| { | |
| "best_metric": 3.9748706817626953, | |
| "best_model_checkpoint": "indian_food_image_detection/checkpoint-1140", | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 1140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3025, | |
| "eval_loss": 4.151414394378662, | |
| "eval_runtime": 24.372, | |
| "eval_samples_per_second": 65.649, | |
| "eval_steps_per_second": 2.052, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.313125, | |
| "eval_loss": 4.140285015106201, | |
| "eval_runtime": 24.4394, | |
| "eval_samples_per_second": 65.468, | |
| "eval_steps_per_second": 2.046, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.321875, | |
| "eval_loss": 4.129441261291504, | |
| "eval_runtime": 24.5066, | |
| "eval_samples_per_second": 65.288, | |
| "eval_steps_per_second": 2.04, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.331875, | |
| "eval_loss": 4.1186909675598145, | |
| "eval_runtime": 24.4129, | |
| "eval_samples_per_second": 65.539, | |
| "eval_steps_per_second": 2.048, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3425, | |
| "eval_loss": 4.108262538909912, | |
| "eval_runtime": 24.4749, | |
| "eval_samples_per_second": 65.373, | |
| "eval_steps_per_second": 2.043, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.35, | |
| "eval_loss": 4.098318099975586, | |
| "eval_runtime": 24.5662, | |
| "eval_samples_per_second": 65.13, | |
| "eval_steps_per_second": 2.035, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.361875, | |
| "eval_loss": 4.0884175300598145, | |
| "eval_runtime": 24.4798, | |
| "eval_samples_per_second": 65.36, | |
| "eval_steps_per_second": 2.043, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.3725, | |
| "eval_loss": 4.079204082489014, | |
| "eval_runtime": 24.5132, | |
| "eval_samples_per_second": 65.271, | |
| "eval_steps_per_second": 2.04, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.38125, | |
| "eval_loss": 4.069871425628662, | |
| "eval_runtime": 24.3786, | |
| "eval_samples_per_second": 65.631, | |
| "eval_steps_per_second": 2.051, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.38625, | |
| "eval_loss": 4.061194896697998, | |
| "eval_runtime": 24.4377, | |
| "eval_samples_per_second": 65.473, | |
| "eval_steps_per_second": 2.046, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.398125, | |
| "eval_loss": 4.05281400680542, | |
| "eval_runtime": 24.8276, | |
| "eval_samples_per_second": 64.444, | |
| "eval_steps_per_second": 2.014, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.406875, | |
| "eval_loss": 4.045093536376953, | |
| "eval_runtime": 24.4234, | |
| "eval_samples_per_second": 65.511, | |
| "eval_steps_per_second": 2.047, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4175, | |
| "eval_loss": 4.037683486938477, | |
| "eval_runtime": 24.4923, | |
| "eval_samples_per_second": 65.327, | |
| "eval_steps_per_second": 2.041, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 13.157894736842104, | |
| "grad_norm": 1.2188057899475098, | |
| "learning_rate": 1.1743119266055047e-06, | |
| "loss": 4.0651, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.42125, | |
| "eval_loss": 4.0303263664245605, | |
| "eval_runtime": 24.5981, | |
| "eval_samples_per_second": 65.046, | |
| "eval_steps_per_second": 2.033, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.425625, | |
| "eval_loss": 4.023651599884033, | |
| "eval_runtime": 24.5314, | |
| "eval_samples_per_second": 65.223, | |
| "eval_steps_per_second": 2.038, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.434375, | |
| "eval_loss": 4.017561435699463, | |
| "eval_runtime": 24.6545, | |
| "eval_samples_per_second": 64.897, | |
| "eval_steps_per_second": 2.028, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.439375, | |
| "eval_loss": 4.011629104614258, | |
| "eval_runtime": 24.5053, | |
| "eval_samples_per_second": 65.292, | |
| "eval_steps_per_second": 2.04, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.446875, | |
| "eval_loss": 4.006289482116699, | |
| "eval_runtime": 24.5387, | |
| "eval_samples_per_second": 65.203, | |
| "eval_steps_per_second": 2.038, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.45375, | |
| "eval_loss": 4.00118350982666, | |
| "eval_runtime": 24.6877, | |
| "eval_samples_per_second": 64.81, | |
| "eval_steps_per_second": 2.025, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4575, | |
| "eval_loss": 3.9966068267822266, | |
| "eval_runtime": 24.6967, | |
| "eval_samples_per_second": 64.786, | |
| "eval_steps_per_second": 2.025, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.46, | |
| "eval_loss": 3.9925529956817627, | |
| "eval_runtime": 24.8697, | |
| "eval_samples_per_second": 64.335, | |
| "eval_steps_per_second": 2.01, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.463125, | |
| "eval_loss": 3.9888575077056885, | |
| "eval_runtime": 24.9595, | |
| "eval_samples_per_second": 64.104, | |
| "eval_steps_per_second": 2.003, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.464375, | |
| "eval_loss": 3.9854891300201416, | |
| "eval_runtime": 24.5799, | |
| "eval_samples_per_second": 65.094, | |
| "eval_steps_per_second": 2.034, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.466875, | |
| "eval_loss": 3.9826958179473877, | |
| "eval_runtime": 24.5912, | |
| "eval_samples_per_second": 65.064, | |
| "eval_steps_per_second": 2.033, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.469375, | |
| "eval_loss": 3.980361223220825, | |
| "eval_runtime": 24.6399, | |
| "eval_samples_per_second": 64.935, | |
| "eval_steps_per_second": 2.029, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.470625, | |
| "eval_loss": 3.9784324169158936, | |
| "eval_runtime": 24.6458, | |
| "eval_samples_per_second": 64.92, | |
| "eval_steps_per_second": 2.029, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 26.31578947368421, | |
| "grad_norm": 1.1505932807922363, | |
| "learning_rate": 2.568807339449541e-07, | |
| "loss": 3.9504, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.470625, | |
| "eval_loss": 3.976879358291626, | |
| "eval_runtime": 24.7593, | |
| "eval_samples_per_second": 64.622, | |
| "eval_steps_per_second": 2.019, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.473125, | |
| "eval_loss": 3.9757637977600098, | |
| "eval_runtime": 24.4731, | |
| "eval_samples_per_second": 65.378, | |
| "eval_steps_per_second": 2.043, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.473125, | |
| "eval_loss": 3.9750988483428955, | |
| "eval_runtime": 24.4848, | |
| "eval_samples_per_second": 65.347, | |
| "eval_steps_per_second": 2.042, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.47375, | |
| "eval_loss": 3.9748706817626953, | |
| "eval_runtime": 24.6946, | |
| "eval_samples_per_second": 64.791, | |
| "eval_steps_per_second": 2.025, | |
| "step": 1140 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.583323767504896e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |