| { |
| "best_global_step": 900, |
| "best_metric": 0.9487214425216864, |
| "best_model_checkpoint": "/root/autodl-tmp/Ver_9/checkpoint-900", |
| "epoch": 5.732484076433121, |
| "eval_steps": 100, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006369426751592357, |
| "grad_norm": 71.95646667480469, |
| "learning_rate": 0.0, |
| "loss": 7.3146, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.6369426751592356, |
| "eval_accuracy": 0.7588227278920834, |
| "eval_loss": 0.6773303151130676, |
| "eval_map@3": 0.8602897760821155, |
| "eval_position": 0.43507289821501566, |
| "eval_runtime": 360.5186, |
| "eval_samples_per_second": 20.357, |
| "eval_steps_per_second": 0.319, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.2738853503184713, |
| "grad_norm": 13.05172348022461, |
| "learning_rate": 4.4176334106728535e-05, |
| "loss": 1.3434, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.2738853503184713, |
| "eval_accuracy": 0.8404414770404687, |
| "eval_loss": 0.45157894492149353, |
| "eval_map@3": 0.9120906572194192, |
| "eval_position": 0.23940591361220875, |
| "eval_runtime": 364.4237, |
| "eval_samples_per_second": 20.139, |
| "eval_steps_per_second": 0.316, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.910828025477707, |
| "eval_accuracy": 0.8551573783894264, |
| "eval_loss": 0.39455440640449524, |
| "eval_map@3": 0.9208793205250478, |
| "eval_position": 0.19103420084480174, |
| "eval_runtime": 358.7498, |
| "eval_samples_per_second": 20.457, |
| "eval_steps_per_second": 0.321, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.5477707006369426, |
| "grad_norm": 9.143854141235352, |
| "learning_rate": 1.1693735498839905e-05, |
| "loss": 0.497, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.5477707006369426, |
| "eval_accuracy": 0.8877231230412863, |
| "eval_loss": 0.3184541165828705, |
| "eval_map@3": 0.9404323931507462, |
| "eval_position": 0.13448698732797384, |
| "eval_runtime": 359.3686, |
| "eval_samples_per_second": 20.422, |
| "eval_steps_per_second": 0.32, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.1847133757961785, |
| "eval_accuracy": 0.8705545714675024, |
| "eval_loss": 0.39355021715164185, |
| "eval_map@3": 0.9310532770132157, |
| "eval_position": 0.1586047145387655, |
| "eval_runtime": 358.8599, |
| "eval_samples_per_second": 20.451, |
| "eval_steps_per_second": 0.32, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.821656050955414, |
| "grad_norm": 8.370223999023438, |
| "learning_rate": 1.747651006711409e-05, |
| "loss": 0.2456, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.821656050955414, |
| "eval_accuracy": 0.8893582231911704, |
| "eval_loss": 0.32028064131736755, |
| "eval_map@3": 0.9410909751555602, |
| "eval_position": 0.13298814552391333, |
| "eval_runtime": 362.093, |
| "eval_samples_per_second": 20.268, |
| "eval_steps_per_second": 0.318, |
| "step": 600 |
| }, |
| { |
| "epoch": 4.45859872611465, |
| "eval_accuracy": 0.8980787573238861, |
| "eval_loss": 0.34446874260902405, |
| "eval_map@3": 0.9450878866330554, |
| "eval_position": 0.1303992369532634, |
| "eval_runtime": 368.1423, |
| "eval_samples_per_second": 19.935, |
| "eval_steps_per_second": 0.312, |
| "step": 700 |
| }, |
| { |
| "epoch": 5.095541401273885, |
| "grad_norm": 4.849258899688721, |
| "learning_rate": 1.1097560975609756e-05, |
| "loss": 0.0541, |
| "step": 800 |
| }, |
| { |
| "epoch": 5.095541401273885, |
| "eval_accuracy": 0.9010764409320071, |
| "eval_loss": 0.3284072279930115, |
| "eval_map@3": 0.947336149339146, |
| "eval_position": 0.12031611936231094, |
| "eval_runtime": 366.9598, |
| "eval_samples_per_second": 19.999, |
| "eval_steps_per_second": 0.313, |
| "step": 800 |
| }, |
| { |
| "epoch": 5.732484076433121, |
| "eval_accuracy": 0.9073443248398965, |
| "eval_loss": 0.33810585737228394, |
| "eval_map@3": 0.9487214425216864, |
| "eval_position": 0.12767407003678977, |
| "eval_runtime": 367.4613, |
| "eval_samples_per_second": 19.972, |
| "eval_steps_per_second": 0.313, |
| "step": 900 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 942, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.177056487899136e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
