| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1908, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9968553459119497, |
| "grad_norm": 8.177992820739746, |
| "learning_rate": 1.668763102725367e-05, |
| "loss": 3.5708, |
| "step": 317 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8719354838709678, |
| "eval_loss": 1.8859736919403076, |
| "eval_runtime": 13.2913, |
| "eval_samples_per_second": 233.236, |
| "eval_steps_per_second": 4.89, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.9937106918238994, |
| "grad_norm": 4.497678279876709, |
| "learning_rate": 1.3364779874213839e-05, |
| "loss": 1.3483, |
| "step": 634 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.94, |
| "eval_loss": 1.054024577140808, |
| "eval_runtime": 10.6465, |
| "eval_samples_per_second": 291.175, |
| "eval_steps_per_second": 6.105, |
| "step": 636 |
| }, |
| { |
| "epoch": 2.990566037735849, |
| "grad_norm": 4.546568393707275, |
| "learning_rate": 1.0041928721174005e-05, |
| "loss": 0.805, |
| "step": 951 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9451612903225807, |
| "eval_loss": 0.8161270022392273, |
| "eval_runtime": 10.614, |
| "eval_samples_per_second": 292.068, |
| "eval_steps_per_second": 6.124, |
| "step": 954 |
| }, |
| { |
| "epoch": 3.9874213836477987, |
| "grad_norm": 2.7849512100219727, |
| "learning_rate": 6.719077568134172e-06, |
| "loss": 0.6122, |
| "step": 1268 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9496774193548387, |
| "eval_loss": 0.7191575765609741, |
| "eval_runtime": 10.6395, |
| "eval_samples_per_second": 291.367, |
| "eval_steps_per_second": 6.109, |
| "step": 1272 |
| }, |
| { |
| "epoch": 4.984276729559748, |
| "grad_norm": 2.2364442348480225, |
| "learning_rate": 3.3962264150943395e-06, |
| "loss": 0.5246, |
| "step": 1585 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9548387096774194, |
| "eval_loss": 0.6736067533493042, |
| "eval_runtime": 10.5946, |
| "eval_samples_per_second": 292.602, |
| "eval_steps_per_second": 6.135, |
| "step": 1590 |
| }, |
| { |
| "epoch": 5.981132075471698, |
| "grad_norm": 2.975221872329712, |
| "learning_rate": 7.337526205450734e-08, |
| "loss": 0.4833, |
| "step": 1902 |
| } |
| ], |
| "logging_steps": 317, |
| "max_steps": 1908, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 1000000000.0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1345908829888644.0, |
| "train_batch_size": 48, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.30644514172774995, |
| "num_train_epochs": 6, |
| "temperature": 11 |
| } |
| } |
|
|
