| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021815848572345205, | |
| "eval_steps": 17, | |
| "global_step": 85, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025665704202759064, | |
| "eval_loss": 2.767350435256958, | |
| "eval_runtime": 491.4277, | |
| "eval_samples_per_second": 13.355, | |
| "eval_steps_per_second": 1.671, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007699711260827719, | |
| "grad_norm": 0.3417242467403412, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015399422521655437, | |
| "grad_norm": 0.35272517800331116, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7375, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023099133782483157, | |
| "grad_norm": 0.350046306848526, | |
| "learning_rate": 9e-05, | |
| "loss": 2.6718, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0030798845043310875, | |
| "grad_norm": 0.3014596104621887, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 2.5993, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0038498556304138597, | |
| "grad_norm": 0.3522738218307495, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 2.5303, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00436316971446904, | |
| "eval_loss": 2.5289151668548584, | |
| "eval_runtime": 493.8022, | |
| "eval_samples_per_second": 13.291, | |
| "eval_steps_per_second": 1.663, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0046198267564966315, | |
| "grad_norm": 0.3675502836704254, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 2.4945, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005389797882579404, | |
| "grad_norm": 0.4536501169204712, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 2.5246, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006159769008662175, | |
| "grad_norm": 0.39700689911842346, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 2.4664, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006929740134744947, | |
| "grad_norm": 0.3603559732437134, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 2.4274, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007699711260827719, | |
| "grad_norm": 0.368173211812973, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 2.4661, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00846968238691049, | |
| "grad_norm": 0.35239627957344055, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 2.3349, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00872633942893808, | |
| "eval_loss": 2.3943283557891846, | |
| "eval_runtime": 493.7443, | |
| "eval_samples_per_second": 13.292, | |
| "eval_steps_per_second": 1.663, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009239653512993263, | |
| "grad_norm": 0.3209523558616638, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 2.4035, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010009624639076035, | |
| "grad_norm": 0.33573678135871887, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 2.3783, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010779595765158807, | |
| "grad_norm": 0.3218136131763458, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 2.4247, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011549566891241578, | |
| "grad_norm": 0.30115804076194763, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 2.3915, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01231953801732435, | |
| "grad_norm": 0.34325042366981506, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.3639, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013089509143407122, | |
| "grad_norm": 0.3467099666595459, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 2.3171, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.013089509143407122, | |
| "eval_loss": 2.341045379638672, | |
| "eval_runtime": 494.2874, | |
| "eval_samples_per_second": 13.278, | |
| "eval_steps_per_second": 1.661, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.013859480269489894, | |
| "grad_norm": 0.3275759220123291, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 2.3057, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.014629451395572667, | |
| "grad_norm": 0.29645541310310364, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 2.3326, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.015399422521655439, | |
| "grad_norm": 0.3317429721355438, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 2.3392, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01616939364773821, | |
| "grad_norm": 0.3201993405818939, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 2.3972, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.01693936477382098, | |
| "grad_norm": 0.3513089716434479, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 2.3498, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.01745267885787616, | |
| "eval_loss": 2.3205010890960693, | |
| "eval_runtime": 493.7323, | |
| "eval_samples_per_second": 13.293, | |
| "eval_steps_per_second": 1.663, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.017709335899903755, | |
| "grad_norm": 0.3993850648403168, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 2.2755, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.018479307025986526, | |
| "grad_norm": 0.3162781000137329, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 2.3094, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.019249278152069296, | |
| "grad_norm": 0.33009400963783264, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 2.3131, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02001924927815207, | |
| "grad_norm": 0.30170515179634094, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 2.2769, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.02078922040423484, | |
| "grad_norm": 0.36391210556030273, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 2.3464, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.021559191530317615, | |
| "grad_norm": 0.34589123725891113, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 2.3523, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.021815848572345205, | |
| "eval_loss": 2.3070456981658936, | |
| "eval_runtime": 494.1111, | |
| "eval_samples_per_second": 13.282, | |
| "eval_steps_per_second": 1.662, | |
| "step": 85 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2294651397747507e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |