| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04479283314669653, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014930944382232176, | |
| "eval_loss": 11.933335304260254, | |
| "eval_runtime": 8.0932, | |
| "eval_samples_per_second": 34.968, | |
| "eval_steps_per_second": 17.546, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004479283314669653, | |
| "grad_norm": 0.14104795455932617, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9348, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008958566629339306, | |
| "grad_norm": 0.10298649221658707, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9314, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011944755505785741, | |
| "eval_loss": 11.931124687194824, | |
| "eval_runtime": 6.7692, | |
| "eval_samples_per_second": 41.807, | |
| "eval_steps_per_second": 20.977, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013437849944008958, | |
| "grad_norm": 0.10454890877008438, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9316, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01791713325867861, | |
| "grad_norm": 0.13820531964302063, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.9282, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022396416573348264, | |
| "grad_norm": 0.15883134305477142, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 11.9254, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023889511011571482, | |
| "eval_loss": 11.924610137939453, | |
| "eval_runtime": 6.3914, | |
| "eval_samples_per_second": 44.278, | |
| "eval_steps_per_second": 22.217, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.026875699888017916, | |
| "grad_norm": 0.16797775030136108, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.9236, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03135498320268757, | |
| "grad_norm": 0.15993663668632507, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 11.9209, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03583426651735722, | |
| "grad_norm": 0.20181462168693542, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 11.9192, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03583426651735722, | |
| "eval_loss": 11.919516563415527, | |
| "eval_runtime": 6.4456, | |
| "eval_samples_per_second": 43.906, | |
| "eval_steps_per_second": 22.03, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.040313549832026875, | |
| "grad_norm": 0.20186784863471985, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 11.9165, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04479283314669653, | |
| "grad_norm": 0.1875421553850174, | |
| "learning_rate": 0.0, | |
| "loss": 11.9174, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 12631660167168.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |