_samples_per_second": 7.167, | |
| "eval_steps_per_second": 3.585, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023506784912918047, | |
| "grad_norm": 0.842316746711731, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.4946, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002564376535954696, | |
| "grad_norm": 0.9651074409484863, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.5619, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002778074580617587, | |
| "grad_norm": 0.9838403463363647, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.6461, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0029917726252804786, | |
| "grad_norm": 0.9522503614425659, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.3381, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00320547066994337, | |
| "grad_norm": 1.0169678926467896, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.321, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00320547066994337, | |
| "eval_loss": 1.4373729228973389, | |
| "eval_runtime": 275.0162, | |
| "eval_samples_per_second": 7.167, | |
| "eval_steps_per_second": 3.585, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0034191687146062615, | |
| "grad_norm": 1.0345380306243896, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.3766, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0036328667592691525, | |
| "grad_norm": 0.920183002948761, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.5197, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003846564803932044, | |
| "grad_norm": 1.0014177560806274, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.5562, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004060262848594935, | |
| "grad_norm": 0.8492229580879211, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.2455, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0042739608932578265, | |
| "grad_norm": 0.8897610902786255, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0042739608932578265, | |
| "eval_loss": 1.3795337677001953, | |
| "eval_runtime": 277.9232, | |
| "eval_samples_per_second": 7.092, | |
| "eval_steps_per_second": 3.548, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004487658937920718, | |
| "grad_norm": 0.8185605406761169, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.2575, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004701356982583609, | |
| "grad_norm": 0.8754450678825378, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.3122, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004915055027246501, | |
| "grad_norm": 0.9416663646697998, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.4327, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005128753071909392, | |
| "grad_norm": 0.9618386626243591, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.2672, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005342451116572284, | |
| "grad_norm": 0.8629248738288879, | |
| "learning_rate": 0.0, | |
| "loss": 1.3367, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005342451116572284, | |
| "eval_loss": 1.3710354566574097, | |
| "eval_runtime": 274.6611, | |
| "eval_samples_per_second": 7.176, | |
| "eval_steps_per_second": 3.59, | |
| "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": 4071832839782400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |