| { | |
| "best_metric": 0.5895436406135559, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.39254170755642787, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015701668302257114, | |
| "grad_norm": 174.0449981689453, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015701668302257114, | |
| "eval_loss": 2.6159276962280273, | |
| "eval_runtime": 36.7437, | |
| "eval_samples_per_second": 11.703, | |
| "eval_steps_per_second": 1.47, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03140333660451423, | |
| "grad_norm": 532.1987915039062, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8384, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.047105004906771344, | |
| "grad_norm": 331.0499267578125, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.6012, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06280667320902845, | |
| "grad_norm": 2862.966552734375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.5431, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07850834151128558, | |
| "grad_norm": 347.0616760253906, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.8474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09421000981354269, | |
| "grad_norm": 279.2650146484375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6665, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1099116781157998, | |
| "grad_norm": 175.72076416015625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3088, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1256133464180569, | |
| "grad_norm": 103.9676284790039, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9821, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14131501472031405, | |
| "grad_norm": 86.11383056640625, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.784, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15701668302257116, | |
| "grad_norm": 75.49951171875, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.755, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17271835132482827, | |
| "grad_norm": 90.43276977539062, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7398, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18842001962708538, | |
| "grad_norm": 99.68488311767578, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8248, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2041216879293425, | |
| "grad_norm": 62.287628173828125, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8065, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2198233562315996, | |
| "grad_norm": 79.25579833984375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2336, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23552502453385674, | |
| "grad_norm": 166.92649841308594, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.0317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2512266928361138, | |
| "grad_norm": 49.47351837158203, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5492, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26692836113837093, | |
| "grad_norm": 106.59893035888672, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5018, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2826300294406281, | |
| "grad_norm": 61.971343994140625, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5298, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2983316977428852, | |
| "grad_norm": 35.90945053100586, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4862, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3140333660451423, | |
| "grad_norm": 37.26945495605469, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4935, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3297350343473994, | |
| "grad_norm": 46.713462829589844, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5518, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34543670264965654, | |
| "grad_norm": 32.227813720703125, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.599, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.36113837095191365, | |
| "grad_norm": 27.146421432495117, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4932, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.37684003925417076, | |
| "grad_norm": 34.5018424987793, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5336, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39254170755642787, | |
| "grad_norm": 27.01970100402832, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5115, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39254170755642787, | |
| "eval_loss": 0.5895436406135559, | |
| "eval_runtime": 37.3927, | |
| "eval_samples_per_second": 11.5, | |
| "eval_steps_per_second": 1.444, | |
| "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": 3.3417726519567974e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |