| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007223084979594785, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002889233991837914, | |
| "grad_norm": 66.85765075683594, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 26.6527, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002889233991837914, | |
| "eval_loss": 4.310550689697266, | |
| "eval_runtime": 990.545, | |
| "eval_samples_per_second": 2.943, | |
| "eval_steps_per_second": 1.472, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005778467983675828, | |
| "grad_norm": 73.37711334228516, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 43.7611, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008667701975513742, | |
| "grad_norm": 65.6069107055664, | |
| "learning_rate": 0.0001, | |
| "loss": 26.0857, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011556935967351656, | |
| "grad_norm": 59.228843688964844, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 28.3396, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001444616995918957, | |
| "grad_norm": 24.407468795776367, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 22.8091, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017335403951027485, | |
| "grad_norm": 19.40464973449707, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 21.675, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0020224637942865397, | |
| "grad_norm": 21.251638412475586, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 17.9579, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002311387193470331, | |
| "grad_norm": 41.2540168762207, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 16.5047, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0026003105926541226, | |
| "grad_norm": 22.907991409301758, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 15.6627, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002889233991837914, | |
| "grad_norm": 37.04414367675781, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 17.3563, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031781573910217055, | |
| "grad_norm": 21.000375747680664, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 14.7146, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003467080790205497, | |
| "grad_norm": 18.32266616821289, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 12.4842, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003756004189389288, | |
| "grad_norm": 27.443967819213867, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 10.4003, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004044927588573079, | |
| "grad_norm": 42.203514099121094, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 8.0634, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004333850987756871, | |
| "grad_norm": 162.54161071777344, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 12.063, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004622774386940662, | |
| "grad_norm": 36.060081481933594, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 8.8787, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004911697786124454, | |
| "grad_norm": 52.42499923706055, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 8.1511, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005200621185308245, | |
| "grad_norm": 49.18842697143555, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.8164, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005489544584492036, | |
| "grad_norm": 28.918075561523438, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 7.1671, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005778467983675828, | |
| "grad_norm": 18.048503875732422, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 8.5257, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006067391382859619, | |
| "grad_norm": 18.87720489501953, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.431, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006356314782043411, | |
| "grad_norm": 19.41789436340332, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 7.1162, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006645238181227202, | |
| "grad_norm": 19.061424255371094, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 7.5901, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006934161580410994, | |
| "grad_norm": 16.62812614440918, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 5.7933, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007223084979594785, | |
| "grad_norm": 28.045270919799805, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 6.6255, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007223084979594785, | |
| "eval_loss": 1.1299744844436646, | |
| "eval_runtime": 994.88, | |
| "eval_samples_per_second": 2.93, | |
| "eval_steps_per_second": 1.466, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.28697269714944e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |