| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00020155702804162154, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.0155702804162153e-05, | |
| "grad_norm": 1.1627131700515747, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8235, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0155702804162153e-05, | |
| "eval_loss": 1.8384151458740234, | |
| "eval_runtime": 858.5305, | |
| "eval_samples_per_second": 24.332, | |
| "eval_steps_per_second": 12.166, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.0311405608324306e-05, | |
| "grad_norm": 2.0875329971313477, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9389, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.0467108412486456e-05, | |
| "grad_norm": 3.7231967449188232, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5567, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.0467108412486456e-05, | |
| "eval_loss": 1.817110300064087, | |
| "eval_runtime": 857.1198, | |
| "eval_samples_per_second": 24.372, | |
| "eval_steps_per_second": 12.186, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.062281121664861e-05, | |
| "grad_norm": 3.0493383407592773, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00010077851402081077, | |
| "grad_norm": 1.6077319383621216, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2053, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00012093421682497291, | |
| "grad_norm": 1.1640726327896118, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1634, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00012093421682497291, | |
| "eval_loss": 1.5944300889968872, | |
| "eval_runtime": 857.3585, | |
| "eval_samples_per_second": 24.366, | |
| "eval_steps_per_second": 12.183, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014108991962913508, | |
| "grad_norm": 2.123807191848755, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7407, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00016124562243329722, | |
| "grad_norm": 1.0386054515838623, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1746, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00018140132523745937, | |
| "grad_norm": 2.409040689468384, | |
| "learning_rate": 0.00018, | |
| "loss": 1.4244, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00018140132523745937, | |
| "eval_loss": 1.3097835779190063, | |
| "eval_runtime": 857.3178, | |
| "eval_samples_per_second": 24.367, | |
| "eval_steps_per_second": 12.183, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00020155702804162154, | |
| "grad_norm": 1.3552900552749634, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1348, | |
| "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": 2728107266015232.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |