| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02056343820686819, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00041126876413736374, | |
| "eval_loss": 1.1108553409576416, | |
| "eval_runtime": 27.293, | |
| "eval_samples_per_second": 37.519, | |
| "eval_steps_per_second": 18.759, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002056343820686819, | |
| "grad_norm": 1.055071234703064, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0573, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004112687641373638, | |
| "grad_norm": 1.6324950456619263, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0706, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004112687641373638, | |
| "eval_loss": 0.989827573299408, | |
| "eval_runtime": 27.3354, | |
| "eval_samples_per_second": 37.461, | |
| "eval_steps_per_second": 18.73, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006169031462060457, | |
| "grad_norm": 1.3293852806091309, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.866, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008225375282747275, | |
| "grad_norm": 1.1884467601776123, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8083, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008225375282747275, | |
| "eval_loss": 0.661908745765686, | |
| "eval_runtime": 27.2106, | |
| "eval_samples_per_second": 37.632, | |
| "eval_steps_per_second": 18.816, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010281719103434095, | |
| "grad_norm": 1.6942882537841797, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6215, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012338062924120914, | |
| "grad_norm": 1.4033981561660767, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5869, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012338062924120914, | |
| "eval_loss": 0.6099783182144165, | |
| "eval_runtime": 27.1649, | |
| "eval_samples_per_second": 37.696, | |
| "eval_steps_per_second": 18.848, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014394406744807731, | |
| "grad_norm": 1.5280038118362427, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5931, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01645075056549455, | |
| "grad_norm": 1.2525250911712646, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01645075056549455, | |
| "eval_loss": 0.589495062828064, | |
| "eval_runtime": 27.3301, | |
| "eval_samples_per_second": 37.468, | |
| "eval_steps_per_second": 18.734, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01850709438618137, | |
| "grad_norm": 1.1442337036132812, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6124, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02056343820686819, | |
| "grad_norm": 0.9440557360649109, | |
| "learning_rate": 0.0, | |
| "loss": 0.5675, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02056343820686819, | |
| "eval_loss": 0.5864447355270386, | |
| "eval_runtime": 27.3552, | |
| "eval_samples_per_second": 37.434, | |
| "eval_steps_per_second": 18.717, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1202727577190400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |