| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 12.67427122940431, |
| "global_step": 10000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.63, |
| "eval_loss": 3.0458309650421143, |
| "eval_runtime": 143.841, |
| "eval_samples_per_second": 32.835, |
| "eval_steps_per_second": 2.739, |
| "eval_wer": 1.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 9.98e-05, |
| "loss": 2.9181, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.27, |
| "eval_loss": 1.1502786874771118, |
| "eval_runtime": 143.5317, |
| "eval_samples_per_second": 32.906, |
| "eval_steps_per_second": 2.745, |
| "eval_wer": 0.4722885713129023, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.9, |
| "eval_loss": 0.8274601101875305, |
| "eval_runtime": 142.4484, |
| "eval_samples_per_second": 33.156, |
| "eval_steps_per_second": 2.766, |
| "eval_wer": 0.3499858305331768, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 8.89111111111111e-05, |
| "loss": 0.7646, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.53, |
| "eval_loss": 0.6990081667900085, |
| "eval_runtime": 145.8955, |
| "eval_samples_per_second": 32.372, |
| "eval_steps_per_second": 2.701, |
| "eval_wer": 0.2845228938099672, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.17, |
| "eval_loss": 0.5828294157981873, |
| "eval_runtime": 147.7617, |
| "eval_samples_per_second": 31.964, |
| "eval_steps_per_second": 2.666, |
| "eval_wer": 0.2508602890571232, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.8, |
| "learning_rate": 7.780000000000001e-05, |
| "loss": 0.5394, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.8, |
| "eval_loss": 0.5363064408302307, |
| "eval_runtime": 147.8939, |
| "eval_samples_per_second": 31.935, |
| "eval_steps_per_second": 2.664, |
| "eval_wer": 0.24873486903364236, |
| "step": 3000 |
| }, |
| { |
| "epoch": 4.44, |
| "eval_loss": 0.5467007756233215, |
| "eval_runtime": 151.8112, |
| "eval_samples_per_second": 31.111, |
| "eval_steps_per_second": 2.595, |
| "eval_wer": 0.21711671592243229, |
| "step": 3500 |
| }, |
| { |
| "epoch": 5.07, |
| "learning_rate": 6.66888888888889e-05, |
| "loss": 0.4558, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.07, |
| "eval_loss": 0.5289521813392639, |
| "eval_runtime": 152.3052, |
| "eval_samples_per_second": 31.01, |
| "eval_steps_per_second": 2.587, |
| "eval_wer": 0.20901987773774341, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.7, |
| "eval_loss": 0.4992470443248749, |
| "eval_runtime": 148.0991, |
| "eval_samples_per_second": 31.891, |
| "eval_steps_per_second": 2.66, |
| "eval_wer": 0.20464758511801143, |
| "step": 4500 |
| }, |
| { |
| "epoch": 6.34, |
| "learning_rate": 5.558888888888889e-05, |
| "loss": 0.3773, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.34, |
| "eval_loss": 0.49340707063674927, |
| "eval_runtime": 155.8909, |
| "eval_samples_per_second": 30.297, |
| "eval_steps_per_second": 2.527, |
| "eval_wer": 0.2051738796000162, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.97, |
| "eval_loss": 0.47003018856048584, |
| "eval_runtime": 146.5312, |
| "eval_samples_per_second": 32.232, |
| "eval_steps_per_second": 2.689, |
| "eval_wer": 0.19827132504756892, |
| "step": 5500 |
| }, |
| { |
| "epoch": 7.6, |
| "learning_rate": 4.447777777777778e-05, |
| "loss": 0.3301, |
| "step": 6000 |
| }, |
| { |
| "epoch": 7.6, |
| "eval_loss": 0.4938233494758606, |
| "eval_runtime": 154.4839, |
| "eval_samples_per_second": 30.573, |
| "eval_steps_per_second": 2.55, |
| "eval_wer": 0.18738107768916237, |
| "step": 6000 |
| }, |
| { |
| "epoch": 8.24, |
| "eval_loss": 0.5363861322402954, |
| "eval_runtime": 163.224, |
| "eval_samples_per_second": 28.936, |
| "eval_steps_per_second": 2.414, |
| "eval_wer": 0.18934456094894944, |
| "step": 6500 |
| }, |
| { |
| "epoch": 8.87, |
| "learning_rate": 3.336666666666667e-05, |
| "loss": 0.2938, |
| "step": 7000 |
| }, |
| { |
| "epoch": 8.87, |
| "eval_loss": 0.5169841051101685, |
| "eval_runtime": 164.5878, |
| "eval_samples_per_second": 28.696, |
| "eval_steps_per_second": 2.394, |
| "eval_wer": 0.18300878506943039, |
| "step": 7000 |
| }, |
| { |
| "epoch": 9.51, |
| "eval_loss": 0.5407580733299255, |
| "eval_runtime": 163.5687, |
| "eval_samples_per_second": 28.875, |
| "eval_steps_per_second": 2.409, |
| "eval_wer": 0.18149062790980122, |
| "step": 7500 |
| }, |
| { |
| "epoch": 10.14, |
| "learning_rate": 2.225555555555556e-05, |
| "loss": 0.2674, |
| "step": 8000 |
| }, |
| { |
| "epoch": 10.14, |
| "eval_loss": 0.5580623149871826, |
| "eval_runtime": 162.7994, |
| "eval_samples_per_second": 29.011, |
| "eval_steps_per_second": 2.42, |
| "eval_wer": 0.173272337152342, |
| "step": 8000 |
| }, |
| { |
| "epoch": 10.77, |
| "eval_loss": 0.538887083530426, |
| "eval_runtime": 163.5851, |
| "eval_samples_per_second": 28.872, |
| "eval_steps_per_second": 2.409, |
| "eval_wer": 0.1719161167564066, |
| "step": 8500 |
| }, |
| { |
| "epoch": 11.41, |
| "learning_rate": 1.1144444444444445e-05, |
| "loss": 0.24, |
| "step": 9000 |
| }, |
| { |
| "epoch": 11.41, |
| "eval_loss": 0.5344488024711609, |
| "eval_runtime": 163.7329, |
| "eval_samples_per_second": 28.846, |
| "eval_steps_per_second": 2.406, |
| "eval_wer": 0.17141006436986356, |
| "step": 9000 |
| }, |
| { |
| "epoch": 12.04, |
| "eval_loss": 0.5502966046333313, |
| "eval_runtime": 154.8226, |
| "eval_samples_per_second": 30.506, |
| "eval_steps_per_second": 2.545, |
| "eval_wer": 0.16863689729160763, |
| "step": 9500 |
| }, |
| { |
| "epoch": 12.67, |
| "learning_rate": 3.3333333333333334e-08, |
| "loss": 0.211, |
| "step": 10000 |
| }, |
| { |
| "epoch": 12.67, |
| "eval_loss": 0.5595183372497559, |
| "eval_runtime": 157.1471, |
| "eval_samples_per_second": 30.055, |
| "eval_steps_per_second": 2.507, |
| "eval_wer": 0.16865713938706936, |
| "step": 10000 |
| }, |
| { |
| "epoch": 12.67, |
| "step": 10000, |
| "total_flos": 2.7136568655380324e+19, |
| "train_loss": 0.6397389862060547, |
| "train_runtime": 13054.0758, |
| "train_samples_per_second": 18.385, |
| "train_steps_per_second": 0.766 |
| } |
| ], |
| "max_steps": 10000, |
| "num_train_epochs": 13, |
| "total_flos": 2.7136568655380324e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
