| { | |
| "best_metric": 0.3849843144416809, | |
| "best_model_checkpoint": "autotrain-rj5xv-b9wsb/checkpoint-1584", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1584, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04734848484848485, | |
| "grad_norm": 4.511193752288818, | |
| "learning_rate": 7.861635220125786e-06, | |
| "loss": 2.8758, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0946969696969697, | |
| "grad_norm": 3.8025200366973877, | |
| "learning_rate": 1.572327044025157e-05, | |
| "loss": 2.3043, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14204545454545456, | |
| "grad_norm": 2.95987868309021, | |
| "learning_rate": 2.358490566037736e-05, | |
| "loss": 1.5836, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1893939393939394, | |
| "grad_norm": 3.758180618286133, | |
| "learning_rate": 3.144654088050314e-05, | |
| "loss": 1.4148, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23674242424242425, | |
| "grad_norm": 1.9288899898529053, | |
| "learning_rate": 3.9308176100628936e-05, | |
| "loss": 1.0447, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2840909090909091, | |
| "grad_norm": 2.4479756355285645, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 0.7194, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3314393939393939, | |
| "grad_norm": 3.4983065128326416, | |
| "learning_rate": 4.943859649122807e-05, | |
| "loss": 0.8141, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.3787878787878788, | |
| "grad_norm": 2.1139252185821533, | |
| "learning_rate": 4.856140350877193e-05, | |
| "loss": 0.8187, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.42613636363636365, | |
| "grad_norm": 2.1289165019989014, | |
| "learning_rate": 4.7684210526315794e-05, | |
| "loss": 0.8632, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.4734848484848485, | |
| "grad_norm": 3.188091516494751, | |
| "learning_rate": 4.680701754385965e-05, | |
| "loss": 0.7706, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5208333333333334, | |
| "grad_norm": 3.666327714920044, | |
| "learning_rate": 4.592982456140351e-05, | |
| "loss": 0.6436, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5681818181818182, | |
| "grad_norm": 3.153630256652832, | |
| "learning_rate": 4.5052631578947366e-05, | |
| "loss": 0.5896, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.615530303030303, | |
| "grad_norm": 1.9767557382583618, | |
| "learning_rate": 4.417543859649123e-05, | |
| "loss": 0.6594, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.6628787878787878, | |
| "grad_norm": 1.0973279476165771, | |
| "learning_rate": 4.329824561403509e-05, | |
| "loss": 0.7358, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7102272727272727, | |
| "grad_norm": 3.707737922668457, | |
| "learning_rate": 4.242105263157895e-05, | |
| "loss": 0.5802, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 1.6052640676498413, | |
| "learning_rate": 4.1543859649122806e-05, | |
| "loss": 0.5345, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8049242424242424, | |
| "grad_norm": 2.5281245708465576, | |
| "learning_rate": 4.066666666666667e-05, | |
| "loss": 0.5426, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.8522727272727273, | |
| "grad_norm": 1.1469014883041382, | |
| "learning_rate": 3.978947368421053e-05, | |
| "loss": 0.4517, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8996212121212122, | |
| "grad_norm": 2.1793298721313477, | |
| "learning_rate": 3.891228070175439e-05, | |
| "loss": 0.5795, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.946969696969697, | |
| "grad_norm": 1.2433311939239502, | |
| "learning_rate": 3.8035087719298247e-05, | |
| "loss": 0.4883, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9943181818181818, | |
| "grad_norm": 1.057558536529541, | |
| "learning_rate": 3.715789473684211e-05, | |
| "loss": 0.6399, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 18.9849, | |
| "eval_loss": 0.45811647176742554, | |
| "eval_rouge1": 45.943, | |
| "eval_rouge2": 41.8728, | |
| "eval_rougeL": 45.3719, | |
| "eval_rougeLsum": 45.5844, | |
| "eval_runtime": 638.6799, | |
| "eval_samples_per_second": 0.415, | |
| "eval_steps_per_second": 0.105, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.0416666666666667, | |
| "grad_norm": 0.9785796999931335, | |
| "learning_rate": 3.628070175438596e-05, | |
| "loss": 0.4255, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0890151515151516, | |
| "grad_norm": 2.2381393909454346, | |
| "learning_rate": 3.5403508771929825e-05, | |
| "loss": 0.4439, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.1363636363636362, | |
| "grad_norm": 2.753933906555176, | |
| "learning_rate": 3.452631578947369e-05, | |
| "loss": 0.5136, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.183712121212121, | |
| "grad_norm": 1.5527116060256958, | |
| "learning_rate": 3.364912280701755e-05, | |
| "loss": 0.3932, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.231060606060606, | |
| "grad_norm": 0.6465177536010742, | |
| "learning_rate": 3.2771929824561403e-05, | |
| "loss": 0.5194, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.2784090909090908, | |
| "grad_norm": 1.6484010219573975, | |
| "learning_rate": 3.1894736842105265e-05, | |
| "loss": 0.4773, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.3257575757575757, | |
| "grad_norm": 1.9873112440109253, | |
| "learning_rate": 3.101754385964912e-05, | |
| "loss": 0.4183, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.3731060606060606, | |
| "grad_norm": 2.486020803451538, | |
| "learning_rate": 3.0140350877192985e-05, | |
| "loss": 0.6344, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.4204545454545454, | |
| "grad_norm": 1.8892446756362915, | |
| "learning_rate": 2.9263157894736844e-05, | |
| "loss": 0.4328, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.4678030303030303, | |
| "grad_norm": 0.961203932762146, | |
| "learning_rate": 2.8385964912280705e-05, | |
| "loss": 0.5562, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "grad_norm": 0.44476789236068726, | |
| "learning_rate": 2.750877192982456e-05, | |
| "loss": 0.3306, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": 0.9097229838371277, | |
| "learning_rate": 2.6631578947368426e-05, | |
| "loss": 0.3695, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.6098484848484849, | |
| "grad_norm": 1.3498631715774536, | |
| "learning_rate": 2.575438596491228e-05, | |
| "loss": 0.3705, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.6571969696969697, | |
| "grad_norm": 0.6882970929145813, | |
| "learning_rate": 2.4877192982456142e-05, | |
| "loss": 0.5327, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.7045454545454546, | |
| "grad_norm": 0.7746265530586243, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.3751, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.7518939393939394, | |
| "grad_norm": 1.2026286125183105, | |
| "learning_rate": 2.312280701754386e-05, | |
| "loss": 0.2608, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.7992424242424243, | |
| "grad_norm": 5.0856099128723145, | |
| "learning_rate": 2.224561403508772e-05, | |
| "loss": 0.4432, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.8465909090909092, | |
| "grad_norm": 2.294633150100708, | |
| "learning_rate": 2.136842105263158e-05, | |
| "loss": 0.5151, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.893939393939394, | |
| "grad_norm": 1.039154052734375, | |
| "learning_rate": 2.0491228070175437e-05, | |
| "loss": 0.3376, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.941287878787879, | |
| "grad_norm": 1.9636164903640747, | |
| "learning_rate": 1.96140350877193e-05, | |
| "loss": 0.4545, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.9886363636363638, | |
| "grad_norm": 1.2051464319229126, | |
| "learning_rate": 1.8736842105263158e-05, | |
| "loss": 0.5154, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 18.9887, | |
| "eval_loss": 0.3989172577857971, | |
| "eval_rouge1": 46.097, | |
| "eval_rouge2": 42.2086, | |
| "eval_rougeL": 45.6885, | |
| "eval_rougeLsum": 45.7885, | |
| "eval_runtime": 648.8496, | |
| "eval_samples_per_second": 0.408, | |
| "eval_steps_per_second": 0.103, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 2.0359848484848486, | |
| "grad_norm": 0.8088118433952332, | |
| "learning_rate": 1.785964912280702e-05, | |
| "loss": 0.4052, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.0833333333333335, | |
| "grad_norm": 0.8511497974395752, | |
| "learning_rate": 1.6982456140350878e-05, | |
| "loss": 0.2922, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.1306818181818183, | |
| "grad_norm": 1.41793954372406, | |
| "learning_rate": 1.6105263157894736e-05, | |
| "loss": 0.1893, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.178030303030303, | |
| "grad_norm": 0.5501357316970825, | |
| "learning_rate": 1.5228070175438596e-05, | |
| "loss": 0.3815, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.225378787878788, | |
| "grad_norm": 0.7588028311729431, | |
| "learning_rate": 1.4350877192982456e-05, | |
| "loss": 0.3866, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 1.9546937942504883, | |
| "learning_rate": 1.3473684210526316e-05, | |
| "loss": 0.3575, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.320075757575758, | |
| "grad_norm": 0.6162445545196533, | |
| "learning_rate": 1.2596491228070176e-05, | |
| "loss": 0.5128, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.367424242424242, | |
| "grad_norm": 2.0828588008880615, | |
| "learning_rate": 1.1719298245614036e-05, | |
| "loss": 0.4164, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.4147727272727275, | |
| "grad_norm": 1.3566968441009521, | |
| "learning_rate": 1.0842105263157895e-05, | |
| "loss": 0.3453, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.462121212121212, | |
| "grad_norm": 0.7142326235771179, | |
| "learning_rate": 9.964912280701755e-06, | |
| "loss": 0.4117, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.5094696969696972, | |
| "grad_norm": 2.7209577560424805, | |
| "learning_rate": 9.087719298245615e-06, | |
| "loss": 0.3381, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.5568181818181817, | |
| "grad_norm": 2.0031161308288574, | |
| "learning_rate": 8.210526315789475e-06, | |
| "loss": 0.2646, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.6041666666666665, | |
| "grad_norm": 0.36383265256881714, | |
| "learning_rate": 7.333333333333334e-06, | |
| "loss": 0.3025, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.6515151515151514, | |
| "grad_norm": 2.464855194091797, | |
| "learning_rate": 6.456140350877193e-06, | |
| "loss": 0.3774, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.6988636363636362, | |
| "grad_norm": 2.341742515563965, | |
| "learning_rate": 5.578947368421053e-06, | |
| "loss": 0.3929, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.746212121212121, | |
| "grad_norm": 0.6026067137718201, | |
| "learning_rate": 4.7017543859649125e-06, | |
| "loss": 0.4215, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.793560606060606, | |
| "grad_norm": 1.8426591157913208, | |
| "learning_rate": 3.8245614035087725e-06, | |
| "loss": 0.2499, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 2.840909090909091, | |
| "grad_norm": 1.0914125442504883, | |
| "learning_rate": 2.9473684210526317e-06, | |
| "loss": 0.3535, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.8882575757575757, | |
| "grad_norm": 0.6658899784088135, | |
| "learning_rate": 2.0701754385964913e-06, | |
| "loss": 0.3272, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 2.9356060606060606, | |
| "grad_norm": 0.7760673761367798, | |
| "learning_rate": 1.192982456140351e-06, | |
| "loss": 0.4175, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.9829545454545454, | |
| "grad_norm": 1.258583426475525, | |
| "learning_rate": 3.1578947368421055e-07, | |
| "loss": 0.4278, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 18.9849, | |
| "eval_loss": 0.3849843144416809, | |
| "eval_rouge1": 46.2037, | |
| "eval_rouge2": 42.3541, | |
| "eval_rougeL": 45.8784, | |
| "eval_rougeLsum": 45.9787, | |
| "eval_runtime": 656.7129, | |
| "eval_samples_per_second": 0.404, | |
| "eval_steps_per_second": 0.102, | |
| "step": 1584 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1584, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 390532125671424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |