| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.2523364485981308, | |
| "eval_steps": 25, | |
| "global_step": 21, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 311.5249328613281, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6401, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "eval_loss": 4.832165718078613, | |
| "eval_runtime": 4.4249, | |
| "eval_samples_per_second": 10.17, | |
| "eval_steps_per_second": 1.356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 243.76405334472656, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4027, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 229.6423797607422, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.43, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 276.1520690917969, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.7089, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 63.68783187866211, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.675, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 66.92127990722656, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.3228, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0841121495327102, | |
| "grad_norm": 119.62931060791016, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.5445, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.233644859813084, | |
| "grad_norm": 31.598838806152344, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.1207, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.3831775700934579, | |
| "grad_norm": 105.07861328125, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.3446, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.5327102803738317, | |
| "grad_norm": 93.04505920410156, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.2086, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.6822429906542056, | |
| "grad_norm": 70.13788604736328, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.1205, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.8317757009345794, | |
| "grad_norm": 105.59453582763672, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.1351, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.0186915887850465, | |
| "grad_norm": 25.851747512817383, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.1665, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.1682242990654204, | |
| "grad_norm": 17.569660186767578, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.0846, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.317757009345794, | |
| "grad_norm": 15.646451950073242, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.1177, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.467289719626168, | |
| "grad_norm": 18.13563346862793, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.0821, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.616822429906542, | |
| "grad_norm": 14.64362621307373, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.0737, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.7663551401869158, | |
| "grad_norm": 26.5267333984375, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.1425, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.9158878504672896, | |
| "grad_norm": 13.506791114807129, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0241, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.102803738317757, | |
| "grad_norm": 35.055320739746094, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.1315, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.2523364485981308, | |
| "grad_norm": 17.9412841796875, | |
| "learning_rate": 0.0, | |
| "loss": 0.0389, | |
| "step": 21 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 21, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.8614638773089075e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |