| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.834862385321101, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03669724770642202, | |
| "eval_loss": 6.940816402435303, | |
| "eval_runtime": 0.4894, | |
| "eval_samples_per_second": 94.001, | |
| "eval_steps_per_second": 12.261, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11009174311926606, | |
| "grad_norm": 0.44857925176620483, | |
| "learning_rate": 3e-05, | |
| "loss": 6.9418, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1834862385321101, | |
| "eval_loss": 6.936913013458252, | |
| "eval_runtime": 0.0633, | |
| "eval_samples_per_second": 726.735, | |
| "eval_steps_per_second": 94.792, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22018348623853212, | |
| "grad_norm": 0.4511624872684479, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9388, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3302752293577982, | |
| "grad_norm": 0.44215646386146545, | |
| "learning_rate": 9e-05, | |
| "loss": 6.9322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "eval_loss": 6.922896862030029, | |
| "eval_runtime": 0.0602, | |
| "eval_samples_per_second": 763.509, | |
| "eval_steps_per_second": 99.588, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.44036697247706424, | |
| "grad_norm": 0.4800911843776703, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 6.9237, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5504587155963303, | |
| "grad_norm": 0.5088721513748169, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9119, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5504587155963303, | |
| "eval_loss": 6.901125907897949, | |
| "eval_runtime": 0.0697, | |
| "eval_samples_per_second": 660.168, | |
| "eval_steps_per_second": 86.109, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6605504587155964, | |
| "grad_norm": 0.5459818840026855, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 6.8969, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "eval_loss": 6.87958288192749, | |
| "eval_runtime": 0.058, | |
| "eval_samples_per_second": 793.383, | |
| "eval_steps_per_second": 103.485, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7706422018348624, | |
| "grad_norm": 0.5402729511260986, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 6.8852, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8807339449541285, | |
| "grad_norm": 0.5008237361907959, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 6.8723, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9174311926605505, | |
| "eval_loss": 6.86152982711792, | |
| "eval_runtime": 0.0589, | |
| "eval_samples_per_second": 781.084, | |
| "eval_steps_per_second": 101.881, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9908256880733946, | |
| "grad_norm": 0.4618155360221863, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 6.8632, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1009174311926606, | |
| "grad_norm": 0.4284931719303131, | |
| "learning_rate": 5e-05, | |
| "loss": 8.6369, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1009174311926606, | |
| "eval_loss": 6.850541591644287, | |
| "eval_runtime": 0.0613, | |
| "eval_samples_per_second": 750.191, | |
| "eval_steps_per_second": 97.851, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2110091743119267, | |
| "grad_norm": 0.37953659892082214, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 6.7564, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2844036697247707, | |
| "eval_loss": 6.844419956207275, | |
| "eval_runtime": 0.0605, | |
| "eval_samples_per_second": 759.745, | |
| "eval_steps_per_second": 99.097, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3211009174311927, | |
| "grad_norm": 0.35859671235084534, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 6.8617, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4311926605504588, | |
| "grad_norm": 0.3261173963546753, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 6.9499, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4678899082568808, | |
| "eval_loss": 6.84140157699585, | |
| "eval_runtime": 0.0596, | |
| "eval_samples_per_second": 772.357, | |
| "eval_steps_per_second": 100.742, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5412844036697249, | |
| "grad_norm": 0.3164646625518799, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 6.8576, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6513761467889907, | |
| "grad_norm": 0.3245089054107666, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.8992, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6513761467889907, | |
| "eval_loss": 6.84040641784668, | |
| "eval_runtime": 0.0629, | |
| "eval_samples_per_second": 731.69, | |
| "eval_steps_per_second": 95.438, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.761467889908257, | |
| "grad_norm": 0.30095237493515015, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 6.7224, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "eval_loss": 6.840231895446777, | |
| "eval_runtime": 0.0584, | |
| "eval_samples_per_second": 788.113, | |
| "eval_steps_per_second": 102.797, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1110703589376.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |