| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00183452577508714, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000183452577508714, | |
| "grad_norm": 0.028588224202394485, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000183452577508714, | |
| "eval_loss": 10.370526313781738, | |
| "eval_runtime": 5.8217, | |
| "eval_samples_per_second": 394.383, | |
| "eval_steps_per_second": 197.192, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000366905155017428, | |
| "grad_norm": 0.02612861804664135, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3846, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000550357732526142, | |
| "grad_norm": 0.029587959870696068, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3683, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000550357732526142, | |
| "eval_loss": 10.370508193969727, | |
| "eval_runtime": 5.8175, | |
| "eval_samples_per_second": 394.67, | |
| "eval_steps_per_second": 197.335, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000733810310034856, | |
| "grad_norm": 0.03267481550574303, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3583, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00091726288754357, | |
| "grad_norm": 0.03008592501282692, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3734, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001100715465052284, | |
| "grad_norm": 0.02972247451543808, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3822, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001100715465052284, | |
| "eval_loss": 10.370424270629883, | |
| "eval_runtime": 5.9079, | |
| "eval_samples_per_second": 388.632, | |
| "eval_steps_per_second": 194.316, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001284168042560998, | |
| "grad_norm": 0.019545597955584526, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3802, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001467620620069712, | |
| "grad_norm": 0.027489911764860153, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3802, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001651073197578426, | |
| "grad_norm": 0.02614646963775158, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3815, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001651073197578426, | |
| "eval_loss": 10.370317459106445, | |
| "eval_runtime": 6.0491, | |
| "eval_samples_per_second": 379.558, | |
| "eval_steps_per_second": 189.779, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00183452577508714, | |
| "grad_norm": 0.024775221943855286, | |
| "learning_rate": 0.0002, | |
| "loss": 10.369, | |
| "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": 129309081600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |