| { | |
| "best_metric": 1.6246213912963867, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.1225114854517611, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004900459418070444, | |
| "grad_norm": 23.471738815307617, | |
| "learning_rate": 5e-05, | |
| "loss": 6.7852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004900459418070444, | |
| "eval_loss": 7.382022857666016, | |
| "eval_runtime": 18.5323, | |
| "eval_samples_per_second": 74.195, | |
| "eval_steps_per_second": 9.281, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009800918836140888, | |
| "grad_norm": 23.077556610107422, | |
| "learning_rate": 0.0001, | |
| "loss": 6.8171, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014701378254211332, | |
| "grad_norm": 17.30784034729004, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.2819, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019601837672281776, | |
| "grad_norm": 10.578380584716797, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.4992, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02450229709035222, | |
| "grad_norm": 8.487051010131836, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.9079, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.029402756508422664, | |
| "grad_norm": 6.275716781616211, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.6387, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03430321592649311, | |
| "grad_norm": 4.362668037414551, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.48, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03920367534456355, | |
| "grad_norm": 3.9618260860443115, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3593, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.044104134762633994, | |
| "grad_norm": 3.2072575092315674, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3954, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04900459418070444, | |
| "grad_norm": 3.726250171661377, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1785, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.053905053598774885, | |
| "grad_norm": 2.532313585281372, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2436, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05880551301684533, | |
| "grad_norm": 2.7389440536499023, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1768, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06370597243491577, | |
| "grad_norm": 2.995002508163452, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9088, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06860643185298622, | |
| "grad_norm": 2.0172295570373535, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4442, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07350689127105667, | |
| "grad_norm": 2.4108283519744873, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5092, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0784073506891271, | |
| "grad_norm": 2.739496946334839, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4547, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08330781010719755, | |
| "grad_norm": 3.4123828411102295, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4325, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08820826952526799, | |
| "grad_norm": 2.2385709285736084, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6656, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09310872894333844, | |
| "grad_norm": 2.2674455642700195, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.6064, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09800918836140889, | |
| "grad_norm": 2.166579484939575, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.707, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10290964777947932, | |
| "grad_norm": 2.1645350456237793, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7495, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10781010719754977, | |
| "grad_norm": 2.4724934101104736, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.0361, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11271056661562022, | |
| "grad_norm": 1.933280110359192, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.0074, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11761102603369065, | |
| "grad_norm": 2.0323431491851807, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.0281, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1225114854517611, | |
| "grad_norm": 2.1172215938568115, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.1502, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1225114854517611, | |
| "eval_loss": 1.6246213912963867, | |
| "eval_runtime": 18.4789, | |
| "eval_samples_per_second": 74.409, | |
| "eval_steps_per_second": 9.308, | |
| "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": 7.957253052799386e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |