| { | |
| "best_metric": 0.17114591920857378, | |
| "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-2705", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 5410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9242144177449169, | |
| "grad_norm": 1.4528056383132935, | |
| "learning_rate": 4.537892791127542e-05, | |
| "loss": 0.3191, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7762986255097697, | |
| "eval_f1": 0.15197789412449098, | |
| "eval_loss": 0.815065860748291, | |
| "eval_precision": 0.08251737207833228, | |
| "eval_recall": 0.9604779411764706, | |
| "eval_runtime": 14.2875, | |
| "eval_samples_per_second": 476.64, | |
| "eval_steps_per_second": 59.632, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.8484288354898335, | |
| "grad_norm": 1.5587466955184937, | |
| "learning_rate": 4.075785582255083e-05, | |
| "loss": 0.1619, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7900778557403161, | |
| "eval_f1": 0.168, | |
| "eval_loss": 0.833220362663269, | |
| "eval_precision": 0.09218777996774771, | |
| "eval_recall": 0.9457720588235294, | |
| "eval_runtime": 14.245, | |
| "eval_samples_per_second": 478.064, | |
| "eval_steps_per_second": 59.811, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 2.7726432532347505, | |
| "grad_norm": 0.9616082310676575, | |
| "learning_rate": 3.613678373382625e-05, | |
| "loss": 0.11, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7738201491205184, | |
| "eval_f1": 0.16426810845193607, | |
| "eval_loss": 1.1093989610671997, | |
| "eval_precision": 0.08991208982505004, | |
| "eval_recall": 0.9494485294117647, | |
| "eval_runtime": 14.3321, | |
| "eval_samples_per_second": 475.159, | |
| "eval_steps_per_second": 59.447, | |
| "step": 1623 | |
| }, | |
| { | |
| "epoch": 3.6968576709796674, | |
| "grad_norm": 1.4018645286560059, | |
| "learning_rate": 3.1515711645101665e-05, | |
| "loss": 0.0764, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7740055199307949, | |
| "eval_f1": 0.16182605273514364, | |
| "eval_loss": 1.1206157207489014, | |
| "eval_precision": 0.08849100456227942, | |
| "eval_recall": 0.9448529411764706, | |
| "eval_runtime": 14.4251, | |
| "eval_samples_per_second": 472.092, | |
| "eval_steps_per_second": 59.064, | |
| "step": 2164 | |
| }, | |
| { | |
| "epoch": 4.621072088724584, | |
| "grad_norm": 1.0904265642166138, | |
| "learning_rate": 2.6894639556377083e-05, | |
| "loss": 0.0567, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7890274211487498, | |
| "eval_f1": 0.17114591920857378, | |
| "eval_loss": 1.1805996894836426, | |
| "eval_precision": 0.09400470929179497, | |
| "eval_recall": 0.9540441176470589, | |
| "eval_runtime": 14.1983, | |
| "eval_samples_per_second": 479.634, | |
| "eval_steps_per_second": 60.007, | |
| "step": 2705 | |
| }, | |
| { | |
| "epoch": 5.545286506469501, | |
| "grad_norm": 1.240962028503418, | |
| "learning_rate": 2.2273567467652497e-05, | |
| "loss": 0.0428, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7827454103560493, | |
| "eval_f1": 0.1644558094933674, | |
| "eval_loss": 1.31381094455719, | |
| "eval_precision": 0.09005776299667426, | |
| "eval_recall": 0.9457720588235294, | |
| "eval_runtime": 14.1863, | |
| "eval_samples_per_second": 480.042, | |
| "eval_steps_per_second": 60.058, | |
| "step": 3246 | |
| }, | |
| { | |
| "epoch": 6.469500924214418, | |
| "grad_norm": 0.44737720489501953, | |
| "learning_rate": 1.7652495378927914e-05, | |
| "loss": 0.0332, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7874071429552226, | |
| "eval_f1": 0.16785861076859843, | |
| "eval_loss": 1.4008890390396118, | |
| "eval_precision": 0.09217297102103457, | |
| "eval_recall": 0.9384191176470589, | |
| "eval_runtime": 14.2845, | |
| "eval_samples_per_second": 476.742, | |
| "eval_steps_per_second": 59.645, | |
| "step": 3787 | |
| }, | |
| { | |
| "epoch": 7.393715341959335, | |
| "grad_norm": 0.7116318941116333, | |
| "learning_rate": 1.3031423290203328e-05, | |
| "loss": 0.0257, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7790997844206132, | |
| "eval_f1": 0.16497502819397453, | |
| "eval_loss": 1.5610512495040894, | |
| "eval_precision": 0.0904114426982165, | |
| "eval_recall": 0.9411764705882353, | |
| "eval_runtime": 14.5465, | |
| "eval_samples_per_second": 468.153, | |
| "eval_steps_per_second": 58.571, | |
| "step": 4328 | |
| }, | |
| { | |
| "epoch": 8.317929759704251, | |
| "grad_norm": 0.9520462155342102, | |
| "learning_rate": 8.410351201478742e-06, | |
| "loss": 0.022, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7835212215249838, | |
| "eval_f1": 0.16788916055419725, | |
| "eval_loss": 1.5933887958526611, | |
| "eval_precision": 0.09211232337685567, | |
| "eval_recall": 0.9466911764705882, | |
| "eval_runtime": 14.1983, | |
| "eval_samples_per_second": 479.635, | |
| "eval_steps_per_second": 60.007, | |
| "step": 4869 | |
| }, | |
| { | |
| "epoch": 9.242144177449168, | |
| "grad_norm": 0.6707109212875366, | |
| "learning_rate": 3.789279112754159e-06, | |
| "loss": 0.0181, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7862743213368668, | |
| "eval_f1": 0.16804385175488834, | |
| "eval_loss": 1.6103088855743408, | |
| "eval_precision": 0.09223170184104176, | |
| "eval_recall": 0.9439338235294118, | |
| "eval_runtime": 14.5612, | |
| "eval_samples_per_second": 467.681, | |
| "eval_steps_per_second": 58.512, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 5410, | |
| "total_flos": 1.7176580067661056e+16, | |
| "train_loss": 0.0812657987344287, | |
| "train_runtime": 1542.5562, | |
| "train_samples_per_second": 224.329, | |
| "train_steps_per_second": 3.507 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5410, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 1.7176580067661056e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |