| { |
| "best_metric": 0.4907146394252777, |
| "best_model_checkpoint": "./xlam_1epoch_pythonic5e-6/checkpoint-9", |
| "epoch": 0.943952802359882, |
| "eval_steps": 1, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0943952802359882, |
| "eval_loss": 0.4915958344936371, |
| "eval_runtime": 39.9035, |
| "eval_samples_per_second": 1.905, |
| "eval_steps_per_second": 1.905, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.1887905604719764, |
| "eval_loss": 0.49122685194015503, |
| "eval_runtime": 40.0588, |
| "eval_samples_per_second": 1.897, |
| "eval_steps_per_second": 1.897, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.2831858407079646, |
| "eval_loss": 0.49121004343032837, |
| "eval_runtime": 39.8314, |
| "eval_samples_per_second": 1.908, |
| "eval_steps_per_second": 1.908, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.3775811209439528, |
| "eval_loss": 0.491177499294281, |
| "eval_runtime": 39.8017, |
| "eval_samples_per_second": 1.909, |
| "eval_steps_per_second": 1.909, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.471976401179941, |
| "eval_loss": 0.49093928933143616, |
| "eval_runtime": 39.8849, |
| "eval_samples_per_second": 1.905, |
| "eval_steps_per_second": 1.905, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.5663716814159292, |
| "eval_loss": 0.49092403054237366, |
| "eval_runtime": 39.8709, |
| "eval_samples_per_second": 1.906, |
| "eval_steps_per_second": 1.906, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.6607669616519174, |
| "eval_loss": 0.4911891520023346, |
| "eval_runtime": 39.9964, |
| "eval_samples_per_second": 1.9, |
| "eval_steps_per_second": 1.9, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.7551622418879056, |
| "eval_loss": 0.49123916029930115, |
| "eval_runtime": 39.9339, |
| "eval_samples_per_second": 1.903, |
| "eval_steps_per_second": 1.903, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.8495575221238938, |
| "eval_loss": 0.4907146394252777, |
| "eval_runtime": 40.1182, |
| "eval_samples_per_second": 1.894, |
| "eval_steps_per_second": 1.894, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.943952802359882, |
| "grad_norm": 6.726446151733398, |
| "learning_rate": 0.0, |
| "loss": 8.3789, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.943952802359882, |
| "eval_loss": 0.4910363256931305, |
| "eval_runtime": 40.126, |
| "eval_samples_per_second": 1.894, |
| "eval_steps_per_second": 1.894, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.943952802359882, |
| "step": 10, |
| "total_flos": 1.9157101442039808e+17, |
| "train_loss": 8.378864288330078, |
| "train_runtime": 2046.8795, |
| "train_samples_per_second": 0.166, |
| "train_steps_per_second": 0.005 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.9157101442039808e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
