| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2317720907774022, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00772573635924674, | |
| "grad_norm": 0.0652494952082634, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9262, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00772573635924674, | |
| "eval_loss": 11.928458213806152, | |
| "eval_runtime": 16.6092, | |
| "eval_samples_per_second": 13.185, | |
| "eval_steps_per_second": 6.623, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01545147271849348, | |
| "grad_norm": 0.07395407557487488, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9359, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02317720907774022, | |
| "grad_norm": 0.06961611658334732, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9329, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03090294543698696, | |
| "grad_norm": 0.06199463829398155, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9383, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0386286817962337, | |
| "grad_norm": 0.07943562418222427, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04635441815548044, | |
| "grad_norm": 0.06378127634525299, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9223, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05408015451472718, | |
| "grad_norm": 0.07464384287595749, | |
| "learning_rate": 7e-05, | |
| "loss": 11.9215, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06180589087397392, | |
| "grad_norm": 0.0745854601264, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9247, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06180589087397392, | |
| "eval_loss": 11.92805004119873, | |
| "eval_runtime": 1.0766, | |
| "eval_samples_per_second": 203.416, | |
| "eval_steps_per_second": 102.172, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06953162723322066, | |
| "grad_norm": 0.09723018854856491, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9271, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0772573635924674, | |
| "grad_norm": 0.06599853187799454, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9294, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08498309995171414, | |
| "grad_norm": 0.08143449574708939, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 11.9204, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09270883631096088, | |
| "grad_norm": 0.06527712196111679, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.9218, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10043457267020763, | |
| "grad_norm": 0.04510502144694328, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 11.932, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10816030902945437, | |
| "grad_norm": 0.0751844048500061, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.9265, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1158860453887011, | |
| "grad_norm": 0.05361689627170563, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9278, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12361178174794785, | |
| "grad_norm": 0.09501861780881882, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 11.9095, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12361178174794785, | |
| "eval_loss": 11.927022933959961, | |
| "eval_runtime": 1.0762, | |
| "eval_samples_per_second": 203.491, | |
| "eval_steps_per_second": 102.21, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1313375181071946, | |
| "grad_norm": 0.06664367020130157, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 11.9275, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13906325446644133, | |
| "grad_norm": 0.09336207807064056, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.9289, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 0.07334022969007492, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 11.9191, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1545147271849348, | |
| "grad_norm": 0.054979972541332245, | |
| "learning_rate": 5e-05, | |
| "loss": 11.927, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16224046354418156, | |
| "grad_norm": 0.059893086552619934, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 11.9292, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1699661999034283, | |
| "grad_norm": 0.062082719057798386, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 11.9272, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17769193626267504, | |
| "grad_norm": 0.06688153743743896, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 11.9169, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.18541767262192177, | |
| "grad_norm": 0.05168774351477623, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 11.92, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18541767262192177, | |
| "eval_loss": 11.926448822021484, | |
| "eval_runtime": 1.1157, | |
| "eval_samples_per_second": 196.289, | |
| "eval_steps_per_second": 98.593, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.19314340898116852, | |
| "grad_norm": 0.07490590214729309, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9273, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20086914534041525, | |
| "grad_norm": 0.06475649774074554, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.9329, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.208594881699662, | |
| "grad_norm": 0.05650734528899193, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 11.9241, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21632061805890873, | |
| "grad_norm": 0.0597919225692749, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 11.9358, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22404635441815549, | |
| "grad_norm": 0.06450095772743225, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 11.9166, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2317720907774022, | |
| "grad_norm": 0.06534530222415924, | |
| "learning_rate": 0.0, | |
| "loss": 11.9311, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 179872727040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |