| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005671506352087115, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.2686025408348456e-05, | |
| "grad_norm": 1.8904634714126587, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.2686025408348456e-05, | |
| "eval_loss": 3.410688638687134, | |
| "eval_runtime": 1237.3059, | |
| "eval_samples_per_second": 30.001, | |
| "eval_steps_per_second": 15.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.537205081669691e-05, | |
| "grad_norm": 1.8866937160491943, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.8678, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.805807622504538e-05, | |
| "grad_norm": 1.8513197898864746, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8435, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.074410163339382e-05, | |
| "grad_norm": 1.658372402191162, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 2.6602, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011343012704174228, | |
| "grad_norm": 2.2875466346740723, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 2.5661, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00013611615245009076, | |
| "grad_norm": 2.1735148429870605, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.4435, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001588021778584392, | |
| "grad_norm": 1.6200734376907349, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.4093, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00018148820326678765, | |
| "grad_norm": 1.4915409088134766, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 2.3486, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00020417422867513612, | |
| "grad_norm": 1.2556705474853516, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2992, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00022686025408348456, | |
| "grad_norm": 1.3379391431808472, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 2.2776, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000249546279491833, | |
| "grad_norm": 1.745252013206482, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.2814, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0002722323049001815, | |
| "grad_norm": 1.214249849319458, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2245, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00029491833030852996, | |
| "grad_norm": 0.9381669163703918, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 2.1434, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0003176043557168784, | |
| "grad_norm": 0.9755675196647644, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 2.1348, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00034029038112522685, | |
| "grad_norm": 1.4853951930999756, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1151, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003629764065335753, | |
| "grad_norm": 1.8705589771270752, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 2.1256, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003856624319419238, | |
| "grad_norm": 1.6596029996871948, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 2.121, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00040834845735027224, | |
| "grad_norm": 2.31752347946167, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1368, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0004310344827586207, | |
| "grad_norm": 3.1325747966766357, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.1559, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00045372050816696913, | |
| "grad_norm": 1.721400260925293, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 2.1241, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00047640653357531763, | |
| "grad_norm": 1.4676975011825562, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0461, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000499092558983666, | |
| "grad_norm": 1.8530941009521484, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 2.0458, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0005217785843920145, | |
| "grad_norm": 2.0539281368255615, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.054, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000544464609800363, | |
| "grad_norm": 1.7614209651947021, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.0725, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005671506352087115, | |
| "grad_norm": 1.2324997186660767, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 2.0791, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005671506352087115, | |
| "eval_loss": 2.161527633666992, | |
| "eval_runtime": 1239.3508, | |
| "eval_samples_per_second": 29.951, | |
| "eval_steps_per_second": 14.976, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 4894017925939200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |