| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4, | |
| "eval_steps": 10, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 6.3205, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 122.68202209472656, | |
| "learning_rate": 0.00016, | |
| "loss": 3.0413, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.1581363677978516, | |
| "eval_runtime": 326.3661, | |
| "eval_samples_per_second": 0.613, | |
| "eval_steps_per_second": 0.306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 27.173540115356445, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.9496, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 5.725452899932861, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.4737, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.3738737404346466, | |
| "eval_runtime": 324.9089, | |
| "eval_samples_per_second": 0.616, | |
| "eval_steps_per_second": 0.308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 4.0513529777526855, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.3124, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1864510458066432.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |