| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02577873254564984, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 11.935391426086426, | |
| "eval_runtime": 11.8148, | |
| "eval_samples_per_second": 41.473, | |
| "eval_steps_per_second": 20.737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025778732545649837, | |
| "grad_norm": 0.18321779370307922, | |
| "learning_rate": 6e-05, | |
| "loss": 11.932, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0051557465091299675, | |
| "grad_norm": 0.17402371764183044, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9445, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006874328678839957, | |
| "eval_loss": 11.934998512268066, | |
| "eval_runtime": 10.7733, | |
| "eval_samples_per_second": 45.483, | |
| "eval_steps_per_second": 22.741, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007733619763694952, | |
| "grad_norm": 0.16528859734535217, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9381, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010311493018259935, | |
| "grad_norm": 0.1380218118429184, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.9345, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 0.16005918383598328, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 11.934, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013748657357679914, | |
| "eval_loss": 11.933707237243652, | |
| "eval_runtime": 11.4809, | |
| "eval_samples_per_second": 42.68, | |
| "eval_steps_per_second": 21.34, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015467239527389903, | |
| "grad_norm": 0.16136936843395233, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.9344, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01804511278195489, | |
| "grad_norm": 0.17389021813869476, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 11.929, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02062298603651987, | |
| "grad_norm": 0.1395042985677719, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 11.9328, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02062298603651987, | |
| "eval_loss": 11.932944297790527, | |
| "eval_runtime": 11.3832, | |
| "eval_samples_per_second": 43.046, | |
| "eval_steps_per_second": 21.523, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023200859291084855, | |
| "grad_norm": 0.1960669457912445, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 11.9328, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 0.23246870934963226, | |
| "learning_rate": 0.0, | |
| "loss": 11.929, | |
| "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": 7617081507840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |