| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2844950213371266, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005689900426742532, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005689900426742532, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.3837, | |
| "eval_samples_per_second": 10.022, | |
| "eval_steps_per_second": 5.011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011379800853485065, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017069701280227598, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02275960170697013, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02844950213371266, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.034139402560455195, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03982930298719772, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04551920341394026, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.051209103840682786, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05689900426742532, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06258890469416785, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06827880512091039, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07396870554765292, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07965860597439545, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08534850640113797, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09103840682788052, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09672830725462304, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10241820768136557, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11379800853485064, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11948790896159317, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1251778093883357, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13086770981507823, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13655761024182078, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1422475106685633, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1422475106685633, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.3949, | |
| "eval_samples_per_second": 10.007, | |
| "eval_steps_per_second": 5.003, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14793741109530584, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.15362731152204837, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1593172119487909, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.16500711237553342, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.17069701280227595, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1763869132290185, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.18207681365576103, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.18776671408250356, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1934566145092461, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.19914651493598862, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.20483641536273114, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.22190611664295876, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.22759601706970128, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2332859174964438, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.23897581792318634, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.24466571834992887, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2503556187766714, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.25604551920341395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26173541963015645, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.267425320056899, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.27311522048364156, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.27880512091038406, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2844950213371266, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2844950213371266, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.4049, | |
| "eval_samples_per_second": 9.993, | |
| "eval_steps_per_second": 4.997, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 1.02936877203456e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |