| { | |
| "best_metric": 3.3242831230163574, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.00024053856584893576, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2026928292446788e-05, | |
| "grad_norm": 14.573991775512695, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 11.9726, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.2026928292446788e-05, | |
| "eval_loss": 3.3685247898101807, | |
| "eval_runtime": 3092.2439, | |
| "eval_samples_per_second": 11.322, | |
| "eval_steps_per_second": 5.661, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.4053856584893577e-05, | |
| "grad_norm": 11.94653606414795, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 13.1679, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.608078487734037e-05, | |
| "grad_norm": 16.6671085357666, | |
| "learning_rate": 6e-06, | |
| "loss": 13.0803, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.8107713169787154e-05, | |
| "grad_norm": 16.513452529907227, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 12.5038, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 6.013464146223394e-05, | |
| "grad_norm": 11.513193130493164, | |
| "learning_rate": 1e-05, | |
| "loss": 14.3786, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.013464146223394e-05, | |
| "eval_loss": 3.3678781986236572, | |
| "eval_runtime": 2392.3778, | |
| "eval_samples_per_second": 14.634, | |
| "eval_steps_per_second": 7.317, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.216156975468073e-05, | |
| "grad_norm": 8.093759536743164, | |
| "learning_rate": 1.2e-05, | |
| "loss": 15.6202, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 8.418849804712752e-05, | |
| "grad_norm": 15.125259399414062, | |
| "learning_rate": 1.4e-05, | |
| "loss": 15.1072, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 9.621542633957431e-05, | |
| "grad_norm": 17.306556701660156, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 11.841, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001082423546320211, | |
| "grad_norm": 18.899417877197266, | |
| "learning_rate": 1.8e-05, | |
| "loss": 11.5655, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00012026928292446788, | |
| "grad_norm": 8.767831802368164, | |
| "learning_rate": 2e-05, | |
| "loss": 14.7897, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00012026928292446788, | |
| "eval_loss": 3.3603010177612305, | |
| "eval_runtime": 3051.4146, | |
| "eval_samples_per_second": 11.473, | |
| "eval_steps_per_second": 5.737, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00013229621121691468, | |
| "grad_norm": 9.166821479797363, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 13.507, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00014432313950936147, | |
| "grad_norm": 9.79527759552002, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 14.5831, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00015635006780180825, | |
| "grad_norm": 13.353811264038086, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 12.4279, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00016837699609425504, | |
| "grad_norm": 19.06542205810547, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 12.7872, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00018040392438670183, | |
| "grad_norm": 19.6158390045166, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 13.3129, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00018040392438670183, | |
| "eval_loss": 3.3403236865997314, | |
| "eval_runtime": 3784.0295, | |
| "eval_samples_per_second": 9.252, | |
| "eval_steps_per_second": 4.626, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00019243085267914861, | |
| "grad_norm": 12.81112289428711, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 12.9199, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002044577809715954, | |
| "grad_norm": 38.4151611328125, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 13.3895, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0002164847092640422, | |
| "grad_norm": 8.710651397705078, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 14.4392, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00022851163755648897, | |
| "grad_norm": 16.718015670776367, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 14.2077, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00024053856584893576, | |
| "grad_norm": 17.698863983154297, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 11.7674, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00024053856584893576, | |
| "eval_loss": 3.3242831230163574, | |
| "eval_runtime": 2367.8712, | |
| "eval_samples_per_second": 14.785, | |
| "eval_steps_per_second": 7.393, | |
| "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": 3257498484080640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |