| { | |
| "best_metric": 11.935075759887695, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.08635578583765112, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0034542314335060447, | |
| "grad_norm": 0.04175278916954994, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9399, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034542314335060447, | |
| "eval_loss": 11.940598487854004, | |
| "eval_runtime": 8.5028, | |
| "eval_samples_per_second": 229.453, | |
| "eval_steps_per_second": 28.696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0069084628670120895, | |
| "grad_norm": 0.04260191321372986, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010362694300518135, | |
| "grad_norm": 0.04679454118013382, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9407, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013816925734024179, | |
| "grad_norm": 0.04993719235062599, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9391, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017271157167530225, | |
| "grad_norm": 0.05013435333967209, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9399, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02072538860103627, | |
| "grad_norm": 0.06913993507623672, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9367, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024179620034542316, | |
| "grad_norm": 0.07582654058933258, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9384, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027633851468048358, | |
| "grad_norm": 0.07948369532823563, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9411, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.031088082901554404, | |
| "grad_norm": 0.08457164466381073, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03454231433506045, | |
| "grad_norm": 0.09221560508012772, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.037996545768566495, | |
| "grad_norm": 0.09865477681159973, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9381, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04145077720207254, | |
| "grad_norm": 0.1040349081158638, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9369, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.044905008635578586, | |
| "grad_norm": 0.06590238213539124, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9372, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04835924006908463, | |
| "grad_norm": 0.05209377408027649, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9386, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05181347150259067, | |
| "grad_norm": 0.06293608248233795, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9372, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.055267702936096716, | |
| "grad_norm": 0.06793326884508133, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9402, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05872193436960276, | |
| "grad_norm": 0.07311394810676575, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9388, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06217616580310881, | |
| "grad_norm": 0.08118285238742828, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9378, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06563039723661486, | |
| "grad_norm": 0.09678582102060318, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9348, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0690846286701209, | |
| "grad_norm": 0.10049033910036087, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9381, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07253886010362694, | |
| "grad_norm": 0.1105872094631195, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.937, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07599309153713299, | |
| "grad_norm": 0.11385960131883621, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9332, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07944732297063903, | |
| "grad_norm": 0.12892016768455505, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9336, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08290155440414508, | |
| "grad_norm": 0.12460300326347351, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9342, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08635578583765112, | |
| "grad_norm": 0.14798326790332794, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9328, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08635578583765112, | |
| "eval_loss": 11.935075759887695, | |
| "eval_runtime": 8.4955, | |
| "eval_samples_per_second": 229.652, | |
| "eval_steps_per_second": 28.721, | |
| "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": 521247129600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |