| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.996832101372756, | |
| "eval_steps": 500, | |
| "global_step": 236, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00025, | |
| "loss": 3.8893, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00045000000000000004, | |
| "loss": 0.6272, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0004983095894354857, | |
| "loss": 0.5738, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0004914814565722671, | |
| "loss": 0.5952, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0004795540267200685, | |
| "loss": 0.5288, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0004627791681092499, | |
| "loss": 0.5324, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0004415111107797445, | |
| "loss": 0.4889, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0004161989664034844, | |
| "loss": 0.563, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003873772445177015, | |
| "loss": 0.5221, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00035565456543517487, | |
| "loss": 0.5077, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003217008081777726, | |
| "loss": 0.4716, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002862329648268117, | |
| "loss": 0.4604, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00025, | |
| "loss": 0.4369, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00021376703517318835, | |
| "loss": 0.4037, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00017829919182222752, | |
| "loss": 0.4352, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001443454345648252, | |
| "loss": 0.4786, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001126227554822985, | |
| "loss": 0.3898, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.380103359651554e-05, | |
| "loss": 0.4148, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 5.848888922025553e-05, | |
| "loss": 0.4038, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.7220831890750065e-05, | |
| "loss": 0.3832, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.0445973279931528e-05, | |
| "loss": 0.4246, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 8.51854342773295e-06, | |
| "loss": 0.3939, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.6904105645142442e-06, | |
| "loss": 0.4482, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 236, | |
| "total_flos": 2.7203285308932096e+16, | |
| "train_loss": 0.6184843576560586, | |
| "train_runtime": 481.5585, | |
| "train_samples_per_second": 7.864, | |
| "train_steps_per_second": 0.49 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 236, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 2.7203285308932096e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |