| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028308563340410473, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005661712668082095, | |
| "grad_norm": 0.683922290802002, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005661712668082095, | |
| "eval_loss": 0.8376506567001343, | |
| "eval_runtime": 58.0143, | |
| "eval_samples_per_second": 5.137, | |
| "eval_steps_per_second": 2.568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01132342533616419, | |
| "grad_norm": 0.7218406200408936, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9107, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01132342533616419, | |
| "eval_loss": 0.7961345911026001, | |
| "eval_runtime": 12.4565, | |
| "eval_samples_per_second": 23.923, | |
| "eval_steps_per_second": 11.962, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016985138004246284, | |
| "grad_norm": 0.6535455584526062, | |
| "learning_rate": 3e-05, | |
| "loss": 0.685, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02264685067232838, | |
| "grad_norm": 0.6205967664718628, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6768, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02264685067232838, | |
| "eval_loss": 0.7685829997062683, | |
| "eval_runtime": 12.4916, | |
| "eval_samples_per_second": 23.856, | |
| "eval_steps_per_second": 11.928, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.028308563340410473, | |
| "grad_norm": 0.6546658277511597, | |
| "learning_rate": 5e-05, | |
| "loss": 0.831, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6970544184360960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |