| { | |
| "best_metric": 0.3850732743740082, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.045845272206303724, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002292263610315186, | |
| "grad_norm": 7.594876289367676, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6697, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002292263610315186, | |
| "eval_loss": 0.6890747547149658, | |
| "eval_runtime": 56.7744, | |
| "eval_samples_per_second": 3.241, | |
| "eval_steps_per_second": 1.62, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004584527220630372, | |
| "grad_norm": 8.860320091247559, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8621, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006876790830945559, | |
| "grad_norm": 6.397947311401367, | |
| "learning_rate": 6e-05, | |
| "loss": 2.836, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009169054441260744, | |
| "grad_norm": 8.215444564819336, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5098, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011461318051575931, | |
| "grad_norm": 8.26395034790039, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3572, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011461318051575931, | |
| "eval_loss": 0.6056112051010132, | |
| "eval_runtime": 55.9895, | |
| "eval_samples_per_second": 3.286, | |
| "eval_steps_per_second": 1.643, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013753581661891117, | |
| "grad_norm": 5.971251487731934, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4809, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016045845272206302, | |
| "grad_norm": 6.999272346496582, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01833810888252149, | |
| "grad_norm": 4.562480449676514, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9463, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020630372492836675, | |
| "grad_norm": 5.3542304039001465, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0711, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022922636103151862, | |
| "grad_norm": 5.165809631347656, | |
| "learning_rate": 0.0002, | |
| "loss": 2.187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022922636103151862, | |
| "eval_loss": 0.4689041078090668, | |
| "eval_runtime": 55.7448, | |
| "eval_samples_per_second": 3.301, | |
| "eval_steps_per_second": 1.65, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02521489971346705, | |
| "grad_norm": 4.579631328582764, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.0219, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027507163323782235, | |
| "grad_norm": 6.482594966888428, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.1928, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02979942693409742, | |
| "grad_norm": 4.32263708114624, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.7855, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.032091690544412604, | |
| "grad_norm": 4.8766188621521, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.6799, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.034383954154727794, | |
| "grad_norm": 4.413567066192627, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.6611, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.034383954154727794, | |
| "eval_loss": 0.40960490703582764, | |
| "eval_runtime": 55.4446, | |
| "eval_samples_per_second": 3.319, | |
| "eval_steps_per_second": 1.659, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03667621776504298, | |
| "grad_norm": 4.532293319702148, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.7058, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03896848137535817, | |
| "grad_norm": 4.254657745361328, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.7261, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04126074498567335, | |
| "grad_norm": 3.960785388946533, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.5435, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04355300859598854, | |
| "grad_norm": 4.079868316650391, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.6584, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.045845272206303724, | |
| "grad_norm": 3.6767802238464355, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.5751, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.045845272206303724, | |
| "eval_loss": 0.3850732743740082, | |
| "eval_runtime": 55.6159, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 1.654, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7010687196856320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |