| { | |
| "best_metric": 9.314793586730957, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.08210180623973727, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003284072249589491, | |
| "grad_norm": 5.0626983642578125, | |
| "learning_rate": 5e-05, | |
| "loss": 10.1534, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003284072249589491, | |
| "eval_loss": 10.289778709411621, | |
| "eval_runtime": 0.5713, | |
| "eval_samples_per_second": 87.527, | |
| "eval_steps_per_second": 22.757, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006568144499178982, | |
| "grad_norm": 4.237027645111084, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3178, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 3.833760976791382, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.4493, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013136288998357963, | |
| "grad_norm": 3.885283946990967, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.4143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016420361247947456, | |
| "grad_norm": 3.647639751434326, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.2325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 3.458007574081421, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.2275, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022988505747126436, | |
| "grad_norm": 3.5521318912506104, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.089, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026272577996715927, | |
| "grad_norm": 3.2706851959228516, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 9.9827, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": 3.162849187850952, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 9.6735, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03284072249589491, | |
| "grad_norm": 3.4256649017333984, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 9.6991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0361247947454844, | |
| "grad_norm": 3.1439263820648193, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 9.4494, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03940886699507389, | |
| "grad_norm": 3.6793322563171387, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 9.4807, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042692939244663386, | |
| "grad_norm": 3.272399663925171, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 9.4473, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04597701149425287, | |
| "grad_norm": 3.0414819717407227, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 9.6337, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 2.6899259090423584, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 9.596, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.052545155993431854, | |
| "grad_norm": 2.572854518890381, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 9.5432, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05582922824302135, | |
| "grad_norm": 2.417119026184082, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.6109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.059113300492610835, | |
| "grad_norm": 2.414215087890625, | |
| "learning_rate": 7.75e-05, | |
| "loss": 9.5861, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06239737274220033, | |
| "grad_norm": 2.457582950592041, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.5782, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06568144499178982, | |
| "grad_norm": 2.355839490890503, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.4318, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 2.5010826587677, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.409, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0722495894909688, | |
| "grad_norm": 2.6175942420959473, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.1827, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0755336617405583, | |
| "grad_norm": 3.066164016723633, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 9.1461, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "grad_norm": 3.4586806297302246, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.2352, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08210180623973727, | |
| "grad_norm": 4.095075607299805, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 9.306, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08210180623973727, | |
| "eval_loss": 9.314793586730957, | |
| "eval_runtime": 0.5512, | |
| "eval_samples_per_second": 90.714, | |
| "eval_steps_per_second": 23.586, | |
| "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": 116006898892800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |