| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004677213783749021, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.6772137837490207e-05, | |
| "grad_norm": 4.8606743812561035, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8899, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.6772137837490207e-05, | |
| "eval_loss": 10.791738510131836, | |
| "eval_runtime": 274.7568, | |
| "eval_samples_per_second": 32.767, | |
| "eval_steps_per_second": 16.385, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.354427567498041e-05, | |
| "grad_norm": 5.791999816894531, | |
| "learning_rate": 4e-05, | |
| "loss": 10.6048, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00014031641351247063, | |
| "grad_norm": 5.240869522094727, | |
| "learning_rate": 6e-05, | |
| "loss": 10.5488, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014031641351247063, | |
| "eval_loss": 10.782638549804688, | |
| "eval_runtime": 268.6469, | |
| "eval_samples_per_second": 33.512, | |
| "eval_steps_per_second": 16.758, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00018708855134996083, | |
| "grad_norm": 5.7843337059021, | |
| "learning_rate": 8e-05, | |
| "loss": 10.0257, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023386068918745105, | |
| "grad_norm": 4.981315612792969, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0307, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00028063282702494127, | |
| "grad_norm": 4.7058820724487305, | |
| "learning_rate": 0.00012, | |
| "loss": 10.68, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00028063282702494127, | |
| "eval_loss": 10.681966781616211, | |
| "eval_runtime": 272.2499, | |
| "eval_samples_per_second": 33.069, | |
| "eval_steps_per_second": 16.536, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00032740496486243143, | |
| "grad_norm": 5.160103797912598, | |
| "learning_rate": 0.00014, | |
| "loss": 10.5204, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00037417710269992165, | |
| "grad_norm": 4.470202445983887, | |
| "learning_rate": 0.00016, | |
| "loss": 11.143, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00042094924053741187, | |
| "grad_norm": 4.327086448669434, | |
| "learning_rate": 0.00018, | |
| "loss": 10.5893, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00042094924053741187, | |
| "eval_loss": 10.49586296081543, | |
| "eval_runtime": 274.0449, | |
| "eval_samples_per_second": 32.852, | |
| "eval_steps_per_second": 16.428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004677213783749021, | |
| "grad_norm": 4.235734462738037, | |
| "learning_rate": 0.0002, | |
| "loss": 10.1739, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5429904015360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |