| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007493817600479605, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.497939200159868e-05, | |
| "eval_loss": 2.177466869354248, | |
| "eval_runtime": 418.6691, | |
| "eval_samples_per_second": 40.263, | |
| "eval_steps_per_second": 20.133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.493817600479604e-05, | |
| "grad_norm": 2.524216413497925, | |
| "learning_rate": 6e-05, | |
| "loss": 8.8213, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001498763520095921, | |
| "grad_norm": 2.597292423248291, | |
| "learning_rate": 0.00012, | |
| "loss": 9.1385, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019983513601278945, | |
| "eval_loss": 2.051755428314209, | |
| "eval_runtime": 415.2269, | |
| "eval_samples_per_second": 40.597, | |
| "eval_steps_per_second": 20.3, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00022481452801438812, | |
| "grad_norm": 2.427201747894287, | |
| "learning_rate": 0.00018, | |
| "loss": 8.4028, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002997527040191842, | |
| "grad_norm": 3.1478488445281982, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 8.1319, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00037469088002398023, | |
| "grad_norm": 3.0699024200439453, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 8.243, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003996702720255789, | |
| "eval_loss": 1.852637767791748, | |
| "eval_runtime": 415.5245, | |
| "eval_samples_per_second": 40.568, | |
| "eval_steps_per_second": 20.285, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00044962905602877624, | |
| "grad_norm": 3.0072250366210938, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.9661, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005245672320335723, | |
| "grad_norm": 2.8843653202056885, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 7.7912, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0005995054080383684, | |
| "grad_norm": 2.694774627685547, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 7.3834, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005995054080383684, | |
| "eval_loss": 1.754106879234314, | |
| "eval_runtime": 415.5851, | |
| "eval_samples_per_second": 40.562, | |
| "eval_steps_per_second": 20.282, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006744435840431644, | |
| "grad_norm": 2.984825611114502, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 7.4132, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0007493817600479605, | |
| "grad_norm": 2.498382329940796, | |
| "learning_rate": 0.0, | |
| "loss": 7.2103, | |
| "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": 583731655999488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |