| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004579480405107882, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011742257448994569, | |
| "eval_loss": 10.336591720581055, | |
| "eval_runtime": 16.0812, | |
| "eval_samples_per_second": 222.993, | |
| "eval_steps_per_second": 111.497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005871128724497284, | |
| "grad_norm": 0.34773606061935425, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3354, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011742257448994569, | |
| "grad_norm": 0.34472596645355225, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3331, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011742257448994569, | |
| "eval_loss": 10.333213806152344, | |
| "eval_runtime": 16.1279, | |
| "eval_samples_per_second": 222.347, | |
| "eval_steps_per_second": 111.174, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017613386173491853, | |
| "grad_norm": 0.36585476994514465, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.33, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023484514897989138, | |
| "grad_norm": 0.3783927857875824, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3252, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0023484514897989138, | |
| "eval_loss": 10.325454711914062, | |
| "eval_runtime": 16.4274, | |
| "eval_samples_per_second": 218.293, | |
| "eval_steps_per_second": 109.147, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0029355643622486424, | |
| "grad_norm": 0.4327518045902252, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3212, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0035226772346983706, | |
| "grad_norm": 0.4167887270450592, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3203, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0035226772346983706, | |
| "eval_loss": 10.319473266601562, | |
| "eval_runtime": 16.4595, | |
| "eval_samples_per_second": 217.868, | |
| "eval_steps_per_second": 108.934, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004109790107148099, | |
| "grad_norm": 0.44718417525291443, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3154, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 507538145280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |