| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1762977473065622, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0039177277179236044, | |
| "eval_loss": 0.6565777659416199, | |
| "eval_runtime": 12.4001, | |
| "eval_samples_per_second": 34.677, | |
| "eval_steps_per_second": 4.355, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011753183153770812, | |
| "grad_norm": 1.89078688621521, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6479, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019588638589618023, | |
| "eval_loss": 0.47148600220680237, | |
| "eval_runtime": 11.9158, | |
| "eval_samples_per_second": 36.087, | |
| "eval_steps_per_second": 4.532, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023506366307541625, | |
| "grad_norm": 1.0767256021499634, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5244, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03525954946131244, | |
| "grad_norm": 0.8303144574165344, | |
| "learning_rate": 9e-05, | |
| "loss": 0.4064, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.039177277179236046, | |
| "eval_loss": 0.3335666358470917, | |
| "eval_runtime": 11.9553, | |
| "eval_samples_per_second": 35.967, | |
| "eval_steps_per_second": 4.517, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04701273261508325, | |
| "grad_norm": 0.8014969229698181, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.304, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.058765915768854066, | |
| "grad_norm": 0.6403971314430237, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3211, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.058765915768854066, | |
| "eval_loss": 0.3230944275856018, | |
| "eval_runtime": 11.9552, | |
| "eval_samples_per_second": 35.968, | |
| "eval_steps_per_second": 4.517, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07051909892262488, | |
| "grad_norm": 0.6620733737945557, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3422, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07835455435847209, | |
| "eval_loss": 0.31188929080963135, | |
| "eval_runtime": 11.9726, | |
| "eval_samples_per_second": 35.915, | |
| "eval_steps_per_second": 4.51, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08227228207639568, | |
| "grad_norm": 0.6292542815208435, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.3624, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0940254652301665, | |
| "grad_norm": 0.6681432723999023, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.3253, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0979431929480901, | |
| "eval_loss": 0.30944231152534485, | |
| "eval_runtime": 11.9771, | |
| "eval_samples_per_second": 35.902, | |
| "eval_steps_per_second": 4.509, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10577864838393732, | |
| "grad_norm": 0.5953491926193237, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.3062, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11753183153770813, | |
| "grad_norm": 0.5565989017486572, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3038, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11753183153770813, | |
| "eval_loss": 0.30763861536979675, | |
| "eval_runtime": 11.9812, | |
| "eval_samples_per_second": 35.89, | |
| "eval_steps_per_second": 4.507, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12928501469147893, | |
| "grad_norm": 0.5618394613265991, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.3488, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13712047012732614, | |
| "eval_loss": 0.3044528067111969, | |
| "eval_runtime": 11.9827, | |
| "eval_samples_per_second": 35.885, | |
| "eval_steps_per_second": 4.507, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14103819784524976, | |
| "grad_norm": 0.5592698454856873, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.294, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15279138099902057, | |
| "grad_norm": 0.5278225541114807, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.2837, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15670910871694418, | |
| "eval_loss": 0.30300983786582947, | |
| "eval_runtime": 11.9966, | |
| "eval_samples_per_second": 35.844, | |
| "eval_steps_per_second": 4.501, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16454456415279137, | |
| "grad_norm": 0.5927110910415649, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.3451, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1762977473065622, | |
| "grad_norm": 0.5226899981498718, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2873, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1762977473065622, | |
| "eval_loss": 0.3025428354740143, | |
| "eval_runtime": 11.995, | |
| "eval_samples_per_second": 35.848, | |
| "eval_steps_per_second": 4.502, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.22465128808448e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |