| { | |
| "best_metric": 1.347914457321167, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-30", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.3863, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.3863, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3853, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.3822, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.3799, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.3753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.3704, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.375, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.3574, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.3805, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.65, | |
| "eval_f1_macro": 0.196969696969697, | |
| "eval_f1_micro": 0.65, | |
| "eval_f1_weighted": 0.5121212121212122, | |
| "eval_loss": 1.3667380809783936, | |
| "eval_precision_macro": 0.1625, | |
| "eval_precision_micro": 0.65, | |
| "eval_precision_weighted": 0.42250000000000004, | |
| "eval_recall_macro": 0.25, | |
| "eval_recall_micro": 0.65, | |
| "eval_recall_weighted": 0.65, | |
| "eval_runtime": 2.6269, | |
| "eval_samples_per_second": 7.613, | |
| "eval_steps_per_second": 0.761, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 1.3646, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.351, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 1.3624, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 1.3458, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.3362, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 1.3464, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 1.3529, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.3428, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 1.3329, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 1.3722, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.65, | |
| "eval_f1_macro": 0.196969696969697, | |
| "eval_f1_micro": 0.65, | |
| "eval_f1_weighted": 0.5121212121212122, | |
| "eval_loss": 1.356222152709961, | |
| "eval_precision_macro": 0.1625, | |
| "eval_precision_micro": 0.65, | |
| "eval_precision_weighted": 0.42250000000000004, | |
| "eval_recall_macro": 0.25, | |
| "eval_recall_micro": 0.65, | |
| "eval_recall_weighted": 0.65, | |
| "eval_runtime": 2.8668, | |
| "eval_samples_per_second": 6.976, | |
| "eval_steps_per_second": 0.698, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.347, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 1.3339, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 1.3488, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.3389, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 1.3107, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 1.33, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 1.3569, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 1.3224, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 1.3139, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.3737, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.65, | |
| "eval_f1_macro": 0.196969696969697, | |
| "eval_f1_micro": 0.65, | |
| "eval_f1_weighted": 0.5121212121212122, | |
| "eval_loss": 1.347914457321167, | |
| "eval_precision_macro": 0.1625, | |
| "eval_precision_micro": 0.65, | |
| "eval_precision_weighted": 0.42250000000000004, | |
| "eval_recall_macro": 0.25, | |
| "eval_recall_micro": 0.65, | |
| "eval_recall_weighted": 0.65, | |
| "eval_runtime": 2.8418, | |
| "eval_samples_per_second": 7.038, | |
| "eval_steps_per_second": 0.704, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 4969950478811136.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |