| { | |
| "best_metric": 1.821385145187378, | |
| "best_model_checkpoint": "autotrain-egbhl-hdsiz/checkpoint-80", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.0, | |
| "loss": 4.5433, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 26.819583892822266, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 2.9431, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 24.515037536621094, | |
| "learning_rate": 1.25e-05, | |
| "loss": 3.5482, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 12.873324394226074, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 2.4086, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 15.799155235290527, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 2.8477, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 23.742237091064453, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.297, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 14.426471710205078, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 2.1671, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 14.933609008789062, | |
| "learning_rate": 4.9537037037037035e-05, | |
| "loss": 1.8833, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 19.533145904541016, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 2.1878, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 35.50374984741211, | |
| "learning_rate": 4.768518518518519e-05, | |
| "loss": 1.8188, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 17.651580810546875, | |
| "learning_rate": 4.675925925925926e-05, | |
| "loss": 2.0148, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 14.465134620666504, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 2.0613, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 13.421053886413574, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 2.5974, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 17.738975524902344, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 2.1862, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 10.630866050720215, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 1.9854, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 13.5612211227417, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 2.3207, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 12.230231285095215, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 2.1946, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 10.226851463317871, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 2.0726, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 17.564428329467773, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 1.8402, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 16.211181640625, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.7316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 19.05, | |
| "eval_loss": 1.8881380558013916, | |
| "eval_rouge1": 55.9005, | |
| "eval_rouge2": 39.684, | |
| "eval_rougeL": 53.7239, | |
| "eval_rougeLsum": 53.5879, | |
| "eval_runtime": 2.3238, | |
| "eval_samples_per_second": 8.606, | |
| "eval_steps_per_second": 2.152, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 11.123723030090332, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 1.8779, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 17.29766845703125, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.2122, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 11.228723526000977, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 1.1288, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 16.350183486938477, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 1.6717, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 73.40056610107422, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 1.6587, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 23.507516860961914, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.1566, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 13.975730895996094, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 1.1459, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 12.104181289672852, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 1.1564, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 9.906718254089355, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 1.564, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 11.82476806640625, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 1.8214, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 11.349201202392578, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 1.8952, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 7.890576362609863, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.0706, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 19.47081184387207, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 1.5111, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 10.134727478027344, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 1.4847, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 10.425029754638672, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0191, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 10.284099578857422, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 1.8213, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 13.63291072845459, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 1.0306, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 12.470438003540039, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.7619, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 17.98394012451172, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 1.2194, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 9.503134727478027, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 1.1788, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 19.15, | |
| "eval_loss": 1.821385145187378, | |
| "eval_rouge1": 55.4476, | |
| "eval_rouge2": 40.4173, | |
| "eval_rougeL": 53.9637, | |
| "eval_rougeLsum": 53.9177, | |
| "eval_runtime": 2.3273, | |
| "eval_samples_per_second": 8.594, | |
| "eval_steps_per_second": 2.148, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 120, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 42923062050816.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |