| { | |
| "best_metric": 1.5246868133544922, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.04405286343612335, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022026431718061676, | |
| "grad_norm": 3.4757564067840576, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022026431718061676, | |
| "eval_loss": 2.5590243339538574, | |
| "eval_runtime": 41.8925, | |
| "eval_samples_per_second": 4.583, | |
| "eval_steps_per_second": 2.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004405286343612335, | |
| "grad_norm": 2.078887939453125, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2218, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006607929515418502, | |
| "grad_norm": 2.3378193378448486, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0489, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00881057268722467, | |
| "grad_norm": 3.0119824409484863, | |
| "learning_rate": 8e-05, | |
| "loss": 2.475, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011013215859030838, | |
| "grad_norm": 2.1958980560302734, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011013215859030838, | |
| "eval_loss": 2.417128324508667, | |
| "eval_runtime": 48.6401, | |
| "eval_samples_per_second": 3.947, | |
| "eval_steps_per_second": 1.974, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013215859030837005, | |
| "grad_norm": 1.8279132843017578, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7968, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015418502202643172, | |
| "grad_norm": 2.1999881267547607, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3432, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01762114537444934, | |
| "grad_norm": 2.385622501373291, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0073, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019823788546255508, | |
| "grad_norm": 2.94974422454834, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022026431718061675, | |
| "grad_norm": 2.4951744079589844, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7185, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022026431718061675, | |
| "eval_loss": 1.875498652458191, | |
| "eval_runtime": 38.808, | |
| "eval_samples_per_second": 4.947, | |
| "eval_steps_per_second": 2.474, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024229074889867842, | |
| "grad_norm": 2.7306602001190186, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.9021, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02643171806167401, | |
| "grad_norm": 3.5390207767486572, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.6349, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028634361233480177, | |
| "grad_norm": 2.431853771209717, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.5561, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030837004405286344, | |
| "grad_norm": 3.1448302268981934, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.4886, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03303964757709251, | |
| "grad_norm": 2.6476869583129883, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.4281, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03303964757709251, | |
| "eval_loss": 1.6235097646713257, | |
| "eval_runtime": 37.9515, | |
| "eval_samples_per_second": 5.059, | |
| "eval_steps_per_second": 2.53, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03524229074889868, | |
| "grad_norm": 2.862135171890259, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.7633, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.037444933920704845, | |
| "grad_norm": 2.980224609375, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.5178, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.039647577092511016, | |
| "grad_norm": 2.1248018741607666, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.2964, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04185022026431718, | |
| "grad_norm": 2.7156856060028076, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.5673, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04405286343612335, | |
| "grad_norm": 2.016173839569092, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.5975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04405286343612335, | |
| "eval_loss": 1.5246868133544922, | |
| "eval_runtime": 36.6734, | |
| "eval_samples_per_second": 5.235, | |
| "eval_steps_per_second": 2.618, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 249306858651648.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |