| { | |
| "best_metric": 8.006572723388672, | |
| "best_model_checkpoint": "/workspaces/wakin_bake/trained_seq2seq/checkpoint-54", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 54, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 232.05528259277344, | |
| "learning_rate": 2.9444444444444445e-05, | |
| "loss": 15.5552, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 625.3634643554688, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 13.7158, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 241.36074829101562, | |
| "learning_rate": 2.8333333333333332e-05, | |
| "loss": 14.5239, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 144.937744140625, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 11.9337, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 59.95172119140625, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 12.6623, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 70.46778869628906, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 13.4721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 26.51784324645996, | |
| "learning_rate": 2.611111111111111e-05, | |
| "loss": 11.7672, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 34.07495880126953, | |
| "learning_rate": 2.5555555555555557e-05, | |
| "loss": 10.9863, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 17.962387084960938, | |
| "learning_rate": 2.5e-05, | |
| "loss": 11.6291, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 14.597478866577148, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 11.5824, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 18.746841430664062, | |
| "learning_rate": 2.388888888888889e-05, | |
| "loss": 12.5436, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 16.38216209411621, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 10.9329, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 12.897452354431152, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 10.3338, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 16.33725357055664, | |
| "learning_rate": 2.222222222222222e-05, | |
| "loss": 12.2682, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 16.713655471801758, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 11.125, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 12.658448219299316, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 10.3801, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9444444444444444, | |
| "grad_norm": 18.49787712097168, | |
| "learning_rate": 2.0555555555555558e-05, | |
| "loss": 11.9023, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 11.225893020629883, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 10.0598, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 8.97833251953125, | |
| "eval_runtime": 17.0971, | |
| "eval_samples_per_second": 0.468, | |
| "eval_steps_per_second": 0.117, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0555555555555556, | |
| "grad_norm": 17.131927490234375, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 11.6307, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 11.501855850219727, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 9.9624, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1666666666666667, | |
| "grad_norm": 18.79712677001953, | |
| "learning_rate": 1.8333333333333336e-05, | |
| "loss": 11.3912, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 14.980157852172852, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 9.997, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2777777777777777, | |
| "grad_norm": 17.382972717285156, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 9.7999, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 14.6889009475708, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 9.5019, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3888888888888888, | |
| "grad_norm": 11.028532028198242, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 8.4348, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 19.165592193603516, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 10.2169, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 11.539628028869629, | |
| "learning_rate": 1.5e-05, | |
| "loss": 8.5594, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 20.748764038085938, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 9.8663, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6111111111111112, | |
| "grad_norm": 25.90353012084961, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 10.4679, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 12.756267547607422, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 8.8323, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7222222222222223, | |
| "grad_norm": 27.25147247314453, | |
| "learning_rate": 1.2777777777777779e-05, | |
| "loss": 10.2936, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 14.550564765930176, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 8.4467, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8333333333333335, | |
| "grad_norm": 15.393588066101074, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 8.4903, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 22.393354415893555, | |
| "learning_rate": 1.111111111111111e-05, | |
| "loss": 8.7652, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.9444444444444444, | |
| "grad_norm": 24.291881561279297, | |
| "learning_rate": 1.0555555555555555e-05, | |
| "loss": 9.3748, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 30.40011215209961, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 9.7655, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 8.464545249938965, | |
| "eval_runtime": 13.5018, | |
| "eval_samples_per_second": 0.593, | |
| "eval_steps_per_second": 0.148, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0555555555555554, | |
| "grad_norm": 23.087289810180664, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 8.9217, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.111111111111111, | |
| "grad_norm": 26.975997924804688, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 8.8655, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.1666666666666665, | |
| "grad_norm": 28.121719360351562, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 9.1362, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 28.4269962310791, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 9.2849, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2777777777777777, | |
| "grad_norm": 31.212228775024414, | |
| "learning_rate": 7.222222222222222e-06, | |
| "loss": 9.5769, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 27.985774993896484, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 8.6151, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.388888888888889, | |
| "grad_norm": 29.317476272583008, | |
| "learning_rate": 6.111111111111111e-06, | |
| "loss": 8.8767, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": 16.052814483642578, | |
| "learning_rate": 5.555555555555555e-06, | |
| "loss": 7.3641, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 22.66093635559082, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 7.9935, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.5555555555555554, | |
| "grad_norm": 39.148033142089844, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 8.8332, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.611111111111111, | |
| "grad_norm": 39.017677307128906, | |
| "learning_rate": 3.888888888888889e-06, | |
| "loss": 8.779, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 26.151742935180664, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 7.5859, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.7222222222222223, | |
| "grad_norm": 32.05317306518555, | |
| "learning_rate": 2.7777777777777775e-06, | |
| "loss": 8.2961, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 31.795818328857422, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 8.156, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.8333333333333335, | |
| "grad_norm": 22.7334041595459, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 7.9457, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": 16.970556259155273, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 7.734, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.9444444444444446, | |
| "grad_norm": 31.753923416137695, | |
| "learning_rate": 5.555555555555555e-07, | |
| "loss": 7.925, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 22.566757202148438, | |
| "learning_rate": 0.0, | |
| "loss": 7.174, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 8.006572723388672, | |
| "eval_runtime": 32.8904, | |
| "eval_samples_per_second": 0.243, | |
| "eval_steps_per_second": 0.061, | |
| "step": 54 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 54, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 350, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 234047297028096.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |