| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000140491368561544, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.40491368561544e-05, | |
| "grad_norm": 11.456639289855957, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8262, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.40491368561544e-05, | |
| "eval_loss": 12.163054466247559, | |
| "eval_runtime": 413.6256, | |
| "eval_samples_per_second": 72.457, | |
| "eval_steps_per_second": 36.228, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.80982737123088e-05, | |
| "grad_norm": 5.828180313110352, | |
| "learning_rate": 4e-05, | |
| "loss": 10.0953, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.21474105684632e-05, | |
| "grad_norm": 7.734110355377197, | |
| "learning_rate": 6e-05, | |
| "loss": 10.6375, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.21474105684632e-05, | |
| "eval_loss": 12.15479564666748, | |
| "eval_runtime": 419.0796, | |
| "eval_samples_per_second": 71.514, | |
| "eval_steps_per_second": 35.757, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.61965474246176e-05, | |
| "grad_norm": 5.531479835510254, | |
| "learning_rate": 8e-05, | |
| "loss": 11.6567, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 7.0245684280772e-05, | |
| "grad_norm": 4.737807273864746, | |
| "learning_rate": 0.0001, | |
| "loss": 11.0582, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.42948211369264e-05, | |
| "grad_norm": 26.38648223876953, | |
| "learning_rate": 0.00012, | |
| "loss": 11.8254, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 8.42948211369264e-05, | |
| "eval_loss": 12.05859088897705, | |
| "eval_runtime": 414.2123, | |
| "eval_samples_per_second": 72.354, | |
| "eval_steps_per_second": 36.177, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.83439579930808e-05, | |
| "grad_norm": 13.912890434265137, | |
| "learning_rate": 0.00014, | |
| "loss": 12.4402, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001123930948492352, | |
| "grad_norm": 3.7871077060699463, | |
| "learning_rate": 0.00016, | |
| "loss": 10.6176, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001264422317053896, | |
| "grad_norm": 7.042935848236084, | |
| "learning_rate": 0.00018, | |
| "loss": 10.2955, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001264422317053896, | |
| "eval_loss": 11.75953197479248, | |
| "eval_runtime": 408.0518, | |
| "eval_samples_per_second": 73.447, | |
| "eval_steps_per_second": 36.723, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000140491368561544, | |
| "grad_norm": 6.2739386558532715, | |
| "learning_rate": 0.0002, | |
| "loss": 11.6255, | |
| "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": 34292650475520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |