| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0011183493164089804, |
| "eval_steps": 8, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.727831054696601e-05, |
| "eval_loss": 9.17426586151123, |
| "eval_runtime": 1670.2712, |
| "eval_samples_per_second": 6.762, |
| "eval_steps_per_second": 3.381, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00011183493164089804, |
| "grad_norm": 8.672355651855469, |
| "learning_rate": 6e-05, |
| "loss": 10.7953, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.00022366986328179608, |
| "grad_norm": 6.415405750274658, |
| "learning_rate": 0.00012, |
| "loss": 5.7534, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.00029822648437572807, |
| "eval_loss": 4.07205057144165, |
| "eval_runtime": 1681.9115, |
| "eval_samples_per_second": 6.716, |
| "eval_steps_per_second": 3.358, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.0003355047949226941, |
| "grad_norm": 14.511173248291016, |
| "learning_rate": 0.00018, |
| "loss": 4.8316, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.00044733972656359216, |
| "grad_norm": 12.734044075012207, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 2.8366, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0005591746582044902, |
| "grad_norm": 8.869030952453613, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 2.2011, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0005964529687514561, |
| "eval_loss": 1.5937066078186035, |
| "eval_runtime": 1682.2165, |
| "eval_samples_per_second": 6.714, |
| "eval_steps_per_second": 3.357, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.0006710095898453882, |
| "grad_norm": 8.932065963745117, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 1.3685, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.0007828445214862862, |
| "grad_norm": 8.256165504455566, |
| "learning_rate": 8.435655349597689e-05, |
| "loss": 1.404, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.0008946794531271843, |
| "grad_norm": 4.563572883605957, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 1.0567, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.0008946794531271843, |
| "eval_loss": 1.3930147886276245, |
| "eval_runtime": 1680.4632, |
| "eval_samples_per_second": 6.721, |
| "eval_steps_per_second": 3.361, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.0010065143847680822, |
| "grad_norm": 8.776552200317383, |
| "learning_rate": 1.0899347581163221e-05, |
| "loss": 1.5312, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.0011183493164089804, |
| "grad_norm": 6.855684757232666, |
| "learning_rate": 0.0, |
| "loss": 1.1873, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 70, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2577036887392256e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
