| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5022341376228776, | |
| "eval_steps": 200, | |
| "global_step": 1400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.9598, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.3436, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.8791261911392212, | |
| "eval_runtime": 1327.8534, | |
| "eval_samples_per_second": 0.753, | |
| "eval_steps_per_second": 0.047, | |
| "eval_wer": 0.8870904221802143, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 6e-06, | |
| "loss": 1.5788, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.1682, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.0307379961013794, | |
| "eval_runtime": 1238.5009, | |
| "eval_samples_per_second": 0.807, | |
| "eval_steps_per_second": 0.051, | |
| "eval_wer": 0.5047652804032766, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9354, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 0.7321, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.6299881935119629, | |
| "eval_runtime": 830.7332, | |
| "eval_samples_per_second": 1.204, | |
| "eval_steps_per_second": 0.076, | |
| "eval_wer": 0.36645400126023947, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.951340343707852e-06, | |
| "loss": 0.5397, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 0.4564, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.438092440366745, | |
| "eval_runtime": 723.2192, | |
| "eval_samples_per_second": 1.383, | |
| "eval_steps_per_second": 0.087, | |
| "eval_wer": 0.35148865784499056, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.806308479691595e-06, | |
| "loss": 0.4291, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.4095, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.40272918343544006, | |
| "eval_runtime": 636.5063, | |
| "eval_samples_per_second": 1.571, | |
| "eval_steps_per_second": 0.099, | |
| "eval_wer": 0.33297889098928796, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 0.3992, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.414737964294636e-06, | |
| "loss": 0.3813, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 0.3847169280052185, | |
| "eval_runtime": 616.7138, | |
| "eval_samples_per_second": 1.621, | |
| "eval_steps_per_second": 0.102, | |
| "eval_wer": 0.3359719596723377, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.24024048078213e-06, | |
| "loss": 0.3711, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.3667, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.37336310744285583, | |
| "eval_runtime": 614.3217, | |
| "eval_samples_per_second": 1.628, | |
| "eval_steps_per_second": 0.103, | |
| "eval_wer": 0.33916194076874606, | |
| "step": 1400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9, | |
| "save_steps": 200, | |
| "total_flos": 5.220858048233472e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |