| { | |
| "best_metric": 0.30335336923599243, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01778845084828675, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00071153803393147, | |
| "grad_norm": 4.1395392417907715, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.1572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00071153803393147, | |
| "eval_loss": 4.378438949584961, | |
| "eval_runtime": 3.4572, | |
| "eval_samples_per_second": 14.463, | |
| "eval_steps_per_second": 3.76, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00142307606786294, | |
| "grad_norm": 4.174035549163818, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.5344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00213461410179441, | |
| "grad_norm": 4.1275458335876465, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00284615213572588, | |
| "grad_norm": 3.8864400386810303, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 3.1984, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00355769016965735, | |
| "grad_norm": 5.862198829650879, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 2.5223, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00426922820358882, | |
| "grad_norm": 4.417128562927246, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.8482, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00498076623752029, | |
| "grad_norm": 3.6660585403442383, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.3222, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00569230427145176, | |
| "grad_norm": 2.8245842456817627, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 0.9788, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00640384230538323, | |
| "grad_norm": 2.523778200149536, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.7001, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0071153803393147, | |
| "grad_norm": 2.617717742919922, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.5022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00782691837324617, | |
| "grad_norm": 2.721231698989868, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.4812, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00853845640717764, | |
| "grad_norm": 2.917170524597168, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.407, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00924999444110911, | |
| "grad_norm": 4.139233112335205, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.965, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00996153247504058, | |
| "grad_norm": 3.3612873554229736, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.7595, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01067307050897205, | |
| "grad_norm": 3.3063018321990967, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5902, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01138460854290352, | |
| "grad_norm": 3.0980429649353027, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.4998, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01209614657683499, | |
| "grad_norm": 1.7593947649002075, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.3775, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01280768461076646, | |
| "grad_norm": 0.964061439037323, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.3036, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01351922264469793, | |
| "grad_norm": 1.0408120155334473, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.2508, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0142307606786294, | |
| "grad_norm": 0.7718386650085449, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.1979, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01494229871256087, | |
| "grad_norm": 1.073320746421814, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.1971, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01565383674649234, | |
| "grad_norm": 0.6882893443107605, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.1843, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01636537478042381, | |
| "grad_norm": 0.8627312183380127, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.1888, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01707691281435528, | |
| "grad_norm": 0.8838256597518921, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1508, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01778845084828675, | |
| "grad_norm": 1.3713014125823975, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.1561, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01778845084828675, | |
| "eval_loss": 0.30335336923599243, | |
| "eval_runtime": 3.496, | |
| "eval_samples_per_second": 14.302, | |
| "eval_steps_per_second": 3.719, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 2.984041808658432e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |