| { |
| "best_global_step": 403, |
| "best_metric": 0.2546365261077881, |
| "best_model_checkpoint": "/Users/stephensolka/dev/notes_2_0/Areas/Feed/feed_classifier/checkpoint-403", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 403, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "embedding_loss": 0.4129, |
| "epoch": 0.0024813895781637717, |
| "grad_norm": 2.87410044670105, |
| "learning_rate": 4.878048780487805e-07, |
| "step": 1 |
| }, |
| { |
| "embedding_loss": 0.2716, |
| "epoch": 0.12406947890818859, |
| "grad_norm": 1.5497353076934814, |
| "learning_rate": 1.950276243093923e-05, |
| "step": 50 |
| }, |
| { |
| "embedding_loss": 0.2432, |
| "epoch": 0.24813895781637718, |
| "grad_norm": 1.2756659984588623, |
| "learning_rate": 1.674033149171271e-05, |
| "step": 100 |
| }, |
| { |
| "embedding_loss": 0.2218, |
| "epoch": 0.37220843672456577, |
| "grad_norm": 1.1529814004898071, |
| "learning_rate": 1.397790055248619e-05, |
| "step": 150 |
| }, |
| { |
| "embedding_loss": 0.1869, |
| "epoch": 0.49627791563275436, |
| "grad_norm": 1.6145966053009033, |
| "learning_rate": 1.1215469613259668e-05, |
| "step": 200 |
| }, |
| { |
| "embedding_loss": 0.1302, |
| "epoch": 0.6203473945409429, |
| "grad_norm": 2.138061285018921, |
| "learning_rate": 8.45303867403315e-06, |
| "step": 250 |
| }, |
| { |
| "embedding_loss": 0.0617, |
| "epoch": 0.7444168734491315, |
| "grad_norm": 2.873232841491699, |
| "learning_rate": 5.69060773480663e-06, |
| "step": 300 |
| }, |
| { |
| "embedding_loss": 0.0343, |
| "epoch": 0.8684863523573201, |
| "grad_norm": 0.7998577952384949, |
| "learning_rate": 2.9281767955801104e-06, |
| "step": 350 |
| }, |
| { |
| "embedding_loss": 0.022, |
| "epoch": 0.9925558312655087, |
| "grad_norm": 1.0344833135604858, |
| "learning_rate": 1.6574585635359117e-07, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_embedding_loss": 0.2546365261077881, |
| "eval_embedding_runtime": 2.148, |
| "eval_embedding_samples_per_second": 763.496, |
| "eval_embedding_steps_per_second": 47.951, |
| "step": 403 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 403, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 0.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
