| { |
| "best_global_step": 800, |
| "best_metric": 1.1868561506271362, |
| "best_model_checkpoint": "gpt2-code-completion/checkpoint-800", |
| "epoch": 3.0, |
| "eval_steps": 100, |
| "global_step": 846, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.7887430787086487, |
| "learning_rate": 0.00017659574468085107, |
| "loss": 1.5612648010253907, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "eval_loss": 1.3591681718826294, |
| "eval_runtime": 50.1494, |
| "eval_samples_per_second": 19.94, |
| "eval_steps_per_second": 9.97, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.5720292925834656, |
| "learning_rate": 0.0001529550827423168, |
| "loss": 1.396163330078125, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "eval_loss": 1.2876965999603271, |
| "eval_runtime": 49.6955, |
| "eval_samples_per_second": 20.123, |
| "eval_steps_per_second": 10.061, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.064, |
| "grad_norm": 0.5929608345031738, |
| "learning_rate": 0.0001293144208037825, |
| "loss": 1.331701202392578, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.064, |
| "eval_loss": 1.25370454788208, |
| "eval_runtime": 49.8889, |
| "eval_samples_per_second": 20.045, |
| "eval_steps_per_second": 10.022, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.4195555555555557, |
| "grad_norm": 0.5653977990150452, |
| "learning_rate": 0.00010567375886524824, |
| "loss": 1.2437220001220703, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.4195555555555557, |
| "eval_loss": 1.2307533025741577, |
| "eval_runtime": 49.6515, |
| "eval_samples_per_second": 20.14, |
| "eval_steps_per_second": 10.07, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.775111111111111, |
| "grad_norm": 0.5379767417907715, |
| "learning_rate": 8.203309692671395e-05, |
| "loss": 1.225320053100586, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.775111111111111, |
| "eval_loss": 1.2142291069030762, |
| "eval_runtime": 49.7334, |
| "eval_samples_per_second": 20.107, |
| "eval_steps_per_second": 10.054, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.128, |
| "grad_norm": 0.5744788646697998, |
| "learning_rate": 5.8392434988179665e-05, |
| "loss": 1.2014379119873047, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.128, |
| "eval_loss": 1.1999704837799072, |
| "eval_runtime": 49.9552, |
| "eval_samples_per_second": 20.018, |
| "eval_steps_per_second": 10.009, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.4835555555555557, |
| "grad_norm": 0.5410752892494202, |
| "learning_rate": 3.4751773049645395e-05, |
| "loss": 1.1546851348876954, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.4835555555555557, |
| "eval_loss": 1.1921426057815552, |
| "eval_runtime": 49.6565, |
| "eval_samples_per_second": 20.138, |
| "eval_steps_per_second": 10.069, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.8391111111111114, |
| "grad_norm": 0.47747260332107544, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 1.1642756652832031, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.8391111111111114, |
| "eval_loss": 1.1868561506271362, |
| "eval_runtime": 49.8613, |
| "eval_samples_per_second": 20.056, |
| "eval_steps_per_second": 10.028, |
| "step": 800 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 846, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7054884864000000.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
