| { |
| "best_global_step": 5673, |
| "best_metric": 0.9974603174603175, |
| "best_model_checkpoint": "./fire-prediction/checkpoint-5673", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 5673, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.26441036488630354, |
| "grad_norm": 4.18302059173584, |
| "learning_rate": 4.5601974264057816e-05, |
| "loss": 0.1085, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5288207297726071, |
| "grad_norm": 0.285849004983902, |
| "learning_rate": 4.1195134849286097e-05, |
| "loss": 0.0621, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7932310946589106, |
| "grad_norm": 0.06462472677230835, |
| "learning_rate": 3.678829543451437e-05, |
| "loss": 0.05, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.993968253968254, |
| "eval_loss": 0.019186964258551598, |
| "eval_runtime": 75.6792, |
| "eval_samples_per_second": 83.246, |
| "eval_steps_per_second": 5.206, |
| "step": 1891 |
| }, |
| { |
| "epoch": 1.0576414595452142, |
| "grad_norm": 0.003392481477931142, |
| "learning_rate": 3.238145601974264e-05, |
| "loss": 0.0347, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.3220518244315178, |
| "grad_norm": 0.0019484340446069837, |
| "learning_rate": 2.7974616604970916e-05, |
| "loss": 0.0137, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.5864621893178212, |
| "grad_norm": 0.004056943580508232, |
| "learning_rate": 2.356777719019919e-05, |
| "loss": 0.0118, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.8508725542041247, |
| "grad_norm": 0.0003875873808283359, |
| "learning_rate": 1.9160937775427465e-05, |
| "loss": 0.011, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9946031746031746, |
| "eval_loss": 0.022848913446068764, |
| "eval_runtime": 35.8338, |
| "eval_samples_per_second": 175.812, |
| "eval_steps_per_second": 10.995, |
| "step": 3782 |
| }, |
| { |
| "epoch": 2.1152829190904283, |
| "grad_norm": 0.00041776912985369563, |
| "learning_rate": 1.4754098360655739e-05, |
| "loss": 0.0101, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.379693283976732, |
| "grad_norm": 0.003777874866500497, |
| "learning_rate": 1.0347258945884013e-05, |
| "loss": 0.0041, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.6441036488630356, |
| "grad_norm": 0.0005048959283158183, |
| "learning_rate": 5.940419531112287e-06, |
| "loss": 0.0019, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.908514013749339, |
| "grad_norm": 0.00039942501462064683, |
| "learning_rate": 1.5335801163405607e-06, |
| "loss": 0.0012, |
| "step": 5500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9974603174603175, |
| "eval_loss": 0.015095149166882038, |
| "eval_runtime": 37.7021, |
| "eval_samples_per_second": 167.1, |
| "eval_steps_per_second": 10.45, |
| "step": 5673 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5673, |
| "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": 7.032398057524224e+18, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
