| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00016752944329965992, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.675294432996599e-05, | |
| "grad_norm": 8.606852531433105, | |
| "learning_rate": 2e-05, | |
| "loss": 2.468, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.675294432996599e-05, | |
| "eval_loss": 0.8240411877632141, | |
| "eval_runtime": 1055.7422, | |
| "eval_samples_per_second": 23.807, | |
| "eval_steps_per_second": 11.903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.350588865993198e-05, | |
| "grad_norm": 9.772021293640137, | |
| "learning_rate": 4e-05, | |
| "loss": 4.0359, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.025883298989798e-05, | |
| "grad_norm": 9.944804191589355, | |
| "learning_rate": 6e-05, | |
| "loss": 3.6989, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.025883298989798e-05, | |
| "eval_loss": 0.81992506980896, | |
| "eval_runtime": 1054.7573, | |
| "eval_samples_per_second": 23.829, | |
| "eval_steps_per_second": 11.915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.701177731986397e-05, | |
| "grad_norm": 10.078585624694824, | |
| "learning_rate": 8e-05, | |
| "loss": 2.9309, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.376472164982996e-05, | |
| "grad_norm": 9.224305152893066, | |
| "learning_rate": 0.0001, | |
| "loss": 4.375, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010051766597979596, | |
| "grad_norm": 10.948613166809082, | |
| "learning_rate": 0.00012, | |
| "loss": 4.1354, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010051766597979596, | |
| "eval_loss": 0.7942958474159241, | |
| "eval_runtime": 1055.5199, | |
| "eval_samples_per_second": 23.812, | |
| "eval_steps_per_second": 11.906, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011727061030976194, | |
| "grad_norm": 25.083349227905273, | |
| "learning_rate": 0.00014, | |
| "loss": 3.8921, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00013402355463972793, | |
| "grad_norm": 4.070237636566162, | |
| "learning_rate": 0.00016, | |
| "loss": 2.564, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001507764989696939, | |
| "grad_norm": 11.22966480255127, | |
| "learning_rate": 0.00018, | |
| "loss": 2.7637, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001507764989696939, | |
| "eval_loss": 0.7840443849563599, | |
| "eval_runtime": 1055.8145, | |
| "eval_samples_per_second": 23.805, | |
| "eval_steps_per_second": 11.903, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00016752944329965992, | |
| "grad_norm": 5.25059175491333, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8051, | |
| "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": 2453740518899712.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |