| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.9087947882736156, | |
| "global_step": 12000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0019185667752442998, | |
| "loss": 2.9941, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0018371335504885993, | |
| "loss": 1.5024, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.001755700325732899, | |
| "loss": 0.0902, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0016742671009771987, | |
| "loss": 0.0504, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0015928338762214984, | |
| "loss": 0.0412, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0015114006514657982, | |
| "loss": 0.0373, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.026404375210404396, | |
| "eval_runtime": 68.798, | |
| "eval_samples_per_second": 178.45, | |
| "eval_steps_per_second": 11.163, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0014299674267100977, | |
| "loss": 0.0346, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0013485342019543974, | |
| "loss": 0.0301, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.001267100977198697, | |
| "loss": 0.0323, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0011856677524429969, | |
| "loss": 0.0305, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0011042345276872966, | |
| "loss": 0.0287, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.001022801302931596, | |
| "loss": 0.0287, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.023602882400155067, | |
| "eval_runtime": 68.7368, | |
| "eval_samples_per_second": 178.609, | |
| "eval_steps_per_second": 11.173, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0009413680781758957, | |
| "loss": 0.0261, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0008599348534201955, | |
| "loss": 0.0255, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0007785016286644952, | |
| "loss": 0.025, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.0006970684039087948, | |
| "loss": 0.0247, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0006156351791530945, | |
| "loss": 0.023, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0005342019543973941, | |
| "loss": 0.0218, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.02037286013364792, | |
| "eval_runtime": 68.7895, | |
| "eval_samples_per_second": 178.472, | |
| "eval_steps_per_second": 11.165, | |
| "step": 9210 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.0004527687296416938, | |
| "loss": 0.0198, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.0003713355048859935, | |
| "loss": 0.0187, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.0002899022801302932, | |
| "loss": 0.0181, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.00020846905537459285, | |
| "loss": 0.0174, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.00012703583061889252, | |
| "loss": 0.0166, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.5602605863192184e-05, | |
| "loss": 0.0167, | |
| "step": 12000 | |
| } | |
| ], | |
| "max_steps": 12280, | |
| "num_train_epochs": 4, | |
| "total_flos": 2.5979941526962176e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |