| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0221606648199446, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00221606648199446, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 9.3977, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00221606648199446, | |
| "eval_loss": 9.974275588989258, | |
| "eval_runtime": 17.5013, | |
| "eval_samples_per_second": 21.713, | |
| "eval_steps_per_second": 5.428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00443213296398892, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 9.5052, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006648199445983379, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 9.5637, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006648199445983379, | |
| "eval_loss": 9.974275588989258, | |
| "eval_runtime": 16.7407, | |
| "eval_samples_per_second": 22.699, | |
| "eval_steps_per_second": 5.675, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00886426592797784, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 11.0612, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0110803324099723, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 9.6454, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013296398891966758, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 10.391, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013296398891966758, | |
| "eval_loss": 9.974275588989258, | |
| "eval_runtime": 16.7359, | |
| "eval_samples_per_second": 22.706, | |
| "eval_steps_per_second": 5.676, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01551246537396122, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 9.5985, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01772853185595568, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 8.5192, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019944598337950138, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 10.565, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019944598337950138, | |
| "eval_loss": 9.974275588989258, | |
| "eval_runtime": 16.7351, | |
| "eval_samples_per_second": 22.707, | |
| "eval_steps_per_second": 5.677, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 9.4913, | |
| "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": 1.47552863256576e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |