| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010706423184759407, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021412846369518813, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021412846369518813, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2484, | |
| "eval_samples_per_second": 11.769, | |
| "eval_steps_per_second": 3.06, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042825692739037626, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006423853910855644, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008565138547807525, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010706423184759406, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012847707821711288, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014988992458663168, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001713027709561505, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0019271561732566932, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021412846369518812, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023554131006470694, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0025695415643422577, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002783670028037446, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0029977984917326336, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003211926955427822, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00342605541912301, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0036401838828181983, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0038543123465133865, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004068440810208574, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0042825692739037625, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004496697737598951, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004710826201294139, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004924954664989327, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005139083128684515, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0053532115923797035, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0053532115923797035, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2473, | |
| "eval_samples_per_second": 11.772, | |
| "eval_steps_per_second": 3.061, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005567340056074892, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00578146851977008, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005995596983465267, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0062097254471604555, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006423853910855644, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006637982374550832, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00685211083824602, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.007066239301941208, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0072803677656363966, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007494496229331585, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007708624693026773, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007922753156721961, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.008136881620417149, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.008351010084112338, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008565138547807525, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008779267011502714, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008993395475197901, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.00920752393889309, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009421652402588278, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009635780866283465, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009849909329978654, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.010064037793673842, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01027816625736903, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.010492294721064218, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010706423184759407, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010706423184759407, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2631, | |
| "eval_samples_per_second": 11.728, | |
| "eval_steps_per_second": 3.049, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |