| { | |
| "best_metric": 0.2677198052406311, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.031578947368421, | |
| "eval_steps": 25, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 5.290541648864746, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1391, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "eval_loss": 6.062305450439453, | |
| "eval_runtime": 4.7353, | |
| "eval_samples_per_second": 16.895, | |
| "eval_steps_per_second": 2.112, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 10.83039379119873, | |
| "learning_rate": 0.0001, | |
| "loss": 6.2114, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": 9.01547908782959, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 4.4483, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 4.820804119110107, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 5.8774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 5.7229180335998535, | |
| "learning_rate": 9.809128215864097e-05, | |
| "loss": 2.4323, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 4.481346607208252, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 3.1135, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5894736842105263, | |
| "grad_norm": 5.059967041015625, | |
| "learning_rate": 9.475816456775313e-05, | |
| "loss": 5.1153, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 3.4522106647491455, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.9424, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7578947368421053, | |
| "grad_norm": 2.8100931644439697, | |
| "learning_rate": 8.9900861364012e-05, | |
| "loss": 2.7768, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 2.5981743335723877, | |
| "learning_rate": 8.695044586103296e-05, | |
| "loss": 2.3917, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9263157894736842, | |
| "grad_norm": 1.2653751373291016, | |
| "learning_rate": 8.368478218232787e-05, | |
| "loss": 0.2868, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0105263157894737, | |
| "grad_norm": 2.118408441543579, | |
| "learning_rate": 8.013173181896283e-05, | |
| "loss": 1.4738, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0947368421052632, | |
| "grad_norm": 3.251176357269287, | |
| "learning_rate": 7.63216081438678e-05, | |
| "loss": 2.1097, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1789473684210527, | |
| "grad_norm": 1.2804324626922607, | |
| "learning_rate": 7.228691778882693e-05, | |
| "loss": 0.4403, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 1.913195252418518, | |
| "learning_rate": 6.806208330935766e-05, | |
| "loss": 0.4639, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3473684210526315, | |
| "grad_norm": 3.9906165599823, | |
| "learning_rate": 6.368314950360415e-05, | |
| "loss": 1.0192, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.431578947368421, | |
| "grad_norm": 0.4292667508125305, | |
| "learning_rate": 5.918747589082853e-05, | |
| "loss": 0.0192, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5157894736842106, | |
| "grad_norm": 3.494691848754883, | |
| "learning_rate": 5.4613417973165106e-05, | |
| "loss": 0.2441, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 4.833470821380615, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6926, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 0.3874737024307251, | |
| "learning_rate": 4.5386582026834906e-05, | |
| "loss": 0.0087, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.768421052631579, | |
| "grad_norm": 1.789414405822754, | |
| "learning_rate": 4.0812524109171476e-05, | |
| "loss": 0.2853, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.8526315789473684, | |
| "grad_norm": 3.8535306453704834, | |
| "learning_rate": 3.631685049639586e-05, | |
| "loss": 0.3714, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.936842105263158, | |
| "grad_norm": 0.4089250862598419, | |
| "learning_rate": 3.1937916690642356e-05, | |
| "loss": 0.0266, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0210526315789474, | |
| "grad_norm": 0.921528160572052, | |
| "learning_rate": 2.771308221117309e-05, | |
| "loss": 0.2166, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 3.09906268119812, | |
| "learning_rate": 2.3678391856132204e-05, | |
| "loss": 0.4467, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "eval_loss": 0.2677198052406311, | |
| "eval_runtime": 4.2004, | |
| "eval_samples_per_second": 19.046, | |
| "eval_steps_per_second": 2.381, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1894736842105265, | |
| "grad_norm": 0.04200873523950577, | |
| "learning_rate": 1.9868268181037185e-05, | |
| "loss": 0.0011, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.2736842105263158, | |
| "grad_norm": 2.74108624458313, | |
| "learning_rate": 1.631521781767214e-05, | |
| "loss": 0.0985, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.3578947368421055, | |
| "grad_norm": 2.8675966262817383, | |
| "learning_rate": 1.3049554138967051e-05, | |
| "loss": 0.4339, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.442105263157895, | |
| "grad_norm": 0.026142483577132225, | |
| "learning_rate": 1.0099138635988026e-05, | |
| "loss": 0.0007, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 4.404775619506836, | |
| "learning_rate": 7.489143213519301e-06, | |
| "loss": 0.1664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.610526315789474, | |
| "grad_norm": 2.646777629852295, | |
| "learning_rate": 5.241835432246889e-06, | |
| "loss": 0.25, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.694736842105263, | |
| "grad_norm": 0.018841933459043503, | |
| "learning_rate": 3.376388529782215e-06, | |
| "loss": 0.0006, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.7789473684210524, | |
| "grad_norm": 4.183905601501465, | |
| "learning_rate": 1.908717841359048e-06, | |
| "loss": 0.2952, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.863157894736842, | |
| "grad_norm": 2.0903871059417725, | |
| "learning_rate": 8.513450158049108e-07, | |
| "loss": 0.2034, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 2.281219959259033, | |
| "learning_rate": 2.1329118524827662e-07, | |
| "loss": 0.0681, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.031578947368421, | |
| "grad_norm": 1.8667627573013306, | |
| "learning_rate": 0.0, | |
| "loss": 0.1752, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.610862382625587e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |