| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08019246190858059, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.99999449047447e-05, | |
| "loss": 2.7413, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9999779619221645e-05, | |
| "loss": 2.6684, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999950414415935e-05, | |
| "loss": 2.6511, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999911848077199e-05, | |
| "loss": 2.72, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999862263075944e-05, | |
| "loss": 2.7222, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999801659630722e-05, | |
| "loss": 2.7479, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999730038008649e-05, | |
| "loss": 2.6063, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9996473985254055e-05, | |
| "loss": 2.576, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.999553741545237e-05, | |
| "loss": 2.579, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.999449067480945e-05, | |
| "loss": 2.5114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9993333767938954e-05, | |
| "loss": 2.6174, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9992066699940085e-05, | |
| "loss": 2.6581, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9990689476397586e-05, | |
| "loss": 2.586, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.998920210338175e-05, | |
| "loss": 2.4642, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9987604587448343e-05, | |
| "loss": 2.6262, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.998589693563861e-05, | |
| "loss": 2.5678, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.998407915547924e-05, | |
| "loss": 2.5597, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9982151254982304e-05, | |
| "loss": 2.6578, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.998011324264527e-05, | |
| "loss": 2.4825, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.997796512745091e-05, | |
| "loss": 2.6197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.997570691886732e-05, | |
| "loss": 2.4921, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.99733386268478e-05, | |
| "loss": 2.5126, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.99708602618309e-05, | |
| "loss": 2.584, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9968271834740305e-05, | |
| "loss": 2.4991, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.996557335698482e-05, | |
| "loss": 2.5242, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.996276484045832e-05, | |
| "loss": 2.4506, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.995984629753967e-05, | |
| "loss": 2.5479, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9956817741092696e-05, | |
| "loss": 2.5316, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.995367918446613e-05, | |
| "loss": 2.6053, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.995043064149354e-05, | |
| "loss": 2.4533, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9947072126493276e-05, | |
| "loss": 2.5279, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.994360365426839e-05, | |
| "loss": 2.4994, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.994002524010659e-05, | |
| "loss": 2.4675, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.9936336899780166e-05, | |
| "loss": 2.5233, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.993253864954592e-05, | |
| "loss": 2.4974, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.992863050614511e-05, | |
| "loss": 2.6295, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.9924612486803346e-05, | |
| "loss": 2.4744, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.992048460923052e-05, | |
| "loss": 2.5248, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.991624689162076e-05, | |
| "loss": 2.5727, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.991189935265231e-05, | |
| "loss": 2.4845, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 7482, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 2528228211425280.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |