| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007541620317125134, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.541620317125135e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.541620317125135e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 372.502, | |
| "eval_samples_per_second": 14.991, | |
| "eval_steps_per_second": 7.495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001508324063425027, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 13.0361, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00022624860951375402, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00022624860951375402, | |
| "eval_loss": NaN, | |
| "eval_runtime": 371.8059, | |
| "eval_samples_per_second": 15.019, | |
| "eval_steps_per_second": 7.509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003016648126850054, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003770810158562567, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 29.3016, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00045249721902750805, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00045249721902750805, | |
| "eval_loss": NaN, | |
| "eval_runtime": 371.7669, | |
| "eval_samples_per_second": 15.02, | |
| "eval_steps_per_second": 7.51, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005279134221987594, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006033296253700108, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006787458285412621, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 7.1649, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006787458285412621, | |
| "eval_loss": NaN, | |
| "eval_runtime": 371.5191, | |
| "eval_samples_per_second": 15.03, | |
| "eval_steps_per_second": 7.515, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 24.5696, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4563351078174720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |