| { | |
| "best_metric": 1.613996982574463, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06575702778234424, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026302811112937697, | |
| "grad_norm": 7.6924729347229, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026302811112937697, | |
| "eval_loss": 6.583785533905029, | |
| "eval_runtime": 2.2573, | |
| "eval_samples_per_second": 22.151, | |
| "eval_steps_per_second": 5.759, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005260562222587539, | |
| "grad_norm": 8.963078498840332, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2095, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007890843333881308, | |
| "grad_norm": 7.708944797515869, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.1646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010521124445175079, | |
| "grad_norm": 5.140854835510254, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.3043, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013151405556468848, | |
| "grad_norm": 5.477720260620117, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.8263, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015781686667762616, | |
| "grad_norm": 6.843749523162842, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.6723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018411967779056387, | |
| "grad_norm": 7.493031978607178, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.812, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021042248890350158, | |
| "grad_norm": 6.828537940979004, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.5599, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023672530001643925, | |
| "grad_norm": 4.211589813232422, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.6797, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026302811112937696, | |
| "grad_norm": 5.306011199951172, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.4685, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028933092224231464, | |
| "grad_norm": 4.892298221588135, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.0411, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03156337333552523, | |
| "grad_norm": 5.788684368133545, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.8765, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034193654446819, | |
| "grad_norm": 7.938673496246338, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.1427, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03682393555811277, | |
| "grad_norm": 4.239195823669434, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.9294, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039454216669406544, | |
| "grad_norm": 3.0556766986846924, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.042084497780700315, | |
| "grad_norm": 3.01393461227417, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.7901, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04471477889199408, | |
| "grad_norm": 2.964114189147949, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.8135, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04734506000328785, | |
| "grad_norm": 2.678053379058838, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.8461, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04997534111458162, | |
| "grad_norm": 2.649806022644043, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.959, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05260562222587539, | |
| "grad_norm": 2.9589452743530273, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.7594, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05523590333716916, | |
| "grad_norm": 3.0157201290130615, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.7822, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05786618444846293, | |
| "grad_norm": 3.3775577545166016, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.5996, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0604964655597567, | |
| "grad_norm": 4.172215461730957, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5145, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06312674667105046, | |
| "grad_norm": 4.449634075164795, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.3848, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06575702778234424, | |
| "grad_norm": 5.117303371429443, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.4496, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06575702778234424, | |
| "eval_loss": 1.613996982574463, | |
| "eval_runtime": 2.3308, | |
| "eval_samples_per_second": 21.452, | |
| "eval_steps_per_second": 5.577, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.087239672233984e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |