| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011534025374855825, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011534025374855825, | |
| "grad_norm": 0.7663769721984863, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1576, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011534025374855825, | |
| "eval_loss": 1.263037085533142, | |
| "eval_runtime": 9.8372, | |
| "eval_samples_per_second": 37.104, | |
| "eval_steps_per_second": 18.603, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002306805074971165, | |
| "grad_norm": 0.7588536143302917, | |
| "learning_rate": 4e-05, | |
| "loss": 1.202, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034602076124567475, | |
| "grad_norm": 0.8643565773963928, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2996, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034602076124567475, | |
| "eval_loss": 1.2619091272354126, | |
| "eval_runtime": 8.6111, | |
| "eval_samples_per_second": 42.387, | |
| "eval_steps_per_second": 21.252, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00461361014994233, | |
| "grad_norm": 0.9262787699699402, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1697, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0057670126874279125, | |
| "grad_norm": 0.9554668664932251, | |
| "learning_rate": 0.0001, | |
| "loss": 1.294, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006920415224913495, | |
| "grad_norm": 0.7350440621376038, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1799, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006920415224913495, | |
| "eval_loss": 1.2279199361801147, | |
| "eval_runtime": 8.5469, | |
| "eval_samples_per_second": 42.706, | |
| "eval_steps_per_second": 21.411, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008073817762399077, | |
| "grad_norm": 0.70282381772995, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1493, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00922722029988466, | |
| "grad_norm": 1.0191278457641602, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3848, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010380622837370242, | |
| "grad_norm": 0.8667598962783813, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1629, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010380622837370242, | |
| "eval_loss": 1.118059754371643, | |
| "eval_runtime": 8.7457, | |
| "eval_samples_per_second": 41.735, | |
| "eval_steps_per_second": 20.925, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011534025374855825, | |
| "grad_norm": 1.0189145803451538, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2477, | |
| "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": 324298258513920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |