| { | |
| "best_metric": 0.540064811706543, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.005889975262103899, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023559901048415596, | |
| "grad_norm": 0.3784501254558563, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023559901048415596, | |
| "eval_loss": 0.6598115563392639, | |
| "eval_runtime": 432.1218, | |
| "eval_samples_per_second": 4.138, | |
| "eval_steps_per_second": 2.069, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004711980209683119, | |
| "grad_norm": 0.3668363094329834, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6555, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007067970314524679, | |
| "grad_norm": 0.5077784657478333, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6326, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009423960419366238, | |
| "grad_norm": 0.4163624048233032, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7083, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011779950524207798, | |
| "grad_norm": 0.4140971601009369, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6878, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011779950524207798, | |
| "eval_loss": 0.6515950560569763, | |
| "eval_runtime": 426.6242, | |
| "eval_samples_per_second": 4.191, | |
| "eval_steps_per_second": 2.096, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014135940629049358, | |
| "grad_norm": 0.47956836223602295, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6468, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016491930733890919, | |
| "grad_norm": 0.4840953052043915, | |
| "learning_rate": 0.00014, | |
| "loss": 0.6795, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0018847920838732477, | |
| "grad_norm": 0.4249662458896637, | |
| "learning_rate": 0.00016, | |
| "loss": 0.5602, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0021203910943574035, | |
| "grad_norm": 0.4048328399658203, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7123, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0023559901048415596, | |
| "grad_norm": 0.38470837473869324, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6979, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023559901048415596, | |
| "eval_loss": 0.5909367203712463, | |
| "eval_runtime": 435.8721, | |
| "eval_samples_per_second": 4.102, | |
| "eval_steps_per_second": 2.051, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025915891153257156, | |
| "grad_norm": 0.47473108768463135, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.5654, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0028271881258098716, | |
| "grad_norm": 0.572853684425354, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.6893, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0030627871362940277, | |
| "grad_norm": 0.6122471690177917, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.593, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0032983861467781837, | |
| "grad_norm": 0.7183160781860352, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.6515, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0035339851572623393, | |
| "grad_norm": 0.4755716621875763, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6092, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0035339851572623393, | |
| "eval_loss": 0.5491443276405334, | |
| "eval_runtime": 432.8959, | |
| "eval_samples_per_second": 4.13, | |
| "eval_steps_per_second": 2.065, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0037695841677464954, | |
| "grad_norm": 0.3686135709285736, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.5829, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004005183178230651, | |
| "grad_norm": 0.39384743571281433, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.5757, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004240782188714807, | |
| "grad_norm": 0.3624189794063568, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.4607, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0044763811991989635, | |
| "grad_norm": 0.3992636799812317, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.4785, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004711980209683119, | |
| "grad_norm": 0.3548687994480133, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.4083, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004711980209683119, | |
| "eval_loss": 0.542029082775116, | |
| "eval_runtime": 430.5877, | |
| "eval_samples_per_second": 4.152, | |
| "eval_steps_per_second": 2.076, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004947579220167276, | |
| "grad_norm": 0.362483412027359, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.4542, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005183178230651431, | |
| "grad_norm": 0.3919994831085205, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.5401, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005418777241135587, | |
| "grad_norm": 0.3926795721054077, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.5272, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005654376251619743, | |
| "grad_norm": 0.4079397916793823, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.5501, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005889975262103899, | |
| "grad_norm": 0.39526617527008057, | |
| "learning_rate": 0.0, | |
| "loss": 0.5403, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005889975262103899, | |
| "eval_loss": 0.540064811706543, | |
| "eval_runtime": 451.99, | |
| "eval_samples_per_second": 3.956, | |
| "eval_steps_per_second": 1.978, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9247826273894400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |