| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0099676052828308, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00033225350942769335, | |
| "eval_loss": 3.131289005279541, | |
| "eval_runtime": 43.4688, | |
| "eval_samples_per_second": 116.612, | |
| "eval_steps_per_second": 14.585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00099676052828308, | |
| "grad_norm": 32.003501892089844, | |
| "learning_rate": 6e-05, | |
| "loss": 13.1374, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00199352105656616, | |
| "grad_norm": 120.35460662841797, | |
| "learning_rate": 0.00012, | |
| "loss": 12.2546, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002658028075421547, | |
| "eval_loss": 3.0293800830841064, | |
| "eval_runtime": 43.6103, | |
| "eval_samples_per_second": 116.234, | |
| "eval_steps_per_second": 14.538, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00299028158484924, | |
| "grad_norm": 11.761849403381348, | |
| "learning_rate": 0.00018, | |
| "loss": 12.3048, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00398704211313232, | |
| "grad_norm": 6.040047645568848, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.7324, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0049838026414154, | |
| "grad_norm": 108.8177719116211, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 11.8782, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005316056150843094, | |
| "eval_loss": 2.809000253677368, | |
| "eval_runtime": 43.4794, | |
| "eval_samples_per_second": 116.584, | |
| "eval_steps_per_second": 14.582, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00598056316969848, | |
| "grad_norm": 49.74205017089844, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.8755, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00697732369798156, | |
| "grad_norm": 8.39399242401123, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 11.0593, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00797408422626464, | |
| "grad_norm": 79.41291809082031, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.9708, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00797408422626464, | |
| "eval_loss": 2.6815297603607178, | |
| "eval_runtime": 43.7056, | |
| "eval_samples_per_second": 115.981, | |
| "eval_steps_per_second": 14.506, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00897084475454772, | |
| "grad_norm": 2.964184045791626, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.5503, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0099676052828308, | |
| "grad_norm": 4.644049167633057, | |
| "learning_rate": 0.0, | |
| "loss": 10.74, | |
| "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": 2047754171842560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |