| { |
| "best_metric": 0.6211453744493393, |
| "best_model_checkpoint": "test/checkpoint-1500", |
| "epoch": 171.42857142857142, |
| "eval_steps": 100, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 11.428571428571429, |
| "eval_accuracy": 0.5990491283676703, |
| "eval_f1": 0.0, |
| "eval_loss": 2.474632740020752, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 8.9694, |
| "eval_samples_per_second": 3.902, |
| "eval_steps_per_second": 2.007, |
| "step": 100 |
| }, |
| { |
| "epoch": 22.857142857142858, |
| "eval_accuracy": 0.6788166930797676, |
| "eval_f1": 0.24288425047438328, |
| "eval_loss": 1.4444608688354492, |
| "eval_precision": 0.3404255319148936, |
| "eval_recall": 0.1887905604719764, |
| "eval_runtime": 8.6978, |
| "eval_samples_per_second": 4.024, |
| "eval_steps_per_second": 2.069, |
| "step": 200 |
| }, |
| { |
| "epoch": 34.285714285714285, |
| "eval_accuracy": 0.7279450607501321, |
| "eval_f1": 0.4191343963553531, |
| "eval_loss": 1.1631263494491577, |
| "eval_precision": 0.431924882629108, |
| "eval_recall": 0.40707964601769914, |
| "eval_runtime": 9.0351, |
| "eval_samples_per_second": 3.874, |
| "eval_steps_per_second": 1.992, |
| "step": 300 |
| }, |
| { |
| "epoch": 45.714285714285715, |
| "eval_accuracy": 0.751188589540412, |
| "eval_f1": 0.48367952522255186, |
| "eval_loss": 1.0832462310791016, |
| "eval_precision": 0.48656716417910445, |
| "eval_recall": 0.4808259587020649, |
| "eval_runtime": 8.7144, |
| "eval_samples_per_second": 4.016, |
| "eval_steps_per_second": 2.066, |
| "step": 400 |
| }, |
| { |
| "epoch": 57.142857142857146, |
| "grad_norm": 0.5479933619499207, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 1.6176, |
| "step": 500 |
| }, |
| { |
| "epoch": 57.142857142857146, |
| "eval_accuracy": 0.7606973058637084, |
| "eval_f1": 0.5132743362831859, |
| "eval_loss": 1.0531902313232422, |
| "eval_precision": 0.5132743362831859, |
| "eval_recall": 0.5132743362831859, |
| "eval_runtime": 8.511, |
| "eval_samples_per_second": 4.112, |
| "eval_steps_per_second": 2.115, |
| "step": 500 |
| }, |
| { |
| "epoch": 68.57142857142857, |
| "eval_accuracy": 0.7733755942947702, |
| "eval_f1": 0.5280728376327769, |
| "eval_loss": 1.037137746810913, |
| "eval_precision": 0.54375, |
| "eval_recall": 0.5132743362831859, |
| "eval_runtime": 8.6418, |
| "eval_samples_per_second": 4.05, |
| "eval_steps_per_second": 2.083, |
| "step": 600 |
| }, |
| { |
| "epoch": 80.0, |
| "eval_accuracy": 0.7786582144743793, |
| "eval_f1": 0.5666178623718887, |
| "eval_loss": 1.0758992433547974, |
| "eval_precision": 0.5625, |
| "eval_recall": 0.5707964601769911, |
| "eval_runtime": 8.6983, |
| "eval_samples_per_second": 4.024, |
| "eval_steps_per_second": 2.069, |
| "step": 700 |
| }, |
| { |
| "epoch": 91.42857142857143, |
| "eval_accuracy": 0.7934495509772848, |
| "eval_f1": 0.5766590389016019, |
| "eval_loss": 1.0628628730773926, |
| "eval_precision": 0.5971563981042654, |
| "eval_recall": 0.5575221238938053, |
| "eval_runtime": 8.7485, |
| "eval_samples_per_second": 4.001, |
| "eval_steps_per_second": 2.058, |
| "step": 800 |
| }, |
| { |
| "epoch": 102.85714285714286, |
| "eval_accuracy": 0.7839408346539883, |
| "eval_f1": 0.5863335782512858, |
| "eval_loss": 1.1126993894577026, |
| "eval_precision": 0.5841874084919473, |
| "eval_recall": 0.588495575221239, |
| "eval_runtime": 8.705, |
| "eval_samples_per_second": 4.021, |
| "eval_steps_per_second": 2.068, |
| "step": 900 |
| }, |
| { |
| "epoch": 114.28571428571429, |
| "grad_norm": 0.422118604183197, |
| "learning_rate": 1.8518518518518518e-05, |
| "loss": 0.2316, |
| "step": 1000 |
| }, |
| { |
| "epoch": 114.28571428571429, |
| "eval_accuracy": 0.7929212889593238, |
| "eval_f1": 0.6058823529411765, |
| "eval_loss": 1.095495581626892, |
| "eval_precision": 0.6041055718475073, |
| "eval_recall": 0.6076696165191741, |
| "eval_runtime": 8.7011, |
| "eval_samples_per_second": 4.022, |
| "eval_steps_per_second": 2.069, |
| "step": 1000 |
| }, |
| { |
| "epoch": 125.71428571428571, |
| "eval_accuracy": 0.7939778129952456, |
| "eval_f1": 0.6077428780131483, |
| "eval_loss": 1.1149332523345947, |
| "eval_precision": 0.6020260492040521, |
| "eval_recall": 0.6135693215339233, |
| "eval_runtime": 8.6311, |
| "eval_samples_per_second": 4.055, |
| "eval_steps_per_second": 2.085, |
| "step": 1100 |
| }, |
| { |
| "epoch": 137.14285714285714, |
| "eval_accuracy": 0.8003169572107766, |
| "eval_f1": 0.6152705707931801, |
| "eval_loss": 1.1157317161560059, |
| "eval_precision": 0.6184798807749627, |
| "eval_recall": 0.612094395280236, |
| "eval_runtime": 8.7629, |
| "eval_samples_per_second": 3.994, |
| "eval_steps_per_second": 2.054, |
| "step": 1200 |
| }, |
| { |
| "epoch": 148.57142857142858, |
| "eval_accuracy": 0.8003169572107766, |
| "eval_f1": 0.6178623718887262, |
| "eval_loss": 1.110547423362732, |
| "eval_precision": 0.6133720930232558, |
| "eval_recall": 0.6224188790560472, |
| "eval_runtime": 8.6877, |
| "eval_samples_per_second": 4.029, |
| "eval_steps_per_second": 2.072, |
| "step": 1300 |
| }, |
| { |
| "epoch": 160.0, |
| "eval_accuracy": 0.8003169572107766, |
| "eval_f1": 0.6191176470588234, |
| "eval_loss": 1.1118284463882446, |
| "eval_precision": 0.6173020527859238, |
| "eval_recall": 0.6209439528023599, |
| "eval_runtime": 8.7049, |
| "eval_samples_per_second": 4.021, |
| "eval_steps_per_second": 2.068, |
| "step": 1400 |
| }, |
| { |
| "epoch": 171.42857142857142, |
| "grad_norm": 0.4956161379814148, |
| "learning_rate": 0.0, |
| "loss": 0.1288, |
| "step": 1500 |
| }, |
| { |
| "epoch": 171.42857142857142, |
| "eval_accuracy": 0.8024300052826202, |
| "eval_f1": 0.6211453744493393, |
| "eval_loss": 1.117030143737793, |
| "eval_precision": 0.618421052631579, |
| "eval_recall": 0.6238938053097345, |
| "eval_runtime": 8.6844, |
| "eval_samples_per_second": 4.03, |
| "eval_steps_per_second": 2.073, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 188, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.217791788632576e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
