| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021856012589063253, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.37120251781265e-05, | |
| "eval_loss": 0.6611042618751526, | |
| "eval_runtime": 1067.3576, | |
| "eval_samples_per_second": 9.025, | |
| "eval_steps_per_second": 4.513, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021856012589063252, | |
| "grad_norm": 8.553230285644531, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00043712025178126504, | |
| "grad_norm": 4.837798595428467, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2083, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00043712025178126504, | |
| "eval_loss": 0.5364651679992676, | |
| "eval_runtime": 1071.4511, | |
| "eval_samples_per_second": 8.991, | |
| "eval_steps_per_second": 4.496, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006556803776718975, | |
| "grad_norm": 5.863097190856934, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0983, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008742405035625301, | |
| "grad_norm": 5.090754985809326, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1696, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008742405035625301, | |
| "eval_loss": 0.4852387309074402, | |
| "eval_runtime": 1072.4751, | |
| "eval_samples_per_second": 8.982, | |
| "eval_steps_per_second": 4.491, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010928006294531627, | |
| "grad_norm": 4.771880626678467, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9564, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001311360755343795, | |
| "grad_norm": 5.076868057250977, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6832, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001311360755343795, | |
| "eval_loss": 0.4634621739387512, | |
| "eval_runtime": 1069.2871, | |
| "eval_samples_per_second": 9.009, | |
| "eval_steps_per_second": 4.505, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015299208812344276, | |
| "grad_norm": 4.293688774108887, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9451, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0017484810071250602, | |
| "grad_norm": 4.276152610778809, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.635, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017484810071250602, | |
| "eval_loss": 0.45457473397254944, | |
| "eval_runtime": 1071.3804, | |
| "eval_samples_per_second": 8.991, | |
| "eval_steps_per_second": 4.496, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0019670411330156927, | |
| "grad_norm": 4.214913845062256, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7661, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0021856012589063253, | |
| "grad_norm": 3.808881998062134, | |
| "learning_rate": 0.0, | |
| "loss": 1.8696, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021856012589063253, | |
| "eval_loss": 0.4522906243801117, | |
| "eval_runtime": 1070.7411, | |
| "eval_samples_per_second": 8.997, | |
| "eval_steps_per_second": 4.499, | |
| "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": 1.6562748502573056e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |