| { | |
| "best_metric": 2.532271385192871, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0007702617349375318, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0810469397501274e-05, | |
| "grad_norm": 5.867096900939941, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.0810469397501274e-05, | |
| "eval_loss": 2.679687023162842, | |
| "eval_runtime": 521.0237, | |
| "eval_samples_per_second": 26.229, | |
| "eval_steps_per_second": 13.115, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.162093879500255e-05, | |
| "grad_norm": 5.904790878295898, | |
| "learning_rate": 4e-05, | |
| "loss": 11.897, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.243140819250382e-05, | |
| "grad_norm": 5.405601501464844, | |
| "learning_rate": 6e-05, | |
| "loss": 10.1774, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001232418775900051, | |
| "grad_norm": 5.622509479522705, | |
| "learning_rate": 8e-05, | |
| "loss": 10.1616, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015405234698750636, | |
| "grad_norm": 7.414961814880371, | |
| "learning_rate": 0.0001, | |
| "loss": 10.9382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00015405234698750636, | |
| "eval_loss": 2.6631760597229004, | |
| "eval_runtime": 520.7036, | |
| "eval_samples_per_second": 26.245, | |
| "eval_steps_per_second": 13.123, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018486281638500763, | |
| "grad_norm": 6.764425754547119, | |
| "learning_rate": 0.00012, | |
| "loss": 12.5051, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002156732857825089, | |
| "grad_norm": 6.588749885559082, | |
| "learning_rate": 0.00014, | |
| "loss": 11.0627, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002464837551800102, | |
| "grad_norm": 7.026829242706299, | |
| "learning_rate": 0.00016, | |
| "loss": 10.2568, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00027729422457751146, | |
| "grad_norm": 5.693941593170166, | |
| "learning_rate": 0.00018, | |
| "loss": 9.478, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003081046939750127, | |
| "grad_norm": 5.87098503112793, | |
| "learning_rate": 0.0002, | |
| "loss": 11.5869, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003081046939750127, | |
| "eval_loss": 2.6051371097564697, | |
| "eval_runtime": 519.5629, | |
| "eval_samples_per_second": 26.303, | |
| "eval_steps_per_second": 13.151, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000338915163372514, | |
| "grad_norm": 7.2281928062438965, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 9.7121, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00036972563277001526, | |
| "grad_norm": 7.50088357925415, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 10.5311, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00040053610216751653, | |
| "grad_norm": 6.620040416717529, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 9.3888, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0004313465715650178, | |
| "grad_norm": 8.688164710998535, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 9.7954, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00046215704096251906, | |
| "grad_norm": 9.269744873046875, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 11.455, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00046215704096251906, | |
| "eval_loss": 2.561781883239746, | |
| "eval_runtime": 518.8295, | |
| "eval_samples_per_second": 26.34, | |
| "eval_steps_per_second": 13.17, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004929675103600204, | |
| "grad_norm": 8.370804786682129, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 9.3559, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005237779797575217, | |
| "grad_norm": 8.053985595703125, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 10.4722, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005545884491550229, | |
| "grad_norm": 9.712014198303223, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 10.2615, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005853989185525242, | |
| "grad_norm": 7.817999839782715, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 9.4811, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006162093879500255, | |
| "grad_norm": 8.400493621826172, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 9.1112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006162093879500255, | |
| "eval_loss": 2.539055585861206, | |
| "eval_runtime": 511.8649, | |
| "eval_samples_per_second": 26.698, | |
| "eval_steps_per_second": 13.349, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006470198573475267, | |
| "grad_norm": 7.9703145027160645, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 9.5349, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000677830326745028, | |
| "grad_norm": 8.338407516479492, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 9.5837, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0007086407961425293, | |
| "grad_norm": 8.587491035461426, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 10.2255, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007394512655400305, | |
| "grad_norm": 7.686610698699951, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 11.9067, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007702617349375318, | |
| "grad_norm": 7.370700836181641, | |
| "learning_rate": 0.0, | |
| "loss": 11.1744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007702617349375318, | |
| "eval_loss": 2.532271385192871, | |
| "eval_runtime": 528.8853, | |
| "eval_samples_per_second": 25.839, | |
| "eval_steps_per_second": 12.92, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 65811486081024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |