| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 21096, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.928896473265074e-05, | |
| "loss": 1.6912, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.857792946530148e-05, | |
| "loss": 1.36, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.786689419795222e-05, | |
| "loss": 1.237, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.7155858930602956e-05, | |
| "loss": 1.1394, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.6444823663253697e-05, | |
| "loss": 1.0594, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.5733788395904438e-05, | |
| "loss": 0.8891, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.5022753128555175e-05, | |
| "loss": 0.8156, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4311717861205915e-05, | |
| "loss": 0.8065, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.3600682593856656e-05, | |
| "loss": 0.7831, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.2889647326507393e-05, | |
| "loss": 0.7783, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.2178612059158134e-05, | |
| "loss": 0.6703, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2.1467576791808874e-05, | |
| "loss": 0.5749, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2.0756541524459615e-05, | |
| "loss": 0.5753, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.0045506257110356e-05, | |
| "loss": 0.5737, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.9334470989761093e-05, | |
| "loss": 0.5586, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.8623435722411833e-05, | |
| "loss": 0.5575, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.7912400455062574e-05, | |
| "loss": 0.4159, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.720136518771331e-05, | |
| "loss": 0.4276, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.6490329920364052e-05, | |
| "loss": 0.4327, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.577929465301479e-05, | |
| "loss": 0.4234, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.506825938566553e-05, | |
| "loss": 0.416, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 1.4357224118316269e-05, | |
| "loss": 0.3128, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 1.3646188850967009e-05, | |
| "loss": 0.3144, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 1.2935153583617748e-05, | |
| "loss": 0.3135, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.2224118316268487e-05, | |
| "loss": 0.3115, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 1.1513083048919226e-05, | |
| "loss": 0.3198, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 1.0802047781569966e-05, | |
| "loss": 0.2544, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 1.0091012514220705e-05, | |
| "loss": 0.2404, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 9.379977246871444e-06, | |
| "loss": 0.2351, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 8.668941979522185e-06, | |
| "loss": 0.2271, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 7.957906712172924e-06, | |
| "loss": 0.235, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 7.2468714448236635e-06, | |
| "loss": 0.2172, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 6.535836177474403e-06, | |
| "loss": 0.18, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 5.824800910125142e-06, | |
| "loss": 0.1726, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 5.113765642775882e-06, | |
| "loss": 0.1829, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 4.402730375426621e-06, | |
| "loss": 0.1828, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 3.691695108077361e-06, | |
| "loss": 0.1771, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 2.9806598407281003e-06, | |
| "loss": 0.1421, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 2.2696245733788397e-06, | |
| "loss": 0.1398, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.5585893060295792e-06, | |
| "loss": 0.1439, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 8.475540386803185e-07, | |
| "loss": 0.14, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1.36518771331058e-07, | |
| "loss": 0.1385, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 21096, | |
| "total_flos": 1.7637949154490778e+17, | |
| "train_loss": 0.4928509355450291, | |
| "train_runtime": 318615.5226, | |
| "train_samples_per_second": 2.119, | |
| "train_steps_per_second": 0.066 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 21096, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "total_flos": 1.7637949154490778e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |