| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009277430865298841, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007136485280999108, | |
| "grad_norm": 0.651326596736908, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007136485280999108, | |
| "eval_loss": 0.648069441318512, | |
| "eval_runtime": 25.8287, | |
| "eval_samples_per_second": 22.843, | |
| "eval_steps_per_second": 11.421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014272970561998216, | |
| "grad_norm": 0.7573561072349548, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9624, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0021409455842997323, | |
| "grad_norm": 0.5478392839431763, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5427, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002854594112399643, | |
| "grad_norm": 0.8651490807533264, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8517, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003568242640499554, | |
| "grad_norm": 0.6873601078987122, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7153, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004281891168599465, | |
| "grad_norm": 0.5542564988136292, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5211, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0049955396966993755, | |
| "grad_norm": 0.5318466424942017, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5258, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005709188224799286, | |
| "grad_norm": 0.6441726684570312, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4835, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006422836752899197, | |
| "grad_norm": 0.7914503812789917, | |
| "learning_rate": 0.00018, | |
| "loss": 0.5978, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007136485280999108, | |
| "grad_norm": 0.7218849062919617, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00785013380909902, | |
| "grad_norm": 0.9477095007896423, | |
| "learning_rate": 0.0001996917333733128, | |
| "loss": 0.5301, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00856378233719893, | |
| "grad_norm": 0.7516474723815918, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.4978, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009277430865298841, | |
| "grad_norm": 1.0167616605758667, | |
| "learning_rate": 0.00019723699203976766, | |
| "loss": 0.7239, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009277430865298841, | |
| "eval_loss": 0.5718203783035278, | |
| "eval_runtime": 25.8435, | |
| "eval_samples_per_second": 22.83, | |
| "eval_steps_per_second": 11.415, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3057746266030080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |