| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07163323782234957, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0028653295128939827, | |
| "grad_norm": 0.18870845437049866, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028653295128939827, | |
| "eval_loss": 10.36025333404541, | |
| "eval_runtime": 1.0201, | |
| "eval_samples_per_second": 288.212, | |
| "eval_steps_per_second": 36.272, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0057306590257879654, | |
| "grad_norm": 0.21544590592384338, | |
| "learning_rate": 2e-05, | |
| "loss": 10.362, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008595988538681949, | |
| "grad_norm": 0.21012459695339203, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3787, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011461318051575931, | |
| "grad_norm": 0.17221978306770325, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3589, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014326647564469915, | |
| "grad_norm": 0.19953270256519318, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017191977077363897, | |
| "grad_norm": 0.2154458910226822, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3715, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02005730659025788, | |
| "grad_norm": 0.18448343873023987, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3615, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.022922636103151862, | |
| "grad_norm": 0.17267638444900513, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3744, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.025787965616045846, | |
| "grad_norm": 0.21264782547950745, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3635, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025787965616045846, | |
| "eval_loss": 10.357918739318848, | |
| "eval_runtime": 1.0313, | |
| "eval_samples_per_second": 285.087, | |
| "eval_steps_per_second": 35.878, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02865329512893983, | |
| "grad_norm": 0.20090581476688385, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3682, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03151862464183381, | |
| "grad_norm": 0.2009212225675583, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3545, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.034383954154727794, | |
| "grad_norm": 0.17764975130558014, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3667, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03724928366762178, | |
| "grad_norm": 0.19756364822387695, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3524, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04011461318051576, | |
| "grad_norm": 0.21011871099472046, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3613, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04297994269340974, | |
| "grad_norm": 0.20613764226436615, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3708, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.045845272206303724, | |
| "grad_norm": 0.27395445108413696, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.347, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04871060171919771, | |
| "grad_norm": 0.20352178812026978, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3532, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05157593123209169, | |
| "grad_norm": 0.2129252851009369, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.354, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05157593123209169, | |
| "eval_loss": 10.35179328918457, | |
| "eval_runtime": 1.0103, | |
| "eval_samples_per_second": 290.994, | |
| "eval_steps_per_second": 36.622, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.054441260744985676, | |
| "grad_norm": 0.1703406721353531, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3596, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05730659025787966, | |
| "grad_norm": 0.2214614599943161, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3457, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06017191977077364, | |
| "grad_norm": 0.2195059061050415, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3563, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06303724928366762, | |
| "grad_norm": 0.21687962114810944, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3525, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0659025787965616, | |
| "grad_norm": 0.20921839773654938, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3405, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06876790830945559, | |
| "grad_norm": 0.21130795776844025, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07163323782234957, | |
| "grad_norm": 0.22695602476596832, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3385, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1307561164800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |