| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005076142131979695, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016920473773265651, | |
| "eval_loss": 1.5492067337036133, | |
| "eval_runtime": 210.0622, | |
| "eval_samples_per_second": 11.849, | |
| "eval_steps_per_second": 5.927, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005076142131979696, | |
| "grad_norm": 0.7747828960418701, | |
| "learning_rate": 6e-05, | |
| "loss": 1.271, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010152284263959391, | |
| "grad_norm": 1.4029040336608887, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2366, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013536379018612521, | |
| "eval_loss": 1.4494123458862305, | |
| "eval_runtime": 210.9289, | |
| "eval_samples_per_second": 11.8, | |
| "eval_steps_per_second": 5.902, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015228426395939086, | |
| "grad_norm": 0.9781267046928406, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1913, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020304568527918783, | |
| "grad_norm": 1.1829664707183838, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.2896, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0025380710659898475, | |
| "grad_norm": 1.0036306381225586, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.0501, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027072758037225042, | |
| "eval_loss": 1.258029818534851, | |
| "eval_runtime": 210.8297, | |
| "eval_samples_per_second": 11.806, | |
| "eval_steps_per_second": 5.905, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003045685279187817, | |
| "grad_norm": 0.8435078859329224, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.2201, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003553299492385787, | |
| "grad_norm": 1.1413564682006836, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.147, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0040609137055837565, | |
| "grad_norm": 0.8211542367935181, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.1632, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0040609137055837565, | |
| "eval_loss": 1.2106075286865234, | |
| "eval_runtime": 210.9168, | |
| "eval_samples_per_second": 11.801, | |
| "eval_steps_per_second": 5.903, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004568527918781726, | |
| "grad_norm": 1.643991470336914, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.0987, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005076142131979695, | |
| "grad_norm": 0.818309485912323, | |
| "learning_rate": 0.0, | |
| "loss": 1.2318, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |