| { | |
| "best_metric": 3.763901472091675, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.10244589576130106, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004097835830452042, | |
| "grad_norm": 8.17273235321045, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004097835830452042, | |
| "eval_loss": 6.038059234619141, | |
| "eval_runtime": 4.7663, | |
| "eval_samples_per_second": 10.49, | |
| "eval_steps_per_second": 2.727, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008195671660904085, | |
| "grad_norm": 8.440423011779785, | |
| "learning_rate": 0.0001, | |
| "loss": 5.9822, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012293507491356128, | |
| "grad_norm": 6.372066497802734, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.4229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01639134332180817, | |
| "grad_norm": 5.9859232902526855, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.6798, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02048917915226021, | |
| "grad_norm": 6.160243988037109, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.703, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024587014982712256, | |
| "grad_norm": 3.177950620651245, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.5104, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028684850813164298, | |
| "grad_norm": 2.2837774753570557, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.2898, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03278268664361634, | |
| "grad_norm": 1.5388017892837524, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.2678, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03688052247406838, | |
| "grad_norm": 3.053107500076294, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.1682, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04097835830452042, | |
| "grad_norm": 2.493290901184082, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.1832, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04507619413497247, | |
| "grad_norm": 1.949349284172058, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.1423, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04917402996542451, | |
| "grad_norm": 2.94350266456604, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.1833, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.053271865795876554, | |
| "grad_norm": 1.939968466758728, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 4.0466, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.057369701626328595, | |
| "grad_norm": 2.102407932281494, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.0055, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06146753745678064, | |
| "grad_norm": 1.9021189212799072, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.9682, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06556537328723268, | |
| "grad_norm": 1.7222744226455688, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.9069, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06966320911768473, | |
| "grad_norm": 1.8017946481704712, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.912, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07376104494813676, | |
| "grad_norm": 1.1817983388900757, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.7766, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07785888077858881, | |
| "grad_norm": 1.441970944404602, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.7548, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08195671660904084, | |
| "grad_norm": 1.084867238998413, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.7368, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08605455243949289, | |
| "grad_norm": 1.1046688556671143, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.8319, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09015238826994494, | |
| "grad_norm": 1.216025710105896, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.701, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09425022410039698, | |
| "grad_norm": 1.1603436470031738, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.7036, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09834805993084902, | |
| "grad_norm": 1.6205642223358154, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.8242, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10244589576130106, | |
| "grad_norm": 1.2837269306182861, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.9515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10244589576130106, | |
| "eval_loss": 3.763901472091675, | |
| "eval_runtime": 4.8358, | |
| "eval_samples_per_second": 10.34, | |
| "eval_steps_per_second": 2.688, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.087239672233984e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |