| { | |
| "best_metric": 0.3771282732486725, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05730659025787966, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002292263610315186, | |
| "grad_norm": 7.770583629608154, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6697, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002292263610315186, | |
| "eval_loss": 0.6890747547149658, | |
| "eval_runtime": 55.5182, | |
| "eval_samples_per_second": 3.314, | |
| "eval_steps_per_second": 1.657, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004584527220630372, | |
| "grad_norm": 9.156136512756348, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8621, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006876790830945559, | |
| "grad_norm": 6.610903263092041, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8403, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009169054441260744, | |
| "grad_norm": 8.174342155456543, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5056, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011461318051575931, | |
| "grad_norm": 7.851437568664551, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3453, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011461318051575931, | |
| "eval_loss": 0.602993905544281, | |
| "eval_runtime": 55.377, | |
| "eval_samples_per_second": 3.323, | |
| "eval_steps_per_second": 1.661, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013753581661891117, | |
| "grad_norm": 6.013002872467041, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4657, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016045845272206302, | |
| "grad_norm": 6.81970739364624, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1724, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01833810888252149, | |
| "grad_norm": 4.467923164367676, | |
| "learning_rate": 0.00016, | |
| "loss": 1.943, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020630372492836675, | |
| "grad_norm": 5.324087142944336, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0512, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022922636103151862, | |
| "grad_norm": 5.302452564239502, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1748, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022922636103151862, | |
| "eval_loss": 0.46889933943748474, | |
| "eval_runtime": 55.0819, | |
| "eval_samples_per_second": 3.34, | |
| "eval_steps_per_second": 1.67, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02521489971346705, | |
| "grad_norm": 4.640089511871338, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.0298, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027507163323782235, | |
| "grad_norm": 6.224593639373779, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.1778, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02979942693409742, | |
| "grad_norm": 4.25213098526001, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.7744, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.032091690544412604, | |
| "grad_norm": 4.979966640472412, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.6806, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.034383954154727794, | |
| "grad_norm": 4.518800258636475, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.6474, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.034383954154727794, | |
| "eval_loss": 0.40958088636398315, | |
| "eval_runtime": 54.7398, | |
| "eval_samples_per_second": 3.361, | |
| "eval_steps_per_second": 1.681, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03667621776504298, | |
| "grad_norm": 4.9027323722839355, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.7134, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03896848137535817, | |
| "grad_norm": 4.276649475097656, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.7094, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04126074498567335, | |
| "grad_norm": 4.055666923522949, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.5544, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04355300859598854, | |
| "grad_norm": 4.310039043426514, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.6613, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.045845272206303724, | |
| "grad_norm": 3.8238983154296875, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.5674, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.045845272206303724, | |
| "eval_loss": 0.3845430910587311, | |
| "eval_runtime": 54.5459, | |
| "eval_samples_per_second": 3.373, | |
| "eval_steps_per_second": 1.687, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.048137535816618914, | |
| "grad_norm": 3.9479007720947266, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.5336, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0504297994269341, | |
| "grad_norm": 3.7271645069122314, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.4092, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05272206303724929, | |
| "grad_norm": 4.096502780914307, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.6154, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05501432664756447, | |
| "grad_norm": 3.3436808586120605, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.5261, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05730659025787966, | |
| "grad_norm": 3.5416524410247803, | |
| "learning_rate": 0.0, | |
| "loss": 1.2902, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05730659025787966, | |
| "eval_loss": 0.3771282732486725, | |
| "eval_runtime": 54.5652, | |
| "eval_samples_per_second": 3.372, | |
| "eval_steps_per_second": 1.686, | |
| "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": 8763358996070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |