| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012733987011333248, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.244662337111083e-05, | |
| "eval_loss": 4.8717498779296875, | |
| "eval_runtime": 2826.5415, | |
| "eval_samples_per_second": 10.528, | |
| "eval_steps_per_second": 2.632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012733987011333248, | |
| "grad_norm": 51.041725158691406, | |
| "learning_rate": 6e-05, | |
| "loss": 28.8506, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025467974022666496, | |
| "grad_norm": 33.79914093017578, | |
| "learning_rate": 0.00012, | |
| "loss": 24.9305, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003395729869688866, | |
| "eval_loss": 2.785485029220581, | |
| "eval_runtime": 2833.9295, | |
| "eval_samples_per_second": 10.501, | |
| "eval_steps_per_second": 2.625, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00038201961033999744, | |
| "grad_norm": 36.487548828125, | |
| "learning_rate": 0.00018, | |
| "loss": 17.2526, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005093594804533299, | |
| "grad_norm": 24.10533905029297, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 14.9313, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006366993505666624, | |
| "grad_norm": 25.62902069091797, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 14.2183, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006791459739377732, | |
| "eval_loss": 2.3047831058502197, | |
| "eval_runtime": 2837.1932, | |
| "eval_samples_per_second": 10.489, | |
| "eval_steps_per_second": 2.622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007640392206799949, | |
| "grad_norm": 18.13753890991211, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 13.969, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008913790907933274, | |
| "grad_norm": 15.9353666305542, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 13.4526, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0010187189609066599, | |
| "grad_norm": 16.094314575195312, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 13.4364, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010187189609066599, | |
| "eval_loss": 2.2031667232513428, | |
| "eval_runtime": 2836.1989, | |
| "eval_samples_per_second": 10.493, | |
| "eval_steps_per_second": 2.623, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0011460588310199923, | |
| "grad_norm": 18.387222290039062, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 12.7279, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0012733987011333248, | |
| "grad_norm": 15.67333698272705, | |
| "learning_rate": 0.0, | |
| "loss": 13.3088, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.164082744066048e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |