| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005783940888124124, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.7839408881241236e-05, | |
| "grad_norm": 0.025963636115193367, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.7839408881241236e-05, | |
| "eval_loss": 10.377110481262207, | |
| "eval_runtime": 20.2859, | |
| "eval_samples_per_second": 358.87, | |
| "eval_steps_per_second": 179.435, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011567881776248247, | |
| "grad_norm": 0.02218487486243248, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3814, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001735182266437237, | |
| "grad_norm": 0.02272448129951954, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3795, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001735182266437237, | |
| "eval_loss": 10.377097129821777, | |
| "eval_runtime": 20.2684, | |
| "eval_samples_per_second": 359.179, | |
| "eval_steps_per_second": 179.59, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023135763552496494, | |
| "grad_norm": 0.02646789513528347, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3793, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002891970444062062, | |
| "grad_norm": 0.024541642516851425, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3757, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003470364532874474, | |
| "grad_norm": 0.035220347344875336, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3789, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003470364532874474, | |
| "eval_loss": 10.377021789550781, | |
| "eval_runtime": 20.5696, | |
| "eval_samples_per_second": 353.921, | |
| "eval_steps_per_second": 176.96, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004048758621686886, | |
| "grad_norm": 0.040737032890319824, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3753, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004627152710499299, | |
| "grad_norm": 0.04791310429573059, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3787, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005205546799311712, | |
| "grad_norm": 0.04301610589027405, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3732, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005205546799311712, | |
| "eval_loss": 10.376879692077637, | |
| "eval_runtime": 20.7038, | |
| "eval_samples_per_second": 351.627, | |
| "eval_steps_per_second": 175.813, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005783940888124124, | |
| "grad_norm": 0.02783135324716568, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3781, | |
| "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": 203661803520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |