| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.986666666666667, | |
| "eval_steps": 500, | |
| "global_step": 168, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 6.429335594177246, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 2.8371, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 6.359095573425293, | |
| "learning_rate": 4.995131923687488e-06, | |
| "loss": 2.5866, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 6.2563042640686035, | |
| "learning_rate": 4.90911473983908e-06, | |
| "loss": 2.1317, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 5.7428483963012695, | |
| "learning_rate": 4.71919261421297e-06, | |
| "loss": 1.6483, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 5.202849388122559, | |
| "learning_rate": 4.43355687413747e-06, | |
| "loss": 1.258, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 3.334800958633423, | |
| "learning_rate": 4.064526968101844e-06, | |
| "loss": 0.9961, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 5.201640605926514, | |
| "learning_rate": 3.6280191288478437e-06, | |
| "loss": 0.6742, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 4.489432334899902, | |
| "learning_rate": 3.142859907420615e-06, | |
| "loss": 0.4521, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 3.431414842605591, | |
| "learning_rate": 2.629974185404951e-06, | |
| "loss": 0.3905, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 2.042440414428711, | |
| "learning_rate": 2.1114826863194882e-06, | |
| "loss": 0.2197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 2.322110891342163, | |
| "learning_rate": 1.6097479104361328e-06, | |
| "loss": 0.235, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 2.210110664367676, | |
| "learning_rate": 1.1464096417858821e-06, | |
| "loss": 0.177, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 1.0164854526519775, | |
| "learning_rate": 7.414516258630245e-07, | |
| "loss": 0.1756, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 4.7322163581848145, | |
| "learning_rate": 4.123396721497977e-07, | |
| "loss": 0.1916, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 2.4119203090667725, | |
| "learning_rate": 1.7326835503629542e-07, | |
| "loss": 0.1296, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 1.8030685186386108, | |
| "learning_rate": 3.4548802869627806e-08, | |
| "loss": 0.1469, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.986666666666667, | |
| "step": 168, | |
| "total_flos": 1.7300235104796672e+16, | |
| "train_loss": 0.8548009863921574, | |
| "train_runtime": 612.7985, | |
| "train_samples_per_second": 4.406, | |
| "train_steps_per_second": 0.274 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 168, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7300235104796672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |