| { | |
| "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": 0.4435124099254608, | |
| "learning_rate": 4.894973780788722e-05, | |
| "loss": 0.6756, | |
| "num_input_tokens_seen": 50880, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.5012878775596619, | |
| "learning_rate": 4.588719528532342e-05, | |
| "loss": 0.6799, | |
| "num_input_tokens_seen": 99184, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.31872692704200745, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 0.6995, | |
| "num_input_tokens_seen": 147408, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.3336561322212219, | |
| "learning_rate": 3.490199415097892e-05, | |
| "loss": 0.6313, | |
| "num_input_tokens_seen": 195568, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.24536238610744476, | |
| "learning_rate": 2.7902322853130757e-05, | |
| "loss": 0.5683, | |
| "num_input_tokens_seen": 246416, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.2896718978881836, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.4988, | |
| "num_input_tokens_seen": 295744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 0.2828458249568939, | |
| "learning_rate": 1.3780020494988446e-05, | |
| "loss": 0.5748, | |
| "num_input_tokens_seen": 345744, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.37326768040657043, | |
| "learning_rate": 7.843959053281663e-06, | |
| "loss": 0.5793, | |
| "num_input_tokens_seen": 390176, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.28728172183036804, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.55, | |
| "num_input_tokens_seen": 438896, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.275715172290802, | |
| "learning_rate": 6.738782355044049e-07, | |
| "loss": 0.5715, | |
| "num_input_tokens_seen": 490544, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "num_input_tokens_seen": 530864, | |
| "step": 54, | |
| "total_flos": 4880889936150528.0, | |
| "train_loss": 0.5967088187182391, | |
| "train_runtime": 437.0311, | |
| "train_samples_per_second": 2.059, | |
| "train_steps_per_second": 0.124 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 54, | |
| "num_input_tokens_seen": 530864, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4880889936150528.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |