| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000924513474783895, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0817115826129835e-05, | |
| "eval_loss": 1.8879210948944092, | |
| "eval_runtime": 421.0165, | |
| "eval_samples_per_second": 32.452, | |
| "eval_steps_per_second": 16.227, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.24513474783895e-05, | |
| "grad_norm": 27.458845138549805, | |
| "learning_rate": 3e-05, | |
| "loss": 19.0786, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000184902694956779, | |
| "grad_norm": 8.83002758026123, | |
| "learning_rate": 6e-05, | |
| "loss": 18.2119, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002465369266090387, | |
| "eval_loss": 1.8819901943206787, | |
| "eval_runtime": 417.6675, | |
| "eval_samples_per_second": 32.713, | |
| "eval_steps_per_second": 16.358, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002773540424351685, | |
| "grad_norm": 8.201346397399902, | |
| "learning_rate": 9e-05, | |
| "loss": 17.0207, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000369805389913558, | |
| "grad_norm": 10.684090614318848, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 14.1279, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004622567373919475, | |
| "grad_norm": 12.148521423339844, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 13.642, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004930738532180774, | |
| "eval_loss": 1.9308699369430542, | |
| "eval_runtime": 417.3387, | |
| "eval_samples_per_second": 32.738, | |
| "eval_steps_per_second": 16.37, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.000554708084870337, | |
| "grad_norm": 8.24918270111084, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 13.7149, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006471594323487265, | |
| "grad_norm": 20.51390266418457, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 12.6019, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000739610779827116, | |
| "grad_norm": 9.698060035705566, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 12.2582, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000739610779827116, | |
| "eval_loss": 1.9277873039245605, | |
| "eval_runtime": 416.4602, | |
| "eval_samples_per_second": 32.807, | |
| "eval_steps_per_second": 16.405, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008320621273055055, | |
| "grad_norm": 8.932806968688965, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 13.5358, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.000924513474783895, | |
| "grad_norm": 7.640513896942139, | |
| "learning_rate": 0.0, | |
| "loss": 11.9805, | |
| "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": 4316639570952192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |