| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 16, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.125, |
| "grad_norm": 14.48385238647461, |
| "learning_rate": 0.00019914448613738106, |
| "loss": 3.3605, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 6.853867530822754, |
| "learning_rate": 0.00019659258262890683, |
| "loss": 1.993, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.375, |
| "grad_norm": 5.492555141448975, |
| "learning_rate": 0.0001923879532511287, |
| "loss": 2.0817, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 5.457701206207275, |
| "learning_rate": 0.00018660254037844388, |
| "loss": 2.0102, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 5.994251251220703, |
| "learning_rate": 0.00017933533402912354, |
| "loss": 1.9157, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 5.06940221786499, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 1.6613, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.875, |
| "grad_norm": 5.290867805480957, |
| "learning_rate": 0.00016087614290087208, |
| "loss": 1.6786, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.920886993408203, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 1.1838, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.125, |
| "grad_norm": 4.250794410705566, |
| "learning_rate": 0.000138268343236509, |
| "loss": 0.8941, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 3.9683432579040527, |
| "learning_rate": 0.00012588190451025207, |
| "loss": 0.7327, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.375, |
| "grad_norm": 5.4088239669799805, |
| "learning_rate": 0.00011305261922200519, |
| "loss": 0.9204, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 4.606368064880371, |
| "learning_rate": 0.0001, |
| "loss": 0.7796, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.625, |
| "grad_norm": 4.5798797607421875, |
| "learning_rate": 8.694738077799488e-05, |
| "loss": 0.7233, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.75, |
| "grad_norm": 5.217900276184082, |
| "learning_rate": 7.411809548974792e-05, |
| "loss": 0.6521, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 5.4491963386535645, |
| "learning_rate": 6.173165676349103e-05, |
| "loss": 0.64, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 6.39097785949707, |
| "learning_rate": 5.000000000000002e-05, |
| "loss": 0.6054, |
| "step": 16 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 24, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 659184659988480.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
