| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02030456852791878, | |
| "eval_steps": 13, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007809449433814916, | |
| "grad_norm": 175.4751434326172, | |
| "learning_rate": 1e-05, | |
| "loss": 36.1201, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007809449433814916, | |
| "eval_loss": 3.8799195289611816, | |
| "eval_runtime": 315.5656, | |
| "eval_samples_per_second": 6.835, | |
| "eval_steps_per_second": 3.419, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015618898867629833, | |
| "grad_norm": 238.4190673828125, | |
| "learning_rate": 2e-05, | |
| "loss": 50.8572, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023428348301444747, | |
| "grad_norm": 363.2473449707031, | |
| "learning_rate": 3e-05, | |
| "loss": 69.5408, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0031237797735259665, | |
| "grad_norm": 166.27882385253906, | |
| "learning_rate": 4e-05, | |
| "loss": 36.4834, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003904724716907458, | |
| "grad_norm": 206.5617218017578, | |
| "learning_rate": 5e-05, | |
| "loss": 43.0769, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004685669660288949, | |
| "grad_norm": 192.99514770507812, | |
| "learning_rate": 6e-05, | |
| "loss": 57.0914, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005466614603670442, | |
| "grad_norm": 187.74777221679688, | |
| "learning_rate": 7e-05, | |
| "loss": 41.0429, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006247559547051933, | |
| "grad_norm": 242.54119873046875, | |
| "learning_rate": 8e-05, | |
| "loss": 50.7796, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007028504490433424, | |
| "grad_norm": 88.46190643310547, | |
| "learning_rate": 9e-05, | |
| "loss": 23.8709, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007809449433814916, | |
| "grad_norm": 102.14177703857422, | |
| "learning_rate": 0.0001, | |
| "loss": 22.4249, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008590394377196407, | |
| "grad_norm": 71.25434875488281, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 20.7456, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009371339320577899, | |
| "grad_norm": 97.2330551147461, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 20.3148, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01015228426395939, | |
| "grad_norm": 71.13471221923828, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 17.7955, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01015228426395939, | |
| "eval_loss": 1.2057011127471924, | |
| "eval_runtime": 300.8171, | |
| "eval_samples_per_second": 7.17, | |
| "eval_steps_per_second": 3.587, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010933229207340883, | |
| "grad_norm": 70.08533477783203, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 17.0262, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011714174150722375, | |
| "grad_norm": 69.94759368896484, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 18.1821, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012495119094103866, | |
| "grad_norm": 58.61181640625, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 17.1924, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013276064037485357, | |
| "grad_norm": 54.452816009521484, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 14.6744, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014057008980866849, | |
| "grad_norm": 67.27265930175781, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 17.592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01483795392424834, | |
| "grad_norm": 51.187679290771484, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 20.2565, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015618898867629832, | |
| "grad_norm": 45.95616912841797, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 16.9602, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016399843811011325, | |
| "grad_norm": 46.94184112548828, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 16.319, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017180788754392814, | |
| "grad_norm": 43.87798309326172, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 12.6792, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.017961733697774308, | |
| "grad_norm": 51.43169403076172, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 16.1705, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018742678641155797, | |
| "grad_norm": 47.817901611328125, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 11.841, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01952362358453729, | |
| "grad_norm": 56.87557601928711, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 17.5764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02030456852791878, | |
| "grad_norm": 45.88191223144531, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 13.4572, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02030456852791878, | |
| "eval_loss": 0.8506395816802979, | |
| "eval_runtime": 300.4403, | |
| "eval_samples_per_second": 7.179, | |
| "eval_steps_per_second": 3.591, | |
| "step": 26 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": 1.4625093572571955e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |