| { | |
| "best_metric": 0.9366852045059204, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.4652014652014653, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05860805860805861, | |
| "grad_norm": 69.92310333251953, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6927, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05860805860805861, | |
| "eval_loss": 2.5487382411956787, | |
| "eval_runtime": 7.7618, | |
| "eval_samples_per_second": 14.816, | |
| "eval_steps_per_second": 1.933, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11721611721611722, | |
| "grad_norm": 55.87076187133789, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5276, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17582417582417584, | |
| "grad_norm": 55.028907775878906, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1781, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23443223443223443, | |
| "grad_norm": 47.40984344482422, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.6883, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 42.50719451904297, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5772, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3516483516483517, | |
| "grad_norm": 36.53390121459961, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4017, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 37.008277893066406, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.2432, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.46886446886446886, | |
| "grad_norm": 34.43931198120117, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1372, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5274725274725275, | |
| "grad_norm": 28.272953033447266, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1788, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 27.42231559753418, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1755, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6446886446886447, | |
| "grad_norm": 25.12748908996582, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0403, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7032967032967034, | |
| "grad_norm": 22.614639282226562, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9622, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 30.539390563964844, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0033, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 25.333518981933594, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1037, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 20.368425369262695, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9753, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9377289377289377, | |
| "grad_norm": 19.483905792236328, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.9837, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9963369963369964, | |
| "grad_norm": 18.775177001953125, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8947, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.054945054945055, | |
| "grad_norm": 36.05515670776367, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0035, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1135531135531136, | |
| "grad_norm": 32.69635772705078, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.9469, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1721611721611722, | |
| "grad_norm": 30.572795867919922, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8656, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 30.598207473754883, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.832, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2893772893772895, | |
| "grad_norm": 29.853466033935547, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.879, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.347985347985348, | |
| "grad_norm": 38.4538688659668, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.902, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4065934065934065, | |
| "grad_norm": 28.7051944732666, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8573, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4652014652014653, | |
| "grad_norm": 28.951257705688477, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8289, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4652014652014653, | |
| "eval_loss": 0.9366852045059204, | |
| "eval_runtime": 7.7637, | |
| "eval_samples_per_second": 14.813, | |
| "eval_steps_per_second": 1.932, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.8426299460131226e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |