| { | |
| "best_metric": 4.555571556091309, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.017114495978093443, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "grad_norm": 1.8983988761901855, | |
| "learning_rate": 5e-05, | |
| "loss": 5.5369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "eval_loss": 5.087055683135986, | |
| "eval_runtime": 1.8291, | |
| "eval_samples_per_second": 27.336, | |
| "eval_steps_per_second": 7.107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013691596782474755, | |
| "grad_norm": 1.7235485315322876, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2483, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020537395173712133, | |
| "grad_norm": 1.5233309268951416, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.085, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002738319356494951, | |
| "grad_norm": 1.1321425437927246, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.9184, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003422899195618689, | |
| "grad_norm": 2.263650417327881, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.8358, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004107479034742427, | |
| "grad_norm": 0.9546835422515869, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.8692, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004792058873866164, | |
| "grad_norm": 0.7501165270805359, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.9064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005476638712989902, | |
| "grad_norm": 0.5767120122909546, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.8118, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00616121855211364, | |
| "grad_norm": 0.6856655478477478, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.8149, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006845798391237378, | |
| "grad_norm": 0.7905865907669067, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.8121, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0075303782303611155, | |
| "grad_norm": 1.2904866933822632, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.8751, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008214958069484853, | |
| "grad_norm": 0.7690590620040894, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.8562, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008899537908608592, | |
| "grad_norm": 1.3141318559646606, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.1032, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009584117747732329, | |
| "grad_norm": 1.111348271369934, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.0121, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010268697586856067, | |
| "grad_norm": 0.9109743237495422, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.7557, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010953277425979804, | |
| "grad_norm": 0.5635835528373718, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.6933, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011637857265103543, | |
| "grad_norm": 1.2304234504699707, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.5971, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01232243710422728, | |
| "grad_norm": 1.4028397798538208, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.6146, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013007016943351019, | |
| "grad_norm": 1.7947639226913452, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.611, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013691596782474755, | |
| "grad_norm": 1.5065919160842896, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.622, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014376176621598494, | |
| "grad_norm": 0.48089975118637085, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.6141, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015060756460722231, | |
| "grad_norm": 0.5148659348487854, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.6095, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01574533629984597, | |
| "grad_norm": 0.6612058281898499, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.5889, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.016429916138969707, | |
| "grad_norm": 0.5617333650588989, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.6246, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017114495978093443, | |
| "grad_norm": 0.5102720260620117, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.6922, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017114495978093443, | |
| "eval_loss": 4.555571556091309, | |
| "eval_runtime": 0.3228, | |
| "eval_samples_per_second": 154.902, | |
| "eval_steps_per_second": 40.274, | |
| "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": 5981868147081216.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |