| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013250517598343685, | |
| "eval_steps": 40, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.625258799171843e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3989.9649, | |
| "eval_samples_per_second": 6.371, | |
| "eval_steps_per_second": 3.186, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002650103519668737, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002650103519668737, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3986.9682, | |
| "eval_samples_per_second": 6.376, | |
| "eval_steps_per_second": 3.188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005300207039337474, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005300207039337474, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3989.1243, | |
| "eval_samples_per_second": 6.373, | |
| "eval_steps_per_second": 3.186, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.007950310559006211, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.007950310559006211, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3989.9051, | |
| "eval_samples_per_second": 6.371, | |
| "eval_steps_per_second": 3.186, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.010600414078674947, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.010600414078674947, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3987.3185, | |
| "eval_samples_per_second": 6.375, | |
| "eval_steps_per_second": 3.188, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.013250517598343685, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.013250517598343685, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3987.784, | |
| "eval_samples_per_second": 6.375, | |
| "eval_steps_per_second": 3.187, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.957752586798367e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |