| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0008243751236562685, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.648750247312537e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.648750247312537e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4953.4443, | |
| "eval_samples_per_second": 5.156, | |
| "eval_steps_per_second": 2.578, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.297500494625074e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.946250741937611e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.595000989250148e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.243751236562685e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 9.892501483875222e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011541251731187759, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00013190001978500296, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00014838752225812833, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001648750247312537, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00018136252720437907, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00019785002967750444, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00021433753215062981, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00023082503462375518, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00024731253709688055, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002638000395700059, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002802875420431313, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00029677504451625667, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00031326254698938204, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0003297500494625074, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003462375519356328, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00036272505440875815, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0003792125568818835, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0003957000593550089, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00041218756182813426, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00042867506430125963, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.000445162566774385, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00046165006924751037, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00047813757172063574, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0004946250741937611, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005111125766668865, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0005276000791400118, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0005440875816131373, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0005605750840862626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.000577062586559388, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0005935500890325133, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0006100375915056388, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0006265250939787641, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0006430125964518895, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0006595000989250148, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0006759876013981402, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0006924751038712656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.000708962606344391, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0007254501088175163, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0007419376112906417, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.000758425113763767, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0007749126162368925, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0007914001187100178, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0008078876211831432, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0008243751236562685, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008243751236562685, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4953.0287, | |
| "eval_samples_per_second": 5.156, | |
| "eval_steps_per_second": 2.578, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": 2.75713949171712e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |