| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.88, | |
| "eval_steps": 500, | |
| "global_step": 54, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 3.518782377243042, | |
| "learning_rate": 4.894973780788722e-05, | |
| "loss": 4.2577, | |
| "num_input_tokens_seen": 5632, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 1.3019957542419434, | |
| "learning_rate": 4.588719528532342e-05, | |
| "loss": 3.7369, | |
| "num_input_tokens_seen": 11216, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.0758732557296753, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 3.3708, | |
| "num_input_tokens_seen": 16944, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 1.1637680530548096, | |
| "learning_rate": 3.490199415097892e-05, | |
| "loss": 3.2937, | |
| "num_input_tokens_seen": 23024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.0908918380737305, | |
| "learning_rate": 2.7902322853130757e-05, | |
| "loss": 3.1281, | |
| "num_input_tokens_seen": 28832, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.24705970287323, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 3.0746, | |
| "num_input_tokens_seen": 34928, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 1.3375575542449951, | |
| "learning_rate": 1.3780020494988446e-05, | |
| "loss": 3.2527, | |
| "num_input_tokens_seen": 40272, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 1.152417778968811, | |
| "learning_rate": 7.843959053281663e-06, | |
| "loss": 3.0867, | |
| "num_input_tokens_seen": 46448, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.3093425035476685, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 2.9973, | |
| "num_input_tokens_seen": 51616, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.0261815786361694, | |
| "learning_rate": 6.738782355044049e-07, | |
| "loss": 3.1154, | |
| "num_input_tokens_seen": 57440, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 54, | |
| "num_input_tokens_seen": 62256, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2649190082789376.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |