| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0050729232720355105, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 1.5858615636825562, | |
| "eval_runtime": 170.9718, | |
| "eval_samples_per_second": 14.564, | |
| "eval_steps_per_second": 7.282, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 35.398643493652344, | |
| "learning_rate": 6e-05, | |
| "loss": 6.2493, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 67.38201141357422, | |
| "learning_rate": 0.00012, | |
| "loss": 6.1214, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "eval_loss": 1.5703749656677246, | |
| "eval_runtime": 170.9801, | |
| "eval_samples_per_second": 14.563, | |
| "eval_steps_per_second": 7.282, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 112.6830062866211, | |
| "learning_rate": 0.00018, | |
| "loss": 6.1368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002029169308814204, | |
| "grad_norm": 7.634250164031982, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.3308, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "grad_norm": 3.4595627784729004, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.1192, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002705559078418939, | |
| "eval_loss": 1.3730992078781128, | |
| "eval_runtime": 171.2537, | |
| "eval_samples_per_second": 14.54, | |
| "eval_steps_per_second": 7.27, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0030437539632213063, | |
| "grad_norm": 2.6122586727142334, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.4754, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0035510462904248573, | |
| "grad_norm": 8.004790306091309, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 5.4139, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004058338617628408, | |
| "grad_norm": 1.8566102981567383, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 5.0694, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004058338617628408, | |
| "eval_loss": 1.2690829038619995, | |
| "eval_runtime": 171.0213, | |
| "eval_samples_per_second": 14.56, | |
| "eval_steps_per_second": 7.28, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004565630944831959, | |
| "grad_norm": 1.8657628297805786, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 5.266, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "grad_norm": 1.5890346765518188, | |
| "learning_rate": 0.0, | |
| "loss": 4.968, | |
| "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": 9801969665310720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |