| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010471204188481676, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010471204188481676, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010471204188481676, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.7521, | |
| "eval_samples_per_second": 16.967, | |
| "eval_steps_per_second": 8.505, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020942408376963353, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8296, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0031413612565445027, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7975, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0031413612565445027, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.2517, | |
| "eval_samples_per_second": 18.111, | |
| "eval_steps_per_second": 9.078, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004188481675392671, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005235602094240838, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0062827225130890054, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0062827225130890054, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.269, | |
| "eval_samples_per_second": 18.097, | |
| "eval_steps_per_second": 9.071, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007329842931937173, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008376963350785341, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009424083769633508, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009424083769633508, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.2622, | |
| "eval_samples_per_second": 18.102, | |
| "eval_steps_per_second": 9.074, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010471204188481676, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 4.085, | |
| "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": 3649284499046400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |