| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 63, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07936507936507936, | |
| "grad_norm": 7.816065311431885, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 2.1099, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": 3.8316564559936523, | |
| "learning_rate": 1.985871018518236e-05, | |
| "loss": 1.2551, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 2.3298184871673584, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 1.0135, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 2.625717878341675, | |
| "learning_rate": 1.7456421648831658e-05, | |
| "loss": 0.9708, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3968253968253968, | |
| "grad_norm": 2.078977108001709, | |
| "learning_rate": 1.5320320765153367e-05, | |
| "loss": 0.9623, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 2.326897382736206, | |
| "learning_rate": 1.2768355114248493e-05, | |
| "loss": 0.9482, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 2.4574167728424072, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9567, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 1.8684089183807373, | |
| "learning_rate": 7.2316448857515076e-06, | |
| "loss": 0.9282, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 2.163802146911621, | |
| "learning_rate": 4.679679234846636e-06, | |
| "loss": 0.9101, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7936507936507936, | |
| "grad_norm": 2.871716260910034, | |
| "learning_rate": 2.5435783511683444e-06, | |
| "loss": 0.9134, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.873015873015873, | |
| "grad_norm": 2.999484062194824, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.9192, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 3.2795374393463135, | |
| "learning_rate": 1.4128981481764115e-07, | |
| "loss": 0.913, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 63, | |
| "total_flos": 2.0883561485697024e+16, | |
| "train_loss": 1.0576730417826818, | |
| "train_runtime": 852.991, | |
| "train_samples_per_second": 2.358, | |
| "train_steps_per_second": 0.074 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 63, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0883561485697024e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |