| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 100, | |
| "global_step": 920, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0869565217391304, | |
| "eval_loss": 3.51055908203125, | |
| "eval_runtime": 36.2042, | |
| "eval_samples_per_second": 17.595, | |
| "eval_steps_per_second": 2.21, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "eval_loss": 2.9226224422454834, | |
| "eval_runtime": 35.9506, | |
| "eval_samples_per_second": 17.719, | |
| "eval_steps_per_second": 2.225, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.260869565217391, | |
| "eval_loss": 2.874464988708496, | |
| "eval_runtime": 35.9419, | |
| "eval_samples_per_second": 17.723, | |
| "eval_steps_per_second": 2.226, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.3478260869565215, | |
| "eval_loss": 1.8099528551101685, | |
| "eval_runtime": 35.9111, | |
| "eval_samples_per_second": 17.738, | |
| "eval_steps_per_second": 2.228, | |
| "eval_wer": 0.9803537770044947, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.434782608695652, | |
| "grad_norm": 0.6213024258613586, | |
| "learning_rate": 0.0002988, | |
| "loss": 3.7609, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.434782608695652, | |
| "eval_loss": 0.4771381616592407, | |
| "eval_runtime": 35.9706, | |
| "eval_samples_per_second": 17.709, | |
| "eval_steps_per_second": 2.224, | |
| "eval_wer": 0.4206901551399159, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.521739130434782, | |
| "eval_loss": 0.3808304965496063, | |
| "eval_runtime": 36.4619, | |
| "eval_samples_per_second": 17.47, | |
| "eval_steps_per_second": 2.194, | |
| "eval_wer": 0.34841235319704217, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.608695652173913, | |
| "eval_loss": 0.34075430035591125, | |
| "eval_runtime": 35.8567, | |
| "eval_samples_per_second": 17.765, | |
| "eval_steps_per_second": 2.231, | |
| "eval_wer": 0.28715383500072494, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.695652173913043, | |
| "eval_loss": 0.3479066789150238, | |
| "eval_runtime": 35.8444, | |
| "eval_samples_per_second": 17.771, | |
| "eval_steps_per_second": 2.232, | |
| "eval_wer": 0.2719298245614035, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.782608695652174, | |
| "eval_loss": 0.3436548411846161, | |
| "eval_runtime": 35.796, | |
| "eval_samples_per_second": 17.795, | |
| "eval_steps_per_second": 2.235, | |
| "eval_wer": 0.260403073800203, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 920, | |
| "total_flos": 9.080032524835507e+18, | |
| "train_loss": 2.111865760969079, | |
| "train_runtime": 3049.4338, | |
| "train_samples_per_second": 9.635, | |
| "train_steps_per_second": 0.302 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 920, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.080032524835507e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |