| { | |
| "best_metric": 0.2730916738510132, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.2872340425531914, | |
| "eval_steps": 25, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 6.59408712387085, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7204, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "eval_loss": 3.381442070007324, | |
| "eval_runtime": 1.1045, | |
| "eval_samples_per_second": 45.269, | |
| "eval_steps_per_second": 11.77, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 10.311667442321777, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 5.0694756507873535, | |
| "learning_rate": 9.964516155915151e-05, | |
| "loss": 1.3925, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 5.360514163970947, | |
| "learning_rate": 9.858624225078841e-05, | |
| "loss": 1.1657, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 2.4355216026306152, | |
| "learning_rate": 9.683994186497132e-05, | |
| "loss": 0.3886, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 1.3297368288040161, | |
| "learning_rate": 9.443380060197387e-05, | |
| "loss": 0.343, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7943262411347518, | |
| "grad_norm": 1.8409028053283691, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.2877, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.9078014184397163, | |
| "grad_norm": 1.5093427896499634, | |
| "learning_rate": 8.780358823396352e-05, | |
| "loss": 0.3318, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.0957446808510638, | |
| "grad_norm": 1.9956127405166626, | |
| "learning_rate": 8.368407953869104e-05, | |
| "loss": 0.3998, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.2092198581560283, | |
| "grad_norm": 0.972147524356842, | |
| "learning_rate": 7.911220577405484e-05, | |
| "loss": 0.2114, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.322695035460993, | |
| "grad_norm": 0.6361852884292603, | |
| "learning_rate": 7.416006812042828e-05, | |
| "loss": 0.2205, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.4361702127659575, | |
| "grad_norm": 0.7156177759170532, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.1946, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.549645390070922, | |
| "grad_norm": 0.5892674326896667, | |
| "learning_rate": 6.343215915635762e-05, | |
| "loss": 0.2051, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.6631205673758864, | |
| "grad_norm": 1.7911550998687744, | |
| "learning_rate": 5.782557337881911e-05, | |
| "loss": 0.228, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.7765957446808511, | |
| "grad_norm": 0.4857326149940491, | |
| "learning_rate": 5.2174426621180906e-05, | |
| "loss": 0.1389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.8900709219858156, | |
| "grad_norm": 0.5573811531066895, | |
| "learning_rate": 4.6567840843642384e-05, | |
| "loss": 0.2438, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.078014184397163, | |
| "grad_norm": 0.8138695359230042, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 0.2988, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.1914893617021276, | |
| "grad_norm": 0.35432174801826477, | |
| "learning_rate": 3.583993187957173e-05, | |
| "loss": 0.1847, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.3049645390070923, | |
| "grad_norm": 0.3583293557167053, | |
| "learning_rate": 3.088779422594514e-05, | |
| "loss": 0.1463, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.4184397163120566, | |
| "grad_norm": 0.46635663509368896, | |
| "learning_rate": 2.6315920461308964e-05, | |
| "loss": 0.1928, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.5319148936170213, | |
| "grad_norm": 0.3333394527435303, | |
| "learning_rate": 2.219641176603649e-05, | |
| "loss": 0.1615, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.645390070921986, | |
| "grad_norm": 0.3103781044483185, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 0.1591, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.7588652482269502, | |
| "grad_norm": 0.24234576523303986, | |
| "learning_rate": 1.556619939802615e-05, | |
| "loss": 0.1287, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.872340425531915, | |
| "grad_norm": 0.3493451178073883, | |
| "learning_rate": 1.3160058135028691e-05, | |
| "loss": 0.1555, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.0602836879432624, | |
| "grad_norm": 0.4571143388748169, | |
| "learning_rate": 1.1413757749211602e-05, | |
| "loss": 0.1864, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.0602836879432624, | |
| "eval_loss": 0.2730916738510132, | |
| "eval_runtime": 1.1024, | |
| "eval_samples_per_second": 45.355, | |
| "eval_steps_per_second": 11.792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.173758865248227, | |
| "grad_norm": 0.3071691393852234, | |
| "learning_rate": 1.0354838440848503e-05, | |
| "loss": 0.1519, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.2872340425531914, | |
| "grad_norm": 0.2735120356082916, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1463, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 27, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.773968303489024e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |