| { | |
| "best_metric": 11.059524536132812, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.00044076357882395464, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7630543152958186e-05, | |
| "grad_norm": 1.2864186763763428, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3172, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7630543152958186e-05, | |
| "eval_loss": 11.080211639404297, | |
| "eval_runtime": 157.8291, | |
| "eval_samples_per_second": 151.316, | |
| "eval_steps_per_second": 75.658, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.526108630591637e-05, | |
| "grad_norm": 1.1442649364471436, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3623, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.2891629458874556e-05, | |
| "grad_norm": 1.320364236831665, | |
| "learning_rate": 6e-05, | |
| "loss": 44.2724, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.052217261183275e-05, | |
| "grad_norm": 1.1162445545196533, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3297, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.815271576479092e-05, | |
| "grad_norm": 1.2065627574920654, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3505, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.815271576479092e-05, | |
| "eval_loss": 11.079597473144531, | |
| "eval_runtime": 154.6193, | |
| "eval_samples_per_second": 154.457, | |
| "eval_steps_per_second": 77.228, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010578325891774911, | |
| "grad_norm": 1.129872441291809, | |
| "learning_rate": 0.00012, | |
| "loss": 44.3087, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001234138020707073, | |
| "grad_norm": 1.278194546699524, | |
| "learning_rate": 0.00014, | |
| "loss": 44.3065, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001410443452236655, | |
| "grad_norm": 0.9755666851997375, | |
| "learning_rate": 0.00016, | |
| "loss": 44.3318, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015867488837662365, | |
| "grad_norm": 1.103223204612732, | |
| "learning_rate": 0.00018, | |
| "loss": 44.3202, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00017630543152958184, | |
| "grad_norm": 1.0434162616729736, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3092, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00017630543152958184, | |
| "eval_loss": 11.074006080627441, | |
| "eval_runtime": 154.9175, | |
| "eval_samples_per_second": 154.159, | |
| "eval_steps_per_second": 77.08, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00019393597468254003, | |
| "grad_norm": 1.1925216913223267, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.2824, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00021156651783549822, | |
| "grad_norm": 1.1967883110046387, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.287, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002291970609884564, | |
| "grad_norm": 1.1843236684799194, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.2499, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0002468276041414146, | |
| "grad_norm": 1.2098557949066162, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.2345, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0002644581472943728, | |
| "grad_norm": 1.283496379852295, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.2413, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002644581472943728, | |
| "eval_loss": 11.064728736877441, | |
| "eval_runtime": 155.3564, | |
| "eval_samples_per_second": 153.724, | |
| "eval_steps_per_second": 76.862, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000282088690447331, | |
| "grad_norm": 1.2000702619552612, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.2442, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002997192336002891, | |
| "grad_norm": 1.1320544481277466, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.2807, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0003173497767532473, | |
| "grad_norm": 1.0614330768585205, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.2788, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0003349803199062055, | |
| "grad_norm": 1.0958316326141357, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.2804, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0003526108630591637, | |
| "grad_norm": 1.0989373922348022, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.2736, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003526108630591637, | |
| "eval_loss": 11.060052871704102, | |
| "eval_runtime": 156.1013, | |
| "eval_samples_per_second": 152.99, | |
| "eval_steps_per_second": 76.495, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003702414062121219, | |
| "grad_norm": 1.2673594951629639, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 44.2516, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00038787194936508007, | |
| "grad_norm": 1.0727105140686035, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 44.2384, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00040550249251803826, | |
| "grad_norm": 1.2554271221160889, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 44.2502, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00042313303567099645, | |
| "grad_norm": 1.1639366149902344, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 44.2355, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00044076357882395464, | |
| "grad_norm": 1.2954105138778687, | |
| "learning_rate": 0.0, | |
| "loss": 44.2127, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00044076357882395464, | |
| "eval_loss": 11.059524536132812, | |
| "eval_runtime": 156.1425, | |
| "eval_samples_per_second": 152.95, | |
| "eval_steps_per_second": 76.475, | |
| "step": 25 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 37355520000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |