| { | |
| "best_metric": 1.1386715173721313, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.0752269779507135, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08300907911802853, | |
| "grad_norm": 3.467146396636963, | |
| "learning_rate": 0.0002989354846774545, | |
| "loss": 3.6542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08300907911802853, | |
| "eval_loss": 2.9620537757873535, | |
| "eval_runtime": 1.664, | |
| "eval_samples_per_second": 30.047, | |
| "eval_steps_per_second": 7.812, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16601815823605706, | |
| "grad_norm": 4.602604866027832, | |
| "learning_rate": 0.0002957587267523652, | |
| "loss": 2.9754, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2490272373540856, | |
| "grad_norm": 9.224260330200195, | |
| "learning_rate": 0.00029051982559491393, | |
| "loss": 2.2457, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3320363164721141, | |
| "grad_norm": 6.159036636352539, | |
| "learning_rate": 0.00028330140180592156, | |
| "loss": 2.5341, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4150453955901427, | |
| "grad_norm": 6.676574230194092, | |
| "learning_rate": 0.00027421729424061787, | |
| "loss": 1.8128, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4980544747081712, | |
| "grad_norm": 3.2664153575897217, | |
| "learning_rate": 0.0002634107647018905, | |
| "loss": 1.5817, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5810635538261998, | |
| "grad_norm": 2.6292076110839844, | |
| "learning_rate": 0.00025105223861607306, | |
| "loss": 2.3494, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6640726329442282, | |
| "grad_norm": 2.5120043754577637, | |
| "learning_rate": 0.00023733661732216452, | |
| "loss": 1.5132, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7470817120622568, | |
| "grad_norm": 4.4901814460754395, | |
| "learning_rate": 0.00022248020436128478, | |
| "loss": 1.4384, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8300907911802854, | |
| "grad_norm": 1.9909392595291138, | |
| "learning_rate": 0.00020671729424061788, | |
| "loss": 2.0038, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9130998702983139, | |
| "grad_norm": 3.3288509845733643, | |
| "learning_rate": 0.00019029647746907283, | |
| "loss": 1.3536, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9961089494163424, | |
| "grad_norm": 2.519279718399048, | |
| "learning_rate": 0.0001734767201364573, | |
| "loss": 1.0483, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0791180285343709, | |
| "grad_norm": 9.918027877807617, | |
| "learning_rate": 0.0001565232798635427, | |
| "loss": 3.532, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1621271076523996, | |
| "grad_norm": 2.53695011138916, | |
| "learning_rate": 0.00013970352253092714, | |
| "loss": 1.2221, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.245136186770428, | |
| "grad_norm": 2.4748690128326416, | |
| "learning_rate": 0.00012328270575938212, | |
| "loss": 1.0417, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3281452658884565, | |
| "grad_norm": 1.6321978569030762, | |
| "learning_rate": 0.00010751979563871518, | |
| "loss": 1.8484, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.411154345006485, | |
| "grad_norm": 1.4795855283737183, | |
| "learning_rate": 9.266338267783541e-05, | |
| "loss": 1.0031, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.4941634241245136, | |
| "grad_norm": 1.9086230993270874, | |
| "learning_rate": 7.894776138392688e-05, | |
| "loss": 0.9499, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.577172503242542, | |
| "grad_norm": 1.3793696165084839, | |
| "learning_rate": 6.658923529810946e-05, | |
| "loss": 1.7622, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.6601815823605706, | |
| "grad_norm": 1.6033817529678345, | |
| "learning_rate": 5.578270575938211e-05, | |
| "loss": 1.0468, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7431906614785992, | |
| "grad_norm": 2.249070167541504, | |
| "learning_rate": 4.669859819407844e-05, | |
| "loss": 0.9214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.8261997405966277, | |
| "grad_norm": 1.2679235935211182, | |
| "learning_rate": 3.948017440508607e-05, | |
| "loss": 1.6549, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9092088197146562, | |
| "grad_norm": 1.4422551393508911, | |
| "learning_rate": 3.4241273247634805e-05, | |
| "loss": 0.9849, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.9922178988326849, | |
| "grad_norm": 1.48310124874115, | |
| "learning_rate": 3.10645153225455e-05, | |
| "loss": 0.9386, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.0752269779507135, | |
| "grad_norm": 3.796576499938965, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.5664, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0752269779507135, | |
| "eval_loss": 1.1386715173721313, | |
| "eval_runtime": 1.6655, | |
| "eval_samples_per_second": 30.021, | |
| "eval_steps_per_second": 7.806, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 30, | |
| "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": 6.115492263624704e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |