| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9473684210526314, | |
| "eval_steps": 500, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 33.15888044761256, | |
| "learning_rate": 5e-06, | |
| "loss": 2.3845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 32.85087228020456, | |
| "learning_rate": 4.957432749209755e-06, | |
| "loss": 2.4262, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 17.287178112682515, | |
| "learning_rate": 4.83118057351089e-06, | |
| "loss": 2.0605, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 22.156624644223225, | |
| "learning_rate": 4.625542839324036e-06, | |
| "loss": 2.0643, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 31.24716491045878, | |
| "learning_rate": 4.3475222930516484e-06, | |
| "loss": 2.1075, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 19.777743012091744, | |
| "learning_rate": 4.006586590948141e-06, | |
| "loss": 2.0151, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 12.072245875701771, | |
| "learning_rate": 3.6143458894413463e-06, | |
| "loss": 1.9219, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 9.496121066394277, | |
| "learning_rate": 3.184157475180208e-06, | |
| "loss": 1.9058, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 10.211533731158024, | |
| "learning_rate": 2.730670898658255e-06, | |
| "loss": 1.9148, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 9.965283978172675, | |
| "learning_rate": 2.269329101341745e-06, | |
| "loss": 1.7407, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 8.734937073121175, | |
| "learning_rate": 1.8158425248197931e-06, | |
| "loss": 1.7286, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 9.508662641095643, | |
| "learning_rate": 1.3856541105586545e-06, | |
| "loss": 1.6936, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 8.355635389438104, | |
| "learning_rate": 9.934134090518593e-07, | |
| "loss": 1.6708, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 8.05041781460727, | |
| "learning_rate": 6.524777069483526e-07, | |
| "loss": 1.6466, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 7.5793931666820455, | |
| "learning_rate": 3.7445716067596506e-07, | |
| "loss": 1.6767, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 7.162816395853179, | |
| "learning_rate": 1.6881942648911077e-07, | |
| "loss": 1.6494, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 7.225686707910806, | |
| "learning_rate": 4.256725079024554e-08, | |
| "loss": 1.6394, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 7.320022756405671, | |
| "learning_rate": 0.0, | |
| "loss": 1.6727, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 7.157781045707602, | |
| "learning_rate": 4.594214621574912e-06, | |
| "loss": 1.5742, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 7.15791774456708, | |
| "learning_rate": 4.54355584639723e-06, | |
| "loss": 1.673, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 10.340618846680513, | |
| "learning_rate": 4.49023266426411e-06, | |
| "loss": 1.5806, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 11.734839865750393, | |
| "learning_rate": 4.434314598432091e-06, | |
| "loss": 1.5359, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 12.307990008201672, | |
| "learning_rate": 4.3758745553910065e-06, | |
| "loss": 1.5259, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 10.433638720770736, | |
| "learning_rate": 4.3149887298078275e-06, | |
| "loss": 1.4633, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 11.46032438607999, | |
| "learning_rate": 4.2517365051833564e-06, | |
| "loss": 1.5129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 12.528340674980042, | |
| "learning_rate": 4.1862003503512845e-06, | |
| "loss": 1.509, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 10.849307524210143, | |
| "learning_rate": 4.11846571195457e-06, | |
| "loss": 1.4902, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 5000.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4718633000960.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |