| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.1636913622140845e-05, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.1636913622140845e-06, | |
| "grad_norm": 3.333584785461426, | |
| "learning_rate": 2e-05, | |
| "loss": 10.6935, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.1636913622140845e-06, | |
| "eval_loss": 10.541769027709961, | |
| "eval_runtime": 1655.7005, | |
| "eval_samples_per_second": 61.077, | |
| "eval_steps_per_second": 30.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.327382724428169e-06, | |
| "grad_norm": 3.640157461166382, | |
| "learning_rate": 4e-05, | |
| "loss": 10.4759, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.2491074086642253e-05, | |
| "grad_norm": 2.783792018890381, | |
| "learning_rate": 6e-05, | |
| "loss": 10.6954, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.2491074086642253e-05, | |
| "eval_loss": 10.536866188049316, | |
| "eval_runtime": 1662.3212, | |
| "eval_samples_per_second": 60.834, | |
| "eval_steps_per_second": 30.417, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.6654765448856338e-05, | |
| "grad_norm": 3.113203525543213, | |
| "learning_rate": 8e-05, | |
| "loss": 10.4829, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0818456811070422e-05, | |
| "grad_norm": 4.432548999786377, | |
| "learning_rate": 0.0001, | |
| "loss": 9.137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.4982148173284507e-05, | |
| "grad_norm": 3.4199392795562744, | |
| "learning_rate": 0.00012, | |
| "loss": 10.2811, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.4982148173284507e-05, | |
| "eval_loss": 10.47288990020752, | |
| "eval_runtime": 1677.5588, | |
| "eval_samples_per_second": 60.281, | |
| "eval_steps_per_second": 30.141, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.914583953549859e-05, | |
| "grad_norm": 3.369419813156128, | |
| "learning_rate": 0.00014, | |
| "loss": 10.474, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 3.3309530897712676e-05, | |
| "grad_norm": 4.212067127227783, | |
| "learning_rate": 0.00016, | |
| "loss": 10.5524, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.7473222259926763e-05, | |
| "grad_norm": 2.955409288406372, | |
| "learning_rate": 0.00018, | |
| "loss": 10.5629, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.7473222259926763e-05, | |
| "eval_loss": 10.348594665527344, | |
| "eval_runtime": 1721.7887, | |
| "eval_samples_per_second": 58.733, | |
| "eval_steps_per_second": 29.367, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.1636913622140845e-05, | |
| "grad_norm": 2.8738622665405273, | |
| "learning_rate": 0.0002, | |
| "loss": 10.0493, | |
| "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 | |
| } | |