| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06472491909385113, | |
| "eval_steps": 4, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002157497303128371, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002157497303128371, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.0965, | |
| "eval_samples_per_second": 177.845, | |
| "eval_steps_per_second": 44.689, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004314994606256742, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006472491909385114, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008629989212513484, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008629989212513484, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.709, | |
| "eval_samples_per_second": 275.044, | |
| "eval_steps_per_second": 69.114, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010787486515641856, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012944983818770227, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015102481121898598, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017259978425026967, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017259978425026967, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7135, | |
| "eval_samples_per_second": 273.295, | |
| "eval_steps_per_second": 68.674, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019417475728155338, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021574973031283712, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023732470334412083, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025889967637540454, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025889967637540454, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7152, | |
| "eval_samples_per_second": 272.637, | |
| "eval_steps_per_second": 68.509, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028047464940668825, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030204962243797196, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.032362459546925564, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.034519956850053934, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.034519956850053934, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7215, | |
| "eval_samples_per_second": 270.276, | |
| "eval_steps_per_second": 67.915, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.036677454153182305, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.038834951456310676, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.040992448759439054, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.043149946062567425, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043149946062567425, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7258, | |
| "eval_samples_per_second": 268.661, | |
| "eval_steps_per_second": 67.51, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.045307443365695796, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04746494066882417, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04962243797195254, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05177993527508091, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05177993527508091, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7434, | |
| "eval_samples_per_second": 262.309, | |
| "eval_steps_per_second": 65.914, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05393743257820928, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05609492988133765, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05825242718446602, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06040992448759439, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06040992448759439, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7208, | |
| "eval_samples_per_second": 270.518, | |
| "eval_steps_per_second": 67.976, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06256742179072276, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06472491909385113, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1550057472000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |