| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007827114690711563, | |
| "eval_steps": 2, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.130845876284625e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.130845876284625e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3425.8749, | |
| "eval_samples_per_second": 3.926, | |
| "eval_steps_per_second": 3.926, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.26169175256925e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.26169175256925e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3318.2461, | |
| "eval_samples_per_second": 4.053, | |
| "eval_steps_per_second": 4.053, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.392537628853876e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000125233835051385, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000125233835051385, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3321.6951, | |
| "eval_samples_per_second": 4.049, | |
| "eval_steps_per_second": 4.049, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015654229381423127, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018785075257707752, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00018785075257707752, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3370.752, | |
| "eval_samples_per_second": 3.99, | |
| "eval_steps_per_second": 3.99, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021915921133992377, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00025046767010277, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00025046767010277, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3267.2262, | |
| "eval_samples_per_second": 4.116, | |
| "eval_steps_per_second": 4.116, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002817761288656163, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00031308458762846253, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00031308458762846253, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3420.2031, | |
| "eval_samples_per_second": 3.932, | |
| "eval_steps_per_second": 3.932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003443930463913088, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00037570150515415504, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00037570150515415504, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3425.7094, | |
| "eval_samples_per_second": 3.926, | |
| "eval_steps_per_second": 3.926, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004070099639170013, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00043831842267984754, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00043831842267984754, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3212.3981, | |
| "eval_samples_per_second": 4.187, | |
| "eval_steps_per_second": 4.187, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0004696268814426938, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00050093534020554, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00050093534020554, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3323.0534, | |
| "eval_samples_per_second": 4.047, | |
| "eval_steps_per_second": 4.047, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005322437989683863, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005635522577312326, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005635522577312326, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3266.4933, | |
| "eval_samples_per_second": 4.117, | |
| "eval_steps_per_second": 4.117, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005948607164940788, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006261691752569251, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006261691752569251, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3211.5506, | |
| "eval_samples_per_second": 4.188, | |
| "eval_steps_per_second": 4.188, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006574776340197713, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006887860927826176, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0006887860927826176, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3316.0191, | |
| "eval_samples_per_second": 4.056, | |
| "eval_steps_per_second": 4.056, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0007200945515454638, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007514030103083101, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007514030103083101, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3210.49, | |
| "eval_samples_per_second": 4.189, | |
| "eval_steps_per_second": 4.189, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007827114690711563, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": 1.75782374670336e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |