| { | |
| "best_metric": 6.913173675537109, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.011883894352179208, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047535577408716834, | |
| "grad_norm": 0.2816944420337677, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047535577408716834, | |
| "eval_loss": 6.9411163330078125, | |
| "eval_runtime": 2.2114, | |
| "eval_samples_per_second": 22.611, | |
| "eval_steps_per_second": 5.879, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009507115481743367, | |
| "grad_norm": 0.25802749395370483, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9376, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001426067322261505, | |
| "grad_norm": 0.244500532746315, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9349, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019014230963486734, | |
| "grad_norm": 0.24236252903938293, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9347, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002376778870435842, | |
| "grad_norm": 0.2415142059326172, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.933, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00285213464452301, | |
| "grad_norm": 0.2429618239402771, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.9313, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033274904186101784, | |
| "grad_norm": 0.2322567105293274, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.9315, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038028461926973467, | |
| "grad_norm": 0.21697010099887848, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.9299, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004278201966784515, | |
| "grad_norm": 0.20793764293193817, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.9323, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004753557740871684, | |
| "grad_norm": 0.20627593994140625, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.9293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005228913514958852, | |
| "grad_norm": 0.17280302941799164, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.9335, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00570426928904602, | |
| "grad_norm": 0.1537674367427826, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.9351, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006179625063133189, | |
| "grad_norm": 0.33964458107948303, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.9212, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006654980837220357, | |
| "grad_norm": 0.3010113835334778, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.9189, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007130336611307526, | |
| "grad_norm": 0.27440688014030457, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.9158, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007605692385394693, | |
| "grad_norm": 0.27747219800949097, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.9154, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008081048159481862, | |
| "grad_norm": 0.27966931462287903, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.9156, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00855640393356903, | |
| "grad_norm": 0.27389419078826904, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.9134, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0090317597076562, | |
| "grad_norm": 0.27709779143333435, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.9137, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009507115481743367, | |
| "grad_norm": 0.2647261321544647, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.9127, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009982471255830535, | |
| "grad_norm": 0.2580931782722473, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.9136, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010457827029917705, | |
| "grad_norm": 0.2511126399040222, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.9131, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010933182804004873, | |
| "grad_norm": 0.19859854876995087, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.9198, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01140853857809204, | |
| "grad_norm": 0.16508285701274872, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.9241, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011883894352179208, | |
| "grad_norm": 0.2387620210647583, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.9247, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011883894352179208, | |
| "eval_loss": 6.913173675537109, | |
| "eval_runtime": 0.0886, | |
| "eval_samples_per_second": 564.04, | |
| "eval_steps_per_second": 146.65, | |
| "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": 3118662336512.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |