| { | |
| "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": 14.599925994873047, | |
| "learning_rate": 2e-05, | |
| "loss": 23.2456, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00221606648199446, | |
| "eval_loss": 3.304386854171753, | |
| "eval_runtime": 6.2679, | |
| "eval_samples_per_second": 30.313, | |
| "eval_steps_per_second": 15.157, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00443213296398892, | |
| "grad_norm": 13.374890327453613, | |
| "learning_rate": 4e-05, | |
| "loss": 24.7178, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006648199445983379, | |
| "grad_norm": 180.24391174316406, | |
| "learning_rate": 6e-05, | |
| "loss": 21.7856, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006648199445983379, | |
| "eval_loss": 3.3025741577148438, | |
| "eval_runtime": 5.5978, | |
| "eval_samples_per_second": 33.942, | |
| "eval_steps_per_second": 16.971, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00886426592797784, | |
| "grad_norm": 19.00010871887207, | |
| "learning_rate": 8e-05, | |
| "loss": 19.4483, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0110803324099723, | |
| "grad_norm": 13.460244178771973, | |
| "learning_rate": 0.0001, | |
| "loss": 23.0721, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013296398891966758, | |
| "grad_norm": 22.324302673339844, | |
| "learning_rate": 0.00012, | |
| "loss": 23.8604, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013296398891966758, | |
| "eval_loss": 3.1988017559051514, | |
| "eval_runtime": 5.7099, | |
| "eval_samples_per_second": 33.275, | |
| "eval_steps_per_second": 16.638, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01551246537396122, | |
| "grad_norm": 24.66731071472168, | |
| "learning_rate": 0.00014, | |
| "loss": 19.7873, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01772853185595568, | |
| "grad_norm": 21.929731369018555, | |
| "learning_rate": 0.00016, | |
| "loss": 21.3106, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019944598337950138, | |
| "grad_norm": 24.648714065551758, | |
| "learning_rate": 0.00018, | |
| "loss": 16.7503, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019944598337950138, | |
| "eval_loss": 2.5536041259765625, | |
| "eval_runtime": 5.6486, | |
| "eval_samples_per_second": 33.637, | |
| "eval_steps_per_second": 16.818, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "grad_norm": 32.41691970825195, | |
| "learning_rate": 0.0002, | |
| "loss": 20.1324, | |
| "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": 1421129684090880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |