| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06389776357827476, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002129925452609159, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.568, | |
| "eval_samples_per_second": 8.773, | |
| "eval_steps_per_second": 4.387, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006389776357827476, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010649627263045794, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.6115, | |
| "eval_samples_per_second": 8.757, | |
| "eval_steps_per_second": 4.378, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012779552715654952, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019169329073482427, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021299254526091587, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.7536, | |
| "eval_samples_per_second": 8.702, | |
| "eval_steps_per_second": 4.351, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025559105431309903, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03194888178913738, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03194888178913738, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.7615, | |
| "eval_samples_per_second": 8.699, | |
| "eval_steps_per_second": 4.349, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.038338658146964855, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.042598509052183174, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.768, | |
| "eval_samples_per_second": 8.696, | |
| "eval_steps_per_second": 4.348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04472843450479233, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.051118210862619806, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05324813631522897, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.7611, | |
| "eval_samples_per_second": 8.699, | |
| "eval_steps_per_second": 4.35, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05750798722044728, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06389776357827476, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06389776357827476, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.7885, | |
| "eval_samples_per_second": 8.689, | |
| "eval_steps_per_second": 4.344, | |
| "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": 1.054694248022016e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |