| { |
| "best_metric": 0.48689982295036316, |
| "best_model_checkpoint": "./xlam_1epoch_pythonic5e-6/checkpoint-35", |
| "epoch": 0.5761316872427984, |
| "eval_steps": 7, |
| "global_step": 35, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11522633744855967, |
| "eval_loss": 0.4905904531478882, |
| "eval_runtime": 40.3827, |
| "eval_samples_per_second": 1.882, |
| "eval_steps_per_second": 1.882, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.1646090534979424, |
| "grad_norm": 6.2620391845703125, |
| "learning_rate": 4.7689385491773934e-06, |
| "loss": 8.4783, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.23045267489711935, |
| "eval_loss": 0.4900592863559723, |
| "eval_runtime": 40.7901, |
| "eval_samples_per_second": 1.863, |
| "eval_steps_per_second": 1.863, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.3292181069958848, |
| "grad_norm": 6.400896072387695, |
| "learning_rate": 3.9029676634059565e-06, |
| "loss": 8.8473, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.345679012345679, |
| "eval_loss": 0.4889541566371918, |
| "eval_runtime": 40.6095, |
| "eval_samples_per_second": 1.871, |
| "eval_steps_per_second": 1.871, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.4609053497942387, |
| "eval_loss": 0.4875749349594116, |
| "eval_runtime": 40.776, |
| "eval_samples_per_second": 1.864, |
| "eval_steps_per_second": 1.864, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.49382716049382713, |
| "grad_norm": 7.524162769317627, |
| "learning_rate": 2.6353472714635443e-06, |
| "loss": 8.0414, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5761316872427984, |
| "eval_loss": 0.48689982295036316, |
| "eval_runtime": 40.5867, |
| "eval_samples_per_second": 1.873, |
| "eval_steps_per_second": 1.873, |
| "step": 35 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 60, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 7, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.656352694443049e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
