| { | |
| "best_metric": 1.5644229650497437, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.10751243112484882, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0043004972449939526, | |
| "grad_norm": 19.8057861328125, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5081, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0043004972449939526, | |
| "eval_loss": 10.621899604797363, | |
| "eval_runtime": 1.3563, | |
| "eval_samples_per_second": 36.864, | |
| "eval_steps_per_second": 9.585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008600994489987905, | |
| "grad_norm": 57.842559814453125, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6077, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012901491734981858, | |
| "grad_norm": 35.29104995727539, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 6.6945, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01720198897997581, | |
| "grad_norm": 24.527158737182617, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 4.4752, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021502486224969763, | |
| "grad_norm": 14.023441314697266, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 3.6787, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025802983469963715, | |
| "grad_norm": 14.097426414489746, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 3.2176, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030103480714957668, | |
| "grad_norm": 10.716201782226562, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 3.1421, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03440397795995162, | |
| "grad_norm": 7.361116409301758, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 2.3853, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03870447520494557, | |
| "grad_norm": 7.526501655578613, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 2.2858, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.043004972449939526, | |
| "grad_norm": 11.618202209472656, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 2.7698, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047305469694933475, | |
| "grad_norm": 19.959169387817383, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 3.5525, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05160596693992743, | |
| "grad_norm": 27.947349548339844, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 4.2679, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05590646418492138, | |
| "grad_norm": 10.88952922821045, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 1.8362, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.060206961429915336, | |
| "grad_norm": 13.4713716506958, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.8983, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06450745867490928, | |
| "grad_norm": 12.285510063171387, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 1.2347, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06880795591990324, | |
| "grad_norm": 5.789817810058594, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 1.3281, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0731084531648972, | |
| "grad_norm": 5.892718315124512, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 1.2367, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07740895040989114, | |
| "grad_norm": 5.36167573928833, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 1.43, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0817094476548851, | |
| "grad_norm": 5.179811000823975, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 1.8865, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08600994489987905, | |
| "grad_norm": 4.091755390167236, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 1.6909, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09031044214487301, | |
| "grad_norm": 3.845872163772583, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 1.6963, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09461093938986695, | |
| "grad_norm": 3.2446541786193848, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 1.7898, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0989114366348609, | |
| "grad_norm": 4.2228617668151855, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 2.1524, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10321193387985486, | |
| "grad_norm": 6.195683002471924, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 2.6266, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10751243112484882, | |
| "grad_norm": 6.88140344619751, | |
| "learning_rate": 1e-05, | |
| "loss": 2.712, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10751243112484882, | |
| "eval_loss": 1.5644229650497437, | |
| "eval_runtime": 1.3728, | |
| "eval_samples_per_second": 36.422, | |
| "eval_steps_per_second": 9.47, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.949802438813286e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |