| { | |
| "best_metric": 2.2857847213745117, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-51", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 51, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 3.7881, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 4.2615, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.6935, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.9086, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 3.8796, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8213, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 3.7254, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 3.6606, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 3.5976, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 3.8338, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 3.4553, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 3.1551, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 3.2316, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 3.1069, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3202, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 3.3816, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 3.3071, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 17.7353, | |
| "eval_loss": 2.7330617904663086, | |
| "eval_rouge1": 25.7354, | |
| "eval_rouge2": 8.0265, | |
| "eval_rougeL": 20.6575, | |
| "eval_rougeLsum": 20.4561, | |
| "eval_runtime": 9.0856, | |
| "eval_samples_per_second": 3.742, | |
| "eval_steps_per_second": 0.33, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 3.601, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 3.4567, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 3.1369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.0047, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 3.0229, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 3.3503, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9631, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 2.9374, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 2.8602, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 2.7998, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 2.6807, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 2.9565, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 3.491, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 2.8686, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 2.5934, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8163, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 2.8732, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 18.6471, | |
| "eval_loss": 2.3937132358551025, | |
| "eval_rouge1": 24.2981, | |
| "eval_rouge2": 8.0449, | |
| "eval_rougeL": 20.8856, | |
| "eval_rougeLsum": 20.5578, | |
| "eval_runtime": 9.0634, | |
| "eval_samples_per_second": 3.751, | |
| "eval_steps_per_second": 0.331, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 2.7866, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.6704, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 2.8105, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 2.7682, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.6407, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 3.4932, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 2.894, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6731, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 2.6587, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 2.7535, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.4699, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 2.6562, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 2.7715, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 2.4702, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 2.6025, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 2.5201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.9425, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 18.7647, | |
| "eval_loss": 2.2857847213745117, | |
| "eval_rouge1": 21.0491, | |
| "eval_rouge2": 7.2608, | |
| "eval_rougeL": 18.1545, | |
| "eval_rougeLsum": 18.0438, | |
| "eval_runtime": 9.0812, | |
| "eval_samples_per_second": 3.744, | |
| "eval_steps_per_second": 0.33, | |
| "step": 51 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 51, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3525230985216.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |