| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0031338138514572234, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031338138514572234, | |
| "grad_norm": 3.1303551197052, | |
| "learning_rate": 2e-05, | |
| "loss": 3.4776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031338138514572234, | |
| "eval_loss": 3.1475110054016113, | |
| "eval_runtime": 32.2503, | |
| "eval_samples_per_second": 41.674, | |
| "eval_steps_per_second": 20.837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006267627702914447, | |
| "grad_norm": 2.9911553859710693, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9316, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000940144155437167, | |
| "grad_norm": 2.444861650466919, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1306, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000940144155437167, | |
| "eval_loss": 3.122896909713745, | |
| "eval_runtime": 30.8863, | |
| "eval_samples_per_second": 43.514, | |
| "eval_steps_per_second": 21.757, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012535255405828893, | |
| "grad_norm": 3.228121757507324, | |
| "learning_rate": 8e-05, | |
| "loss": 3.6865, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015669069257286117, | |
| "grad_norm": 3.7739205360412598, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1468, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001880288310874334, | |
| "grad_norm": 1.4495387077331543, | |
| "learning_rate": 0.00012, | |
| "loss": 3.0667, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001880288310874334, | |
| "eval_loss": 2.9685263633728027, | |
| "eval_runtime": 30.6729, | |
| "eval_samples_per_second": 43.817, | |
| "eval_steps_per_second": 21.909, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0021936696960200563, | |
| "grad_norm": 0.9425989985466003, | |
| "learning_rate": 0.00014, | |
| "loss": 2.8153, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025070510811657787, | |
| "grad_norm": 0.8482406735420227, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8272, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002820432466311501, | |
| "grad_norm": 0.7540348172187805, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8656, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002820432466311501, | |
| "eval_loss": 2.9086689949035645, | |
| "eval_runtime": 30.2979, | |
| "eval_samples_per_second": 44.359, | |
| "eval_steps_per_second": 22.18, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031338138514572234, | |
| "grad_norm": 0.7617051601409912, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9328, | |
| "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": 153447605207040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |