| { | |
| "best_metric": 1.2492481470108032, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.032208712456719545, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012883484982687816, | |
| "grad_norm": 41.074459075927734, | |
| "learning_rate": 5e-05, | |
| "loss": 63.858, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012883484982687816, | |
| "eval_loss": 3.9600865840911865, | |
| "eval_runtime": 4.6029, | |
| "eval_samples_per_second": 10.863, | |
| "eval_steps_per_second": 2.824, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025766969965375633, | |
| "grad_norm": 39.653533935546875, | |
| "learning_rate": 0.0001, | |
| "loss": 64.808, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038650454948063453, | |
| "grad_norm": 40.987003326416016, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 69.3187, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0051533939930751265, | |
| "grad_norm": 45.15346908569336, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 65.6071, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006441742491343909, | |
| "grad_norm": 33.79973602294922, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 47.4306, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007730090989612691, | |
| "grad_norm": 40.15324020385742, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 46.1572, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009018439487881473, | |
| "grad_norm": 39.12355422973633, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 40.6804, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010306787986150253, | |
| "grad_norm": 33.08439254760742, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 35.9482, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011595136484419035, | |
| "grad_norm": 26.991741180419922, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 34.3955, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012883484982687817, | |
| "grad_norm": 21.47414207458496, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 28.7994, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0141718334809566, | |
| "grad_norm": 46.37200164794922, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 28.7715, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015460181979225381, | |
| "grad_norm": 45.901329040527344, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 28.0989, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016748530477494163, | |
| "grad_norm": 77.20433044433594, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 28.8962, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018036878975762945, | |
| "grad_norm": 185.42774963378906, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 25.8943, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019325227474031724, | |
| "grad_norm": 299.84588623046875, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 27.0279, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020613575972300506, | |
| "grad_norm": 105.05233001708984, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 27.1692, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021901924470569288, | |
| "grad_norm": 48.8776741027832, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 27.1052, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02319027296883807, | |
| "grad_norm": 42.15166091918945, | |
| "learning_rate": 7.75e-05, | |
| "loss": 25.2864, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024478621467106852, | |
| "grad_norm": 38.06427764892578, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 24.3782, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025766969965375634, | |
| "grad_norm": 35.02044677734375, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 22.4459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027055318463644416, | |
| "grad_norm": 20.02016830444336, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 21.0181, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0283436669619132, | |
| "grad_norm": 16.83022117614746, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 19.7452, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02963201546018198, | |
| "grad_norm": 29.09676742553711, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 19.312, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030920363958450763, | |
| "grad_norm": 20.50575065612793, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 22.3072, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.032208712456719545, | |
| "grad_norm": 27.935426712036133, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 23.8577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032208712456719545, | |
| "eval_loss": 1.2492481470108032, | |
| "eval_runtime": 4.6519, | |
| "eval_samples_per_second": 10.748, | |
| "eval_steps_per_second": 2.795, | |
| "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": 2.629578157719552e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |