| { | |
| "best_metric": 0.22512628138065338, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05522192310347208, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022088769241388833, | |
| "grad_norm": 17.61588478088379, | |
| "learning_rate": 1.25e-05, | |
| "loss": 3.9116, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022088769241388833, | |
| "eval_loss": 5.86042594909668, | |
| "eval_runtime": 2.0601, | |
| "eval_samples_per_second": 24.27, | |
| "eval_steps_per_second": 6.31, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0044177538482777666, | |
| "grad_norm": 18.221654891967773, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.2731, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006626630772416649, | |
| "grad_norm": 18.73583984375, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 4.2538, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008835507696555533, | |
| "grad_norm": 16.894182205200195, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5849, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011044384620694415, | |
| "grad_norm": 13.671380996704102, | |
| "learning_rate": 6.25e-05, | |
| "loss": 2.4494, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013253261544833299, | |
| "grad_norm": 14.39706039428711, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5397, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015462138468972183, | |
| "grad_norm": 36.43305587768555, | |
| "learning_rate": 8.75e-05, | |
| "loss": 4.0588, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017671015393111066, | |
| "grad_norm": 29.52732276916504, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5498, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019879892317249948, | |
| "grad_norm": 15.871655464172363, | |
| "learning_rate": 9.999397620593029e-05, | |
| "loss": 0.7469, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02208876924138883, | |
| "grad_norm": 37.426918029785156, | |
| "learning_rate": 9.997590643643647e-05, | |
| "loss": 0.2828, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024297646165527716, | |
| "grad_norm": 38.68975830078125, | |
| "learning_rate": 9.994579552923277e-05, | |
| "loss": 0.4165, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.026506523089666598, | |
| "grad_norm": 3.2423059940338135, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.0656, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02871540001380548, | |
| "grad_norm": 21.096725463867188, | |
| "learning_rate": 9.984948576891312e-05, | |
| "loss": 1.0799, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030924276937944365, | |
| "grad_norm": 10.848109245300293, | |
| "learning_rate": 9.978331270024886e-05, | |
| "loss": 0.4541, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.033133153862083244, | |
| "grad_norm": 3.0925045013427734, | |
| "learning_rate": 9.9705150055875e-05, | |
| "loss": 0.0921, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03534203078622213, | |
| "grad_norm": 0.7270008325576782, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.012, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.037550907710361014, | |
| "grad_norm": 2.127373695373535, | |
| "learning_rate": 9.951294294841516e-05, | |
| "loss": 0.006, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.039759784634499896, | |
| "grad_norm": 13.903672218322754, | |
| "learning_rate": 9.939894994381957e-05, | |
| "loss": 0.0372, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04196866155863878, | |
| "grad_norm": 0.047538336366415024, | |
| "learning_rate": 9.927307026671848e-05, | |
| "loss": 0.0005, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04417753848277766, | |
| "grad_norm": 0.12976495921611786, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.0015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04638641540691654, | |
| "grad_norm": 0.053914595395326614, | |
| "learning_rate": 9.898578887246075e-05, | |
| "loss": 0.0006, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04859529233105543, | |
| "grad_norm": 0.016516996547579765, | |
| "learning_rate": 9.882446406748002e-05, | |
| "loss": 0.0002, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05080416925519431, | |
| "grad_norm": 0.004742575343698263, | |
| "learning_rate": 9.865140639375449e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.053013046179333195, | |
| "grad_norm": 0.001722239889204502, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05522192310347208, | |
| "grad_norm": 0.0011573476949706674, | |
| "learning_rate": 9.827028089573329e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05522192310347208, | |
| "eval_loss": 0.22512628138065338, | |
| "eval_runtime": 2.0717, | |
| "eval_samples_per_second": 24.135, | |
| "eval_steps_per_second": 6.275, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "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": 8.1240447254528e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |