| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.039416633819471816, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.999997870262096e-05, | |
| "loss": 2.714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.999991481057455e-05, | |
| "loss": 2.7679, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9999808324132915e-05, | |
| "loss": 2.6887, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.999965924374964e-05, | |
| "loss": 2.6986, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.999946757005972e-05, | |
| "loss": 2.7536, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9999233303879592e-05, | |
| "loss": 2.7516, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.99989564462071e-05, | |
| "loss": 2.6283, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.999863699822152e-05, | |
| "loss": 2.708, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9998274961283523e-05, | |
| "loss": 2.6932, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9997870336935207e-05, | |
| "loss": 2.6321, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9997423126900056e-05, | |
| "loss": 2.7129, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9996933333082945e-05, | |
| "loss": 2.6179, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9996400957570148e-05, | |
| "loss": 2.6052, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.99958260026293e-05, | |
| "loss": 2.7054, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9995208470709405e-05, | |
| "loss": 2.6568, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9994548364440836e-05, | |
| "loss": 2.6436, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.999384568663529e-05, | |
| "loss": 2.7091, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9993100440285805e-05, | |
| "loss": 2.5557, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.999231262856675e-05, | |
| "loss": 2.5945, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.999148225483378e-05, | |
| "loss": 2.4729, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 7611, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1370020913479680.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |