| { | |
| "best_metric": 1.188790202140808, | |
| "best_model_checkpoint": "output_dir/checkpoint-24", | |
| "epoch": 0.7224835371589841, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 1.2047, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 1.2148, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8e-06, | |
| "loss": 1.2134, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.2068, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.1929587125778198, | |
| "eval_runtime": 4.3547, | |
| "eval_samples_per_second": 2.526, | |
| "eval_steps_per_second": 0.459, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3e-06, | |
| "loss": 1.2093, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.6e-06, | |
| "loss": 1.2063, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 1.211, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.2042, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.1931304931640625, | |
| "eval_runtime": 4.3471, | |
| "eval_samples_per_second": 2.53, | |
| "eval_steps_per_second": 0.46, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5.4e-06, | |
| "loss": 1.2042, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6e-06, | |
| "loss": 1.1951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.6e-06, | |
| "loss": 1.2194, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.2e-06, | |
| "loss": 1.1958, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.1925488710403442, | |
| "eval_runtime": 4.3544, | |
| "eval_samples_per_second": 2.526, | |
| "eval_steps_per_second": 0.459, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.8e-06, | |
| "loss": 1.2059, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 1.1939, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9e-06, | |
| "loss": 1.2042, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.1974, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.1915441751480103, | |
| "eval_runtime": 4.3592, | |
| "eval_samples_per_second": 2.523, | |
| "eval_steps_per_second": 0.459, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.02e-05, | |
| "loss": 1.1917, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.08e-05, | |
| "loss": 1.2156, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.1400000000000001e-05, | |
| "loss": 1.2204, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.1997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.190488576889038, | |
| "eval_runtime": 4.3516, | |
| "eval_samples_per_second": 2.528, | |
| "eval_steps_per_second": 0.46, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.26e-05, | |
| "loss": 1.2041, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.32e-05, | |
| "loss": 1.1954, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.3800000000000002e-05, | |
| "loss": 1.1951, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.44e-05, | |
| "loss": 1.2017, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.188790202140808, | |
| "eval_runtime": 4.3616, | |
| "eval_samples_per_second": 2.522, | |
| "eval_steps_per_second": 0.459, | |
| "step": 24 | |
| } | |
| ], | |
| "max_steps": 33, | |
| "num_train_epochs": 1, | |
| "total_flos": 4.871267940512563e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |