| { | |
| "best_metric": 0.6161407232284546, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.41237113402061853, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016494845360824743, | |
| "grad_norm": 27.123544692993164, | |
| "learning_rate": 5e-05, | |
| "loss": 13.379, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016494845360824743, | |
| "eval_loss": 13.364030838012695, | |
| "eval_runtime": 12.0291, | |
| "eval_samples_per_second": 34.001, | |
| "eval_steps_per_second": 4.323, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.032989690721649485, | |
| "grad_norm": 26.585224151611328, | |
| "learning_rate": 0.0001, | |
| "loss": 12.9234, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.049484536082474224, | |
| "grad_norm": 24.71361541748047, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.7235, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06597938144329897, | |
| "grad_norm": 26.475887298583984, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.4102, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 23.473953247070312, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.8938, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09896907216494845, | |
| "grad_norm": 24.470653533935547, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.4529, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1154639175257732, | |
| "grad_norm": 32.81455612182617, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.9449, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13195876288659794, | |
| "grad_norm": 18.870418548583984, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3707, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14845360824742268, | |
| "grad_norm": 38.58383560180664, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1763, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 27.82632064819336, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8994, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18144329896907216, | |
| "grad_norm": 14.27000617980957, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7961, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1979381443298969, | |
| "grad_norm": 14.294880867004395, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6592, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21443298969072164, | |
| "grad_norm": 10.414827346801758, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.717, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2309278350515464, | |
| "grad_norm": 6.658370018005371, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5636, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 20.65096664428711, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7669, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2639175257731959, | |
| "grad_norm": 17.110864639282227, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7092, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2804123711340206, | |
| "grad_norm": 11.446817398071289, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6073, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.29690721649484536, | |
| "grad_norm": 16.738853454589844, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6819, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3134020618556701, | |
| "grad_norm": 17.020660400390625, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6582, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 4.482657432556152, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5101, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3463917525773196, | |
| "grad_norm": 6.59984016418457, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5481, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3628865979381443, | |
| "grad_norm": 8.41876220703125, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5884, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.37938144329896906, | |
| "grad_norm": 6.026383399963379, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5506, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3958762886597938, | |
| "grad_norm": 3.7949957847595215, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4389, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 5.4872026443481445, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4634, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "eval_loss": 0.6161407232284546, | |
| "eval_runtime": 12.0098, | |
| "eval_samples_per_second": 34.056, | |
| "eval_steps_per_second": 4.33, | |
| "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": 7.94731890081792e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |