| { | |
| "best_metric": 2.3570337295532227, | |
| "best_model_checkpoint": "output/grimes/checkpoint-168", | |
| "epoch": 8.0, | |
| "global_step": 168, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011888735840752609, | |
| "loss": 2.8697, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.372648442002871e-05, | |
| "loss": 2.7244, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.5828599592490882e-05, | |
| "loss": 2.5533, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.662053209561833e-07, | |
| "loss": 2.4558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.552718162536621, | |
| "eval_runtime": 1.4059, | |
| "eval_samples_per_second": 22.762, | |
| "eval_steps_per_second": 2.845, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.1920020081922749e-05, | |
| "loss": 2.436, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.333506393059682e-05, | |
| "loss": 2.4972, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 2.1316, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00013415229447692924, | |
| "loss": 2.3666, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.45241641998291, | |
| "eval_runtime": 1.4175, | |
| "eval_samples_per_second": 22.575, | |
| "eval_steps_per_second": 2.822, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00013040646433810595, | |
| "loss": 2.2004, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 9.36623942715347e-05, | |
| "loss": 2.2352, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.3537605728465284e-05, | |
| "loss": 1.9823, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 6.793535661894062e-06, | |
| "loss": 2.0814, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.412614583969116, | |
| "eval_runtime": 1.4325, | |
| "eval_samples_per_second": 22.338, | |
| "eval_steps_per_second": 2.792, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.047705523070765e-06, | |
| "loss": 1.9043, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.4300000000000014e-05, | |
| "loss": 2.0794, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 8.386493606940314e-05, | |
| "loss": 1.767, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00012527997991807721, | |
| "loss": 2.0631, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.377373456954956, | |
| "eval_runtime": 1.4484, | |
| "eval_samples_per_second": 22.093, | |
| "eval_steps_per_second": 2.762, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00013643379467904383, | |
| "loss": 2.0061, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00011137140040750914, | |
| "loss": 1.6506, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 6.347351557997137e-05, | |
| "loss": 1.9202, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 1.8312641592473912e-05, | |
| "loss": 1.9009, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.7547, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.376068592071533, | |
| "eval_runtime": 1.4234, | |
| "eval_samples_per_second": 22.481, | |
| "eval_steps_per_second": 2.81, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 1.8312641592473936e-05, | |
| "loss": 1.6331, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 6.347351557997117e-05, | |
| "loss": 1.7732, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.00011137140040750908, | |
| "loss": 1.7347, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.00013643379467904383, | |
| "loss": 1.5963, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.3798959255218506, | |
| "eval_runtime": 1.4389, | |
| "eval_samples_per_second": 22.239, | |
| "eval_steps_per_second": 2.78, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.0001252799799180772, | |
| "loss": 1.5787, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 8.386493606940322e-05, | |
| "loss": 1.3787, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 3.429999999999998e-05, | |
| "loss": 1.4709, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 3.0477055230707115e-06, | |
| "loss": 1.7318, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.3730082511901855, | |
| "eval_runtime": 1.4477, | |
| "eval_samples_per_second": 22.104, | |
| "eval_steps_per_second": 2.763, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 6.793535661894024e-06, | |
| "loss": 1.4261, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 4.353760572846532e-05, | |
| "loss": 1.2714, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 9.366239427153457e-05, | |
| "loss": 1.3748, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 0.00013040646433810593, | |
| "loss": 1.5499, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.3570337295532227, | |
| "eval_runtime": 1.4478, | |
| "eval_samples_per_second": 22.102, | |
| "eval_steps_per_second": 2.763, | |
| "step": 168 | |
| } | |
| ], | |
| "max_steps": 210, | |
| "num_train_epochs": 10, | |
| "total_flos": 175588245504000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |