| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.056700482783555585, | |
| "eval_steps": 500, | |
| "global_step": 2666, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.9096835851669312, | |
| "learning_rate": 4.989366000978328e-05, | |
| "loss": 0.5573, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.8342915177345276, | |
| "learning_rate": 4.978732001956656e-05, | |
| "loss": 0.5416, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.401437759399414, | |
| "learning_rate": 4.968098002934984e-05, | |
| "loss": 0.5475, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.7456225156784058, | |
| "learning_rate": 4.957464003913312e-05, | |
| "loss": 0.5302, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.966705858707428, | |
| "learning_rate": 4.94683000489164e-05, | |
| "loss": 0.5257, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.8829948902130127, | |
| "learning_rate": 4.936302345860184e-05, | |
| "loss": 0.5185, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.8967320322990417, | |
| "learning_rate": 4.925668346838512e-05, | |
| "loss": 0.5195, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.8852934241294861, | |
| "learning_rate": 4.9151406878070574e-05, | |
| "loss": 0.5117, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.0393266677856445, | |
| "learning_rate": 4.9045066887853846e-05, | |
| "loss": 0.5027, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.016802191734314, | |
| "learning_rate": 4.8938726897637125e-05, | |
| "loss": 0.5099, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.0666687488555908, | |
| "learning_rate": 4.8832386907420405e-05, | |
| "loss": 0.5129, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.0762836933135986, | |
| "learning_rate": 4.872604691720369e-05, | |
| "loss": 0.5277, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.8559880256652832, | |
| "learning_rate": 4.861970692698696e-05, | |
| "loss": 0.4987, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.0834448337554932, | |
| "learning_rate": 4.851336693677024e-05, | |
| "loss": 0.5171, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.9118117690086365, | |
| "learning_rate": 4.840702694655352e-05, | |
| "loss": 0.5073, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.029111623764038, | |
| "learning_rate": 4.830068695633681e-05, | |
| "loss": 0.5085, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.9440446496009827, | |
| "learning_rate": 4.819434696612008e-05, | |
| "loss": 0.4978, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.8061498403549194, | |
| "learning_rate": 4.808800697590336e-05, | |
| "loss": 0.4859, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.1587491035461426, | |
| "learning_rate": 4.798166698568664e-05, | |
| "loss": 0.5029, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.8422715067863464, | |
| "learning_rate": 4.787532699546992e-05, | |
| "loss": 0.507, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.0634592771530151, | |
| "learning_rate": 4.77689870052532e-05, | |
| "loss": 0.4967, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.1594743728637695, | |
| "learning_rate": 4.7662647015036477e-05, | |
| "loss": 0.4993, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.0729972124099731, | |
| "learning_rate": 4.7556307024819756e-05, | |
| "loss": 0.496, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.0069080591201782, | |
| "learning_rate": 4.7449967034603035e-05, | |
| "loss": 0.5016, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.9722279906272888, | |
| "learning_rate": 4.7343627044386314e-05, | |
| "loss": 0.4883, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.760681688785553, | |
| "learning_rate": 4.7237287054169594e-05, | |
| "loss": 0.4899, | |
| "step": 2600 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 47019, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1333, | |
| "total_flos": 7.500219014216417e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |