| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5115089514066496, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010230179028132993, | |
| "eval_loss": 2.483304738998413, | |
| "eval_runtime": 5.4403, | |
| "eval_samples_per_second": 7.72, | |
| "eval_steps_per_second": 3.86, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05115089514066496, | |
| "grad_norm": 26.666269302368164, | |
| "learning_rate": 5e-05, | |
| "loss": 10.9039, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10230179028132992, | |
| "grad_norm": 15.509090423583984, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10230179028132992, | |
| "eval_loss": 2.162769079208374, | |
| "eval_runtime": 5.6657, | |
| "eval_samples_per_second": 7.413, | |
| "eval_steps_per_second": 3.706, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1534526854219949, | |
| "grad_norm": 10.331184387207031, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.3725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20460358056265984, | |
| "grad_norm": 7.912665843963623, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.717, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20460358056265984, | |
| "eval_loss": 1.9835408926010132, | |
| "eval_runtime": 5.7895, | |
| "eval_samples_per_second": 7.254, | |
| "eval_steps_per_second": 3.627, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2557544757033248, | |
| "grad_norm": 4.825455665588379, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.8041, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3069053708439898, | |
| "grad_norm": 6.498897075653076, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2391, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3069053708439898, | |
| "eval_loss": 1.9637117385864258, | |
| "eval_runtime": 5.8807, | |
| "eval_samples_per_second": 7.142, | |
| "eval_steps_per_second": 3.571, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35805626598465473, | |
| "grad_norm": 16.6773681640625, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 8.4421, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4092071611253197, | |
| "grad_norm": 4.831422328948975, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.9696, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4092071611253197, | |
| "eval_loss": 1.9575275182724, | |
| "eval_runtime": 5.9341, | |
| "eval_samples_per_second": 7.078, | |
| "eval_steps_per_second": 3.539, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46035805626598464, | |
| "grad_norm": 6.5614118576049805, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.1391, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5115089514066496, | |
| "grad_norm": 9.683886528015137, | |
| "learning_rate": 0.0, | |
| "loss": 8.4033, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5115089514066496, | |
| "eval_loss": 1.9544819593429565, | |
| "eval_runtime": 5.9739, | |
| "eval_samples_per_second": 7.031, | |
| "eval_steps_per_second": 3.515, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4109251085533184e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |