| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 222, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13651877133105803, |
| "grad_norm": 661.1541748046875, |
| "learning_rate": 3.6000000000000003e-06, |
| "loss": 4.1112, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.27303754266211605, |
| "grad_norm": 404.9569091796875, |
| "learning_rate": 7.600000000000001e-06, |
| "loss": 3.4668, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.40955631399317405, |
| "grad_norm": 221.81915283203125, |
| "learning_rate": 1.16e-05, |
| "loss": 3.9445, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5460750853242321, |
| "grad_norm": 624.3930053710938, |
| "learning_rate": 1.5600000000000003e-05, |
| "loss": 4.0167, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6825938566552902, |
| "grad_norm": 144.68826293945312, |
| "learning_rate": 1.9600000000000002e-05, |
| "loss": 4.353, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8191126279863481, |
| "grad_norm": 76.5335922241211, |
| "learning_rate": 1.8953488372093027e-05, |
| "loss": 2.4911, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9556313993174061, |
| "grad_norm": 156.03607177734375, |
| "learning_rate": 1.7790697674418608e-05, |
| "loss": 3.0436, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0819112627986347, |
| "grad_norm": 429.53564453125, |
| "learning_rate": 1.6627906976744188e-05, |
| "loss": 2.6976, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2184300341296928, |
| "grad_norm": 90.31644439697266, |
| "learning_rate": 1.546511627906977e-05, |
| "loss": 2.0883, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3549488054607508, |
| "grad_norm": 189.0266571044922, |
| "learning_rate": 1.4302325581395352e-05, |
| "loss": 3.0638, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4914675767918089, |
| "grad_norm": 80.8642578125, |
| "learning_rate": 1.313953488372093e-05, |
| "loss": 1.7315, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.627986348122867, |
| "grad_norm": 129.05471801757812, |
| "learning_rate": 1.1976744186046511e-05, |
| "loss": 2.8467, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.764505119453925, |
| "grad_norm": 427.9339294433594, |
| "learning_rate": 1.0813953488372094e-05, |
| "loss": 2.511, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.901023890784983, |
| "grad_norm": 157.96697998046875, |
| "learning_rate": 9.651162790697676e-06, |
| "loss": 2.4705, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.0273037542662116, |
| "grad_norm": 76.74122619628906, |
| "learning_rate": 8.488372093023256e-06, |
| "loss": 2.1727, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.1638225255972694, |
| "grad_norm": 8.750153541564941, |
| "learning_rate": 7.325581395348837e-06, |
| "loss": 0.9306, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.3003412969283277, |
| "grad_norm": 130.6959228515625, |
| "learning_rate": 6.162790697674419e-06, |
| "loss": 1.1803, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.4368600682593855, |
| "grad_norm": 4.233165740966797, |
| "learning_rate": 5e-06, |
| "loss": 1.1223, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.573378839590444, |
| "grad_norm": 210.20428466796875, |
| "learning_rate": 3.837209302325582e-06, |
| "loss": 1.5384, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.7098976109215016, |
| "grad_norm": 25.38463592529297, |
| "learning_rate": 2.674418604651163e-06, |
| "loss": 0.6051, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.84641638225256, |
| "grad_norm": 189.81982421875, |
| "learning_rate": 1.5116279069767443e-06, |
| "loss": 0.9252, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.9829351535836177, |
| "grad_norm": 11.452348709106445, |
| "learning_rate": 3.488372093023256e-07, |
| "loss": 1.1221, |
| "step": 220 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 222, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.091492960403456e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
