| { | |
| "best_metric": 0.7070627062706271, | |
| "best_model_checkpoint": "food-image-classification/checkpoint-7000", | |
| "epoch": 8.447729672650475, | |
| "eval_steps": 1000, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.0559662090813095e-06, | |
| "loss": 4.6112, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.034851485148514855, | |
| "eval_loss": 4.575930118560791, | |
| "eval_runtime": 157.053, | |
| "eval_samples_per_second": 96.464, | |
| "eval_steps_per_second": 6.03, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.111932418162619e-06, | |
| "loss": 4.4899, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_accuracy": 0.3103630363036304, | |
| "eval_loss": 4.3788862228393555, | |
| "eval_runtime": 154.3948, | |
| "eval_samples_per_second": 98.125, | |
| "eval_steps_per_second": 6.134, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 3.167898627243928e-06, | |
| "loss": 4.2111, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_accuracy": 0.5498349834983498, | |
| "eval_loss": 4.030922889709473, | |
| "eval_runtime": 155.2257, | |
| "eval_samples_per_second": 97.6, | |
| "eval_steps_per_second": 6.101, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.223864836325238e-06, | |
| "loss": 3.8257, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "eval_accuracy": 0.6111551155115511, | |
| "eval_loss": 3.634243965148926, | |
| "eval_runtime": 156.2293, | |
| "eval_samples_per_second": 96.973, | |
| "eval_steps_per_second": 6.062, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 5.279831045406547e-06, | |
| "loss": 3.4182, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "eval_accuracy": 0.6514851485148515, | |
| "eval_loss": 3.225186586380005, | |
| "eval_runtime": 154.6911, | |
| "eval_samples_per_second": 97.937, | |
| "eval_steps_per_second": 6.122, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 6.335797254487856e-06, | |
| "loss": 2.9962, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "eval_accuracy": 0.687062706270627, | |
| "eval_loss": 2.805878162384033, | |
| "eval_runtime": 154.6826, | |
| "eval_samples_per_second": 97.943, | |
| "eval_steps_per_second": 6.122, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 7.3917634635691666e-06, | |
| "loss": 2.5605, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "eval_accuracy": 0.7070627062706271, | |
| "eval_loss": 2.382246494293213, | |
| "eval_runtime": 155.5967, | |
| "eval_samples_per_second": 97.367, | |
| "eval_steps_per_second": 6.086, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 8.447729672650476e-06, | |
| "loss": 2.1397, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "eval_accuracy": 0.7335973597359736, | |
| "eval_loss": 1.975380539894104, | |
| "eval_runtime": 156.8793, | |
| "eval_samples_per_second": 96.571, | |
| "eval_steps_per_second": 6.036, | |
| "step": 8000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 473500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 500, | |
| "save_steps": 1000, | |
| "total_flos": 3.970613944525455e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |