| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008438818565400843, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009376465072667605, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009376465072667605, | |
| "eval_loss": NaN, | |
| "eval_runtime": 10.1455, | |
| "eval_samples_per_second": 44.354, | |
| "eval_steps_per_second": 22.177, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001875293014533521, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0028129395218002813, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0028129395218002813, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.1413, | |
| "eval_samples_per_second": 49.227, | |
| "eval_steps_per_second": 24.614, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003750586029067042, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0046882325363338025, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005625879043600563, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2749, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005625879043600563, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.2696, | |
| "eval_samples_per_second": 48.546, | |
| "eval_steps_per_second": 24.273, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006563525550867323, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007501172058134084, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008438818565400843, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008438818565400843, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.2011, | |
| "eval_samples_per_second": 48.907, | |
| "eval_steps_per_second": 24.454, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 398071494082560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |