| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.034675566728793725, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006935113345758744, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006935113345758744, | |
| "eval_loss": NaN, | |
| "eval_runtime": 704.6135, | |
| "eval_samples_per_second": 6.893, | |
| "eval_steps_per_second": 1.724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001387022669151749, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020805340037276234, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002774045338303498, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0034675566728793726, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004161068007455247, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004854579342031122, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5000000000000004e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005548090676606996, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00624160201118287, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006935113345758745, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007628624680334619, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008322136014910494, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009015647349486369, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009709158684062243, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010402670018638116, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011096181353213991, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011789692687789866, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.500000000000002e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01248320402236574, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013176715356941615, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01387022669151749, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014563738026093363, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.05e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015257249360669238, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015950760695245113, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1500000000000002e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.016644272029820988, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017337783364396862, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017337783364396862, | |
| "eval_loss": NaN, | |
| "eval_runtime": 705.1149, | |
| "eval_samples_per_second": 6.888, | |
| "eval_steps_per_second": 1.723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018031294698972737, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.018724806033548612, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019418317368124487, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02011182870270036, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.45e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.020805340037276233, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021498851371852108, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.55e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.022192362706427982, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.022885874041003857, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.65e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023579385375579732, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.024272896710155607, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02496640804473148, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.025659919379307356, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.85e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02635343071388323, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.027046942048459106, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9500000000000003e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02774045338303498, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028433964717610852, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.05e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.029127476052186727, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0298209873867626, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.15e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.030514498721338476, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03120801005591435, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.031901521390490226, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0325950327250661, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.35e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.033288544059641975, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03398205539421785, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.45e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.034675566728793725, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.034675566728793725, | |
| "eval_loss": NaN, | |
| "eval_runtime": 703.9635, | |
| "eval_samples_per_second": 6.9, | |
| "eval_steps_per_second": 1.726, | |
| "step": 50 | |
| } | |
| ], | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.861999239200768e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |