| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008614810294698302, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.8716034315661008e-05, | |
| "eval_loss": 0.6277486085891724, | |
| "eval_runtime": 3963.8601, | |
| "eval_samples_per_second": 3.699, | |
| "eval_steps_per_second": 1.85, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.614810294698303e-05, | |
| "grad_norm": 10.357335090637207, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2861, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00017229620589396605, | |
| "grad_norm": 4.4522705078125, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0703, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00022972827452528806, | |
| "eval_loss": 0.4868163764476776, | |
| "eval_runtime": 3964.4349, | |
| "eval_samples_per_second": 3.699, | |
| "eval_steps_per_second": 1.849, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00025844430884094905, | |
| "grad_norm": 1.8443008661270142, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9082, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003445924117879321, | |
| "grad_norm": 2.81721568107605, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.752, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004307405147349151, | |
| "grad_norm": 2.9363415241241455, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9166, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004594565490505761, | |
| "eval_loss": 0.4595007300376892, | |
| "eval_runtime": 3964.9019, | |
| "eval_samples_per_second": 3.698, | |
| "eval_steps_per_second": 1.849, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005168886176818981, | |
| "grad_norm": 1.9836229085922241, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.027, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006030367206288812, | |
| "grad_norm": 2.3975160121917725, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.9556, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006891848235758642, | |
| "grad_norm": 1.2486457824707031, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.8344, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006891848235758642, | |
| "eval_loss": 0.44342318177223206, | |
| "eval_runtime": 3966.1386, | |
| "eval_samples_per_second": 3.697, | |
| "eval_steps_per_second": 1.849, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007753329265228472, | |
| "grad_norm": 1.603333592414856, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.6793, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0008614810294698302, | |
| "grad_norm": 1.5062958002090454, | |
| "learning_rate": 0.0, | |
| "loss": 1.9452, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.054694248022016e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |