| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.12975523444411677, |
| "eval_steps": 500, |
| "global_step": 110, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.011795930404010616, |
| "grad_norm": 1.6082771771683364, |
| "learning_rate": 1.0588235294117648e-06, |
| "loss": 0.7619158267974854, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.023591860808021232, |
| "grad_norm": 0.7435107194033177, |
| "learning_rate": 2.2352941176470592e-06, |
| "loss": 0.6887937545776367, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03538779121203185, |
| "grad_norm": 0.3929338257386395, |
| "learning_rate": 3.4117647058823532e-06, |
| "loss": 0.6154314994812011, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.047183721616042465, |
| "grad_norm": 0.294584784052743, |
| "learning_rate": 4.588235294117647e-06, |
| "loss": 0.570392656326294, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.058979652020053085, |
| "grad_norm": 0.26241333881617407, |
| "learning_rate": 5.764705882352941e-06, |
| "loss": 0.5440690040588378, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0707755824240637, |
| "grad_norm": 0.22176527857340889, |
| "learning_rate": 6.941176470588236e-06, |
| "loss": 0.52490234375, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.08257151282807432, |
| "grad_norm": 0.48251093193969485, |
| "learning_rate": 8.11764705882353e-06, |
| "loss": 0.5174517631530762, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.09436744323208493, |
| "grad_norm": 0.2301578989148145, |
| "learning_rate": 9.294117647058824e-06, |
| "loss": 0.5046623229980469, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.10616337363609554, |
| "grad_norm": 0.24175747960955796, |
| "learning_rate": 9.999321888914837e-06, |
| "loss": 0.4992623805999756, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.11795930404010617, |
| "grad_norm": 0.2661087745214427, |
| "learning_rate": 9.991695251414584e-06, |
| "loss": 0.493220853805542, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.12975523444411677, |
| "grad_norm": 0.2088421316748935, |
| "learning_rate": 9.975607308402101e-06, |
| "loss": 0.488851261138916, |
| "step": 110 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 848, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 5, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5436128954498417e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
