| { |
| "best_metric": 0.0003124794748146087, |
| "best_model_checkpoint": "autotrain-NarrativesAnalogues-MPNET/checkpoint-60", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15, |
| "grad_norm": 54.21066665649414, |
| "learning_rate": 1.5e-05, |
| "loss": 0.2656, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.020640991628170013, |
| "learning_rate": 3e-05, |
| "loss": 0.0915, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.011682721786201, |
| "learning_rate": 2.8333333333333332e-05, |
| "loss": 0.0079, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.004591422621160746, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 0.0004, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.21765249967575073, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0006, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 2.3890717029571533, |
| "learning_rate": 2.3333333333333336e-05, |
| "loss": 0.0082, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.0018002312863245606, |
| "eval_runtime": 26.9382, |
| "eval_samples_per_second": 1.448, |
| "eval_steps_per_second": 0.111, |
| "eval_validation_pearson_cosine": 0.9153972316303126, |
| "eval_validation_spearman_cosine": 0.6996947820398319, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.05, |
| "grad_norm": 0.04182960465550423, |
| "learning_rate": 2.1666666666666667e-05, |
| "loss": 0.0002, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.04211459681391716, |
| "learning_rate": 1.9999999999999998e-05, |
| "loss": 0.0006, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.35, |
| "grad_norm": 0.041771624237298965, |
| "learning_rate": 1.8333333333333336e-05, |
| "loss": 0.0003, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.017494792118668556, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0022, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.65, |
| "grad_norm": 0.19024378061294556, |
| "learning_rate": 1.5e-05, |
| "loss": 0.0007, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.03826698660850525, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.0002, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.95, |
| "grad_norm": 0.0008889578166417778, |
| "learning_rate": 1.1666666666666668e-05, |
| "loss": 0.0, |
| "step": 39 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.0005154665559530258, |
| "eval_runtime": 21.3339, |
| "eval_samples_per_second": 1.828, |
| "eval_steps_per_second": 0.141, |
| "eval_validation_pearson_cosine": 0.9349506184847284, |
| "eval_validation_spearman_cosine": 0.6996947820398319, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.1, |
| "grad_norm": 0.0013974634930491447, |
| "learning_rate": 9.999999999999999e-06, |
| "loss": 0.0, |
| "step": 42 |
| }, |
| { |
| "epoch": 2.25, |
| "grad_norm": 0.00019241037080064416, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.0006215217872522771, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.0, |
| "step": 48 |
| }, |
| { |
| "epoch": 2.55, |
| "grad_norm": 0.006116971839219332, |
| "learning_rate": 4.9999999999999996e-06, |
| "loss": 0.0002, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.7, |
| "grad_norm": 0.0, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.0, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.85, |
| "grad_norm": 0.004311254248023033, |
| "learning_rate": 1.6666666666666667e-06, |
| "loss": 0.0, |
| "step": 57 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.0, |
| "learning_rate": 0.0, |
| "loss": 0.0001, |
| "step": 60 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.0003124794748146087, |
| "eval_runtime": 21.3489, |
| "eval_samples_per_second": 1.827, |
| "eval_steps_per_second": 0.141, |
| "eval_validation_pearson_cosine": 0.9414523862441698, |
| "eval_validation_spearman_cosine": 0.6996947820398319, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 60, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.01 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 2 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
