| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002046978148508265, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020469781485082646, | |
| "grad_norm": 1.2547894716262817, | |
| "learning_rate": 2e-05, | |
| "loss": 6.4072, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020469781485082646, | |
| "eval_loss": 1.2191214561462402, | |
| "eval_runtime": 100.5339, | |
| "eval_samples_per_second": 20.461, | |
| "eval_steps_per_second": 10.235, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004093956297016529, | |
| "grad_norm": 0.8546660542488098, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8069, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006140934445524794, | |
| "grad_norm": 0.619439423084259, | |
| "learning_rate": 6e-05, | |
| "loss": 4.1533, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006140934445524794, | |
| "eval_loss": 1.2186319828033447, | |
| "eval_runtime": 100.4724, | |
| "eval_samples_per_second": 20.473, | |
| "eval_steps_per_second": 10.242, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008187912594033058, | |
| "grad_norm": 0.5808221697807312, | |
| "learning_rate": 8e-05, | |
| "loss": 5.8187, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010234890742541324, | |
| "grad_norm": 0.5882579684257507, | |
| "learning_rate": 0.0001, | |
| "loss": 5.1005, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012281868891049587, | |
| "grad_norm": 0.4735078811645508, | |
| "learning_rate": 0.00012, | |
| "loss": 3.7797, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012281868891049587, | |
| "eval_loss": 1.213784098625183, | |
| "eval_runtime": 100.4977, | |
| "eval_samples_per_second": 20.468, | |
| "eval_steps_per_second": 10.239, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014328847039557853, | |
| "grad_norm": 0.5567461252212524, | |
| "learning_rate": 0.00014, | |
| "loss": 4.0799, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016375825188066117, | |
| "grad_norm": 0.5600012540817261, | |
| "learning_rate": 0.00016, | |
| "loss": 3.1631, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018422803336574382, | |
| "grad_norm": 1.1744024753570557, | |
| "learning_rate": 0.00018, | |
| "loss": 5.6894, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018422803336574382, | |
| "eval_loss": 1.19596266746521, | |
| "eval_runtime": 100.794, | |
| "eval_samples_per_second": 20.408, | |
| "eval_steps_per_second": 10.209, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002046978148508265, | |
| "grad_norm": 0.8542954325675964, | |
| "learning_rate": 0.0002, | |
| "loss": 3.8363, | |
| "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": 2443123863060480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |