| { | |
| "best_metric": 2.0798914432525635, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.14342058085335246, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005736823234134099, | |
| "grad_norm": 1.0254684686660767, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4173, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005736823234134099, | |
| "eval_loss": 2.756528854370117, | |
| "eval_runtime": 2.271, | |
| "eval_samples_per_second": 22.016, | |
| "eval_steps_per_second": 5.724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011473646468268197, | |
| "grad_norm": 1.3013254404067993, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4681, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017210469702402295, | |
| "grad_norm": 1.187984824180603, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.5124, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022947292936536395, | |
| "grad_norm": 0.864932656288147, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.3035, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02868411617067049, | |
| "grad_norm": 1.027928113937378, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.3102, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03442093940480459, | |
| "grad_norm": 1.039202094078064, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2879, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.040157762638938686, | |
| "grad_norm": 0.8895488977432251, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.3463, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04589458587307279, | |
| "grad_norm": 0.8706251978874207, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.3098, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.051631409107206885, | |
| "grad_norm": 0.9032915830612183, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.2915, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05736823234134098, | |
| "grad_norm": 0.7826951742172241, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.2719, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06310505557547508, | |
| "grad_norm": 0.8883889317512512, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.2135, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06884187880960918, | |
| "grad_norm": 0.9226004481315613, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.352, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07457870204374328, | |
| "grad_norm": 0.9469476342201233, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.1279, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08031552527787737, | |
| "grad_norm": 0.728985071182251, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.0353, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08605234851201148, | |
| "grad_norm": 0.9158313870429993, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.0043, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09178917174614558, | |
| "grad_norm": 0.7416771054267883, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0701, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09752599498027967, | |
| "grad_norm": 0.6386289596557617, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.1131, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10326281821441377, | |
| "grad_norm": 0.7471883296966553, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.1982, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10899964144854786, | |
| "grad_norm": 0.8133168816566467, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.2225, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11473646468268196, | |
| "grad_norm": 0.6914170980453491, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.1752, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12047328791681607, | |
| "grad_norm": 0.7954630851745605, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.1777, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12621011115095015, | |
| "grad_norm": 0.7441710829734802, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.224, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13194693438508426, | |
| "grad_norm": 0.6862707138061523, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.2437, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13768375761921836, | |
| "grad_norm": 0.7326493859291077, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.2941, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14342058085335246, | |
| "grad_norm": 0.9635663628578186, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.1895, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14342058085335246, | |
| "eval_loss": 2.0798914432525635, | |
| "eval_runtime": 2.3185, | |
| "eval_samples_per_second": 21.565, | |
| "eval_steps_per_second": 5.607, | |
| "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": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |