| { | |
| "best_global_step": 372, | |
| "best_metric": 0.39589157700538635, | |
| "best_model_checkpoint": "F:\\Work_stuff\\VisualStudio_cursor\\audio_mood_classifier_hf\\models\\mood_classifier_2026-07-16_09-27\\checkpoint-372", | |
| "epoch": 12.0, | |
| "eval_steps": 500, | |
| "global_step": 372, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 86.11, | |
| "eval_gain_over_random": 52.78, | |
| "eval_loss": 0.42865681648254395, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 46.4446, | |
| "eval_samples_per_second": 4.651, | |
| "eval_steps_per_second": 0.581, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.6129032258064515, | |
| "grad_norm": 5.450277328491211, | |
| "learning_rate": 3.578494623655914e-07, | |
| "loss": 0.4940774917602539, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 86.57, | |
| "eval_gain_over_random": 53.24, | |
| "eval_loss": 0.4212609827518463, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 46.6498, | |
| "eval_samples_per_second": 4.63, | |
| "eval_steps_per_second": 0.579, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 86.57, | |
| "eval_gain_over_random": 53.24, | |
| "eval_loss": 0.4187099039554596, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 46.4674, | |
| "eval_samples_per_second": 4.648, | |
| "eval_steps_per_second": 0.581, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.225806451612903, | |
| "grad_norm": 3.5786874294281006, | |
| "learning_rate": 3.148387096774193e-07, | |
| "loss": 0.4830916976928711, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 85.65, | |
| "eval_gain_over_random": 52.31, | |
| "eval_loss": 0.42973992228507996, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 46.5953, | |
| "eval_samples_per_second": 4.636, | |
| "eval_steps_per_second": 0.579, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.838709677419355, | |
| "grad_norm": 2.840916633605957, | |
| "learning_rate": 2.718279569892473e-07, | |
| "loss": 0.4838411331176758, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 83.8, | |
| "eval_gain_over_random": 50.46, | |
| "eval_loss": 0.4159768521785736, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 46.5148, | |
| "eval_samples_per_second": 4.644, | |
| "eval_steps_per_second": 0.58, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 85.19, | |
| "eval_gain_over_random": 51.85, | |
| "eval_loss": 0.4102042019367218, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 46.3609, | |
| "eval_samples_per_second": 4.659, | |
| "eval_steps_per_second": 0.582, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 6.451612903225806, | |
| "grad_norm": 3.7706756591796875, | |
| "learning_rate": 2.2881720430107524e-07, | |
| "loss": 0.47981719970703124, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 85.65, | |
| "eval_gain_over_random": 52.31, | |
| "eval_loss": 0.4190486669540405, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 43.6211, | |
| "eval_samples_per_second": 4.952, | |
| "eval_steps_per_second": 0.619, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 86.11, | |
| "eval_gain_over_random": 52.78, | |
| "eval_loss": 0.42142894864082336, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 52.8985, | |
| "eval_samples_per_second": 4.083, | |
| "eval_steps_per_second": 0.51, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 8.064516129032258, | |
| "grad_norm": 2.820573091506958, | |
| "learning_rate": 1.8580645161290323e-07, | |
| "loss": 0.4633090591430664, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 85.19, | |
| "eval_gain_over_random": 51.85, | |
| "eval_loss": 0.4239995777606964, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 54.2035, | |
| "eval_samples_per_second": 3.985, | |
| "eval_steps_per_second": 0.498, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 9.67741935483871, | |
| "grad_norm": 2.8738181591033936, | |
| "learning_rate": 1.4279569892473117e-07, | |
| "loss": 0.47099334716796876, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 85.19, | |
| "eval_gain_over_random": 51.85, | |
| "eval_loss": 0.4082905948162079, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 53.1952, | |
| "eval_samples_per_second": 4.061, | |
| "eval_steps_per_second": 0.508, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 87.96, | |
| "eval_gain_over_random": 54.63, | |
| "eval_loss": 0.4077238440513611, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 53.3942, | |
| "eval_samples_per_second": 4.045, | |
| "eval_steps_per_second": 0.506, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 11.290322580645162, | |
| "grad_norm": 3.939497232437134, | |
| "learning_rate": 9.978494623655913e-08, | |
| "loss": 0.47861801147460936, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 87.04, | |
| "eval_gain_over_random": 53.7, | |
| "eval_loss": 0.39589157700538635, | |
| "eval_random_baseline": 33.33, | |
| "eval_runtime": 53.13, | |
| "eval_samples_per_second": 4.065, | |
| "eval_steps_per_second": 0.508, | |
| "step": 372 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 465, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.052673225634611e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |