| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.38162544169611307, | |
| "eval_steps": 9, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014134275618374558, | |
| "eval_loss": 2.42022705078125, | |
| "eval_runtime": 3.0081, | |
| "eval_samples_per_second": 39.893, | |
| "eval_steps_per_second": 4.987, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04240282685512368, | |
| "grad_norm": 0.04235639423131943, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.5861, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08480565371024736, | |
| "grad_norm": 0.04095880687236786, | |
| "learning_rate": 3e-05, | |
| "loss": 2.562, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.127208480565371, | |
| "grad_norm": 0.04078473523259163, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.5813, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.127208480565371, | |
| "eval_loss": 2.419612169265747, | |
| "eval_runtime": 2.9968, | |
| "eval_samples_per_second": 40.042, | |
| "eval_steps_per_second": 5.005, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1696113074204947, | |
| "grad_norm": 0.03982920944690704, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 2.5416, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21201413427561838, | |
| "grad_norm": 0.05580739304423332, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 2.6521, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.254416961130742, | |
| "grad_norm": 0.05870726332068443, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 2.7235, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.254416961130742, | |
| "eval_loss": 2.414585828781128, | |
| "eval_runtime": 3.0217, | |
| "eval_samples_per_second": 39.713, | |
| "eval_steps_per_second": 4.964, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2968197879858657, | |
| "grad_norm": 0.05065983161330223, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 2.6602, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3392226148409894, | |
| "grad_norm": 0.046720851212739944, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 2.5159, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.38162544169611307, | |
| "grad_norm": 0.04852389171719551, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 2.4776, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38162544169611307, | |
| "eval_loss": 2.4045073986053467, | |
| "eval_runtime": 3.0023, | |
| "eval_samples_per_second": 39.969, | |
| "eval_steps_per_second": 4.996, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3432620532695040.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |