| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.75609756097561, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.9049399495124817, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 2.2562, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.8101117610931396, | |
| "learning_rate": 4.88544474393531e-05, | |
| "loss": 2.1366, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 0.6929331421852112, | |
| "learning_rate": 4.750673854447439e-05, | |
| "loss": 1.9538, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 0.754576563835144, | |
| "learning_rate": 4.615902964959569e-05, | |
| "loss": 1.9039, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 0.8291248679161072, | |
| "learning_rate": 4.4811320754716985e-05, | |
| "loss": 1.8062, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.341463414634146, | |
| "grad_norm": 0.9486225247383118, | |
| "learning_rate": 4.3463611859838275e-05, | |
| "loss": 1.7765, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.7317073170731705, | |
| "grad_norm": 1.1279809474945068, | |
| "learning_rate": 4.211590296495957e-05, | |
| "loss": 1.7288, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.1219512195121952, | |
| "grad_norm": 1.1358485221862793, | |
| "learning_rate": 4.076819407008086e-05, | |
| "loss": 1.7136, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.5121951219512195, | |
| "grad_norm": 1.2939114570617676, | |
| "learning_rate": 3.942048517520216e-05, | |
| "loss": 1.698, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.902439024390244, | |
| "grad_norm": 1.3795692920684814, | |
| "learning_rate": 3.807277628032345e-05, | |
| "loss": 1.668, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.2926829268292686, | |
| "grad_norm": 1.2294673919677734, | |
| "learning_rate": 3.672506738544474e-05, | |
| "loss": 1.6258, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.682926829268292, | |
| "grad_norm": 1.4048880338668823, | |
| "learning_rate": 3.537735849056604e-05, | |
| "loss": 1.6133, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.073170731707317, | |
| "grad_norm": 1.1704691648483276, | |
| "learning_rate": 3.4029649595687336e-05, | |
| "loss": 1.6349, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.463414634146342, | |
| "grad_norm": 1.4525257349014282, | |
| "learning_rate": 3.2681940700808625e-05, | |
| "loss": 1.5788, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.853658536585366, | |
| "grad_norm": 1.5394439697265625, | |
| "learning_rate": 3.133423180592992e-05, | |
| "loss": 1.5827, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.2439024390243905, | |
| "grad_norm": 1.5792720317840576, | |
| "learning_rate": 2.998652291105121e-05, | |
| "loss": 1.5451, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.634146341463414, | |
| "grad_norm": 1.6444499492645264, | |
| "learning_rate": 2.863881401617251e-05, | |
| "loss": 1.5757, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.024390243902439, | |
| "grad_norm": 1.5749609470367432, | |
| "learning_rate": 2.7291105121293804e-05, | |
| "loss": 1.5414, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.414634146341464, | |
| "grad_norm": 1.6040682792663574, | |
| "learning_rate": 2.5943396226415094e-05, | |
| "loss": 1.5311, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 7.804878048780488, | |
| "grad_norm": 1.7397934198379517, | |
| "learning_rate": 2.459568733153639e-05, | |
| "loss": 1.534, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.195121951219512, | |
| "grad_norm": 1.9339927434921265, | |
| "learning_rate": 2.3247978436657683e-05, | |
| "loss": 1.5277, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.585365853658537, | |
| "grad_norm": 1.8686648607254028, | |
| "learning_rate": 2.1900269541778976e-05, | |
| "loss": 1.496, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.975609756097562, | |
| "grad_norm": 1.8943285942077637, | |
| "learning_rate": 2.055256064690027e-05, | |
| "loss": 1.4955, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.365853658536585, | |
| "grad_norm": 2.715195894241333, | |
| "learning_rate": 1.9204851752021562e-05, | |
| "loss": 1.4837, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 9.75609756097561, | |
| "grad_norm": 2.464538097381592, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 1.5082, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 765, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.137043399013171e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |