| { | |
| "best_metric": 6.917301654815674, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.20629190304280556, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008251676121712223, | |
| "grad_norm": 0.19007240235805511, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008251676121712223, | |
| "eval_loss": 6.937552452087402, | |
| "eval_runtime": 0.8717, | |
| "eval_samples_per_second": 937.293, | |
| "eval_steps_per_second": 118.165, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016503352243424446, | |
| "grad_norm": 0.18242356181144714, | |
| "learning_rate": 0.0001, | |
| "loss": 6.858, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02475502836513667, | |
| "grad_norm": 0.1995544582605362, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.8447, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03300670448684889, | |
| "grad_norm": 0.18593429028987885, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.8302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.041258380608561115, | |
| "grad_norm": 0.18931446969509125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.8183, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04951005673027334, | |
| "grad_norm": 0.1950785368680954, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.8054, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05776173285198556, | |
| "grad_norm": 0.20064397156238556, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.7876, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06601340897369778, | |
| "grad_norm": 0.22192345559597015, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07426508509541001, | |
| "grad_norm": 0.22847650945186615, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.7498, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08251676121712223, | |
| "grad_norm": 0.2764003574848175, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.7123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09076843733883445, | |
| "grad_norm": 0.25168463587760925, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.6124, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09902011346054668, | |
| "grad_norm": 0.31273701786994934, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.3779, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1072717895822589, | |
| "grad_norm": 0.18679746985435486, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 6.8239, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11552346570397112, | |
| "grad_norm": 0.19334200024604797, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.8569, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12377514182568335, | |
| "grad_norm": 0.21157041192054749, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 6.8419, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13202681794739557, | |
| "grad_norm": 0.20532171428203583, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 6.8266, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14027849406910778, | |
| "grad_norm": 0.1977279633283615, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 6.8141, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14853017019082002, | |
| "grad_norm": 0.19488519430160522, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.7972, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15678184631253222, | |
| "grad_norm": 0.21557967364788055, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.7828, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16503352243424446, | |
| "grad_norm": 0.22028861939907074, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.7694, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17328519855595667, | |
| "grad_norm": 0.23538333177566528, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.7487, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1815368746776689, | |
| "grad_norm": 0.2506059408187866, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.7218, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18978855079938112, | |
| "grad_norm": 0.25545573234558105, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.6615, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19804022692109335, | |
| "grad_norm": 0.28446659445762634, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.4915, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20629190304280556, | |
| "grad_norm": 0.3152291476726532, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20629190304280556, | |
| "eval_loss": 6.917301654815674, | |
| "eval_runtime": 0.8631, | |
| "eval_samples_per_second": 946.555, | |
| "eval_steps_per_second": 119.333, | |
| "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": 2852978688000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |