| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3838771593090211, |
| "eval_steps": 200, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03198976327575176, |
| "grad_norm": 0.27879878878593445, |
| "learning_rate": 0.0009895500106632544, |
| "loss": 2.0325, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06397952655150352, |
| "grad_norm": 0.30282971262931824, |
| "learning_rate": 0.0009788867562380039, |
| "loss": 1.9529, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09596928982725528, |
| "grad_norm": 0.3248352110385895, |
| "learning_rate": 0.0009682235018127533, |
| "loss": 2.0104, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.12795905310300704, |
| "grad_norm": 0.3304312527179718, |
| "learning_rate": 0.0009575602473875027, |
| "loss": 1.9798, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.12795905310300704, |
| "eval_loss": 1.6201289892196655, |
| "eval_rouge1": 24.9524, |
| "eval_rouge2": 11.8115, |
| "eval_rougeL": 20.4228, |
| "eval_rougeLsum": 23.4167, |
| "eval_runtime": 315.9771, |
| "eval_samples_per_second": 7.912, |
| "eval_steps_per_second": 0.497, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1599488163787588, |
| "grad_norm": 0.35063809156417847, |
| "learning_rate": 0.000946896992962252, |
| "loss": 2.0127, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.19193857965451055, |
| "grad_norm": 0.3319188356399536, |
| "learning_rate": 0.0009362337385370016, |
| "loss": 1.9046, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.22392834293026231, |
| "grad_norm": 0.35874632000923157, |
| "learning_rate": 0.0009255704841117509, |
| "loss": 1.983, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.2559181062060141, |
| "grad_norm": 0.37553051114082336, |
| "learning_rate": 0.0009149072296865004, |
| "loss": 1.9382, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2559181062060141, |
| "eval_loss": 1.6310702562332153, |
| "eval_rouge1": 24.8892, |
| "eval_rouge2": 11.7408, |
| "eval_rougeL": 20.3925, |
| "eval_rougeLsum": 23.3202, |
| "eval_runtime": 315.7526, |
| "eval_samples_per_second": 7.918, |
| "eval_steps_per_second": 0.497, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.28790786948176583, |
| "grad_norm": 0.3704718053340912, |
| "learning_rate": 0.0009042439752612498, |
| "loss": 1.975, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.3198976327575176, |
| "grad_norm": 0.33435943722724915, |
| "learning_rate": 0.0008935807208359991, |
| "loss": 1.9376, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.35188739603326935, |
| "grad_norm": 0.3917178213596344, |
| "learning_rate": 0.0008829174664107486, |
| "loss": 1.9519, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.3838771593090211, |
| "grad_norm": 0.4132656455039978, |
| "learning_rate": 0.000872254211985498, |
| "loss": 1.9487, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3838771593090211, |
| "eval_loss": 1.62241792678833, |
| "eval_rouge1": 24.8193, |
| "eval_rouge2": 11.7477, |
| "eval_rougeL": 20.3401, |
| "eval_rougeLsum": 23.362, |
| "eval_runtime": 315.9731, |
| "eval_samples_per_second": 7.912, |
| "eval_steps_per_second": 0.497, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 4689, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6599762509824000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
