| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011473152822395595, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011473152822395595, | |
| "grad_norm": 0.11972332745790482, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8259, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011473152822395595, | |
| "eval_loss": 10.830893516540527, | |
| "eval_runtime": 12.0707, | |
| "eval_samples_per_second": 304.042, | |
| "eval_steps_per_second": 152.021, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002294630564479119, | |
| "grad_norm": 0.10545982420444489, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8448, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003441945846718678, | |
| "grad_norm": 0.1160721629858017, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8331, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003441945846718678, | |
| "eval_loss": 10.83078384399414, | |
| "eval_runtime": 11.1143, | |
| "eval_samples_per_second": 330.206, | |
| "eval_steps_per_second": 165.103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004589261128958238, | |
| "grad_norm": 0.11106434464454651, | |
| "learning_rate": 8e-05, | |
| "loss": 10.83, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005736576411197798, | |
| "grad_norm": 0.08514314144849777, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8347, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006883891693437356, | |
| "grad_norm": 0.12030701339244843, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8354, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006883891693437356, | |
| "eval_loss": 10.829866409301758, | |
| "eval_runtime": 11.259, | |
| "eval_samples_per_second": 325.962, | |
| "eval_steps_per_second": 162.981, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008031206975676916, | |
| "grad_norm": 0.11245135217905045, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8283, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009178522257916476, | |
| "grad_norm": 0.11634627729654312, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8305, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010325837540156035, | |
| "grad_norm": 0.12073604017496109, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8336, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010325837540156035, | |
| "eval_loss": 10.8283052444458, | |
| "eval_runtime": 11.2767, | |
| "eval_samples_per_second": 325.449, | |
| "eval_steps_per_second": 162.725, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011473152822395595, | |
| "grad_norm": 0.1371632069349289, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8294, | |
| "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": 1004862308352.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |