🍻 cheers

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 license: apache-2.0
 base_model: google-bert/bert-base-cased
 tags:
+- text-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -19,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-cased_yelp_review_fullv3
 
-This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the yelp_review_full dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9685
 - Accuracy: 0.591

all_results.json

@@ -0,0 +1,16 @@
+{
+ "epoch": 3.0,
+ "eval_accuracy": 0.591,
+ "eval_f1": 0.5878857105251075,
+ "eval_loss": 0.9685279726982117,
+ "eval_precision": 0.5895730080885607,
+ "eval_recall": 0.591,
+ "eval_runtime": 31.5826,
+ "eval_samples_per_second": 31.663,
+ "eval_steps_per_second": 0.507,
+ "total_flos": 789354427392000.0,
+ "train_loss": 1.0597923823765345,
+ "train_runtime": 392.6959,
+ "train_samples_per_second": 7.639,
+ "train_steps_per_second": 0.481
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+ "epoch": 3.0,
+ "eval_accuracy": 0.591,
+ "eval_f1": 0.5878857105251075,
+ "eval_loss": 0.9685279726982117,
+ "eval_precision": 0.5895730080885607,
+ "eval_recall": 0.591,
+ "eval_runtime": 31.5826,
+ "eval_samples_per_second": 31.663,
+ "eval_steps_per_second": 0.507
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+ "epoch": 3.0,
+ "total_flos": 789354427392000.0,
+ "train_loss": 1.0597923823765345,
+ "train_runtime": 392.6959,
+ "train_samples_per_second": 7.639,
+ "train_steps_per_second": 0.481
+}

trainer_state.json

@@ -0,0 +1,204 @@
+{
+ "best_metric": 0.591,
+ "best_model_checkpoint": "./bert-base-cased_yelp_review_fullv3/checkpoint-189",
+ "epoch": 3.0,
+ "eval_steps": 500,
+ "global_step": 189,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.15873015873015872,
+ "grad_norm": 8.031379699707031,
+ "learning_rate": 4.7354497354497356e-05,
+ "loss": 1.6438,
+ "step": 10
+ },
+ {
+ "epoch": 0.31746031746031744,
+ "grad_norm": 5.4050750732421875,
+ "learning_rate": 4.470899470899471e-05,
+ "loss": 1.6259,
+ "step": 20
+ },
+ {
+ "epoch": 0.47619047619047616,
+ "grad_norm": 7.3123016357421875,
+ "learning_rate": 4.2063492063492065e-05,
+ "loss": 1.5252,
+ "step": 30
+ },
+ {
+ "epoch": 0.6349206349206349,
+ "grad_norm": 9.38806438446045,
+ "learning_rate": 3.941798941798942e-05,
+ "loss": 1.3744,
+ "step": 40
+ },
+ {
+ "epoch": 0.7936507936507936,
+ "grad_norm": 6.830764293670654,
+ "learning_rate": 3.677248677248677e-05,
+ "loss": 1.2989,
+ "step": 50
+ },
+ {
+ "epoch": 0.9523809523809523,
+ "grad_norm": 6.1702985763549805,
+ "learning_rate": 3.412698412698413e-05,
+ "loss": 1.2576,
+ "step": 60
+ },
+ {
+ "epoch": 1.0,
+ "eval_accuracy": 0.522,
+ "eval_f1": 0.5057942307842115,
+ "eval_loss": 1.121078610420227,
+ "eval_precision": 0.5055368275623285,
+ "eval_recall": 0.522,
+ "eval_runtime": 31.2136,
+ "eval_samples_per_second": 32.037,
+ "eval_steps_per_second": 0.513,
+ "step": 63
+ },
+ {
+ "epoch": 1.1111111111111112,
+ "grad_norm": 8.638846397399902,
+ "learning_rate": 3.148148148148148e-05,
+ "loss": 1.1302,
+ "step": 70
+ },
+ {
+ "epoch": 1.2698412698412698,
+ "grad_norm": 8.810479164123535,
+ "learning_rate": 2.8835978835978838e-05,
+ "loss": 1.0124,
+ "step": 80
+ },
+ {
+ "epoch": 1.4285714285714286,
+ "grad_norm": 8.507294654846191,
+ "learning_rate": 2.6190476190476192e-05,
+ "loss": 1.0946,
+ "step": 90
+ },
+ {
+ "epoch": 1.5873015873015874,
+ "grad_norm": 6.252330303192139,
+ "learning_rate": 2.3544973544973546e-05,
+ "loss": 1.0634,
+ "step": 100
+ },
+ {
+ "epoch": 1.746031746031746,
+ "grad_norm": 8.558077812194824,
+ "learning_rate": 2.08994708994709e-05,
+ "loss": 1.0714,
+ "step": 110
+ },
+ {
+ "epoch": 1.9047619047619047,
+ "grad_norm": 10.300935745239258,
+ "learning_rate": 1.8253968253968254e-05,
+ "loss": 0.9039,
+ "step": 120
+ },
+ {
+ "epoch": 2.0,
+ "eval_accuracy": 0.558,
+ "eval_f1": 0.5467340038122136,
+ "eval_loss": 0.9913303256034851,
+ "eval_precision": 0.5494611412424277,
+ "eval_recall": 0.558,
+ "eval_runtime": 31.0513,
+ "eval_samples_per_second": 32.205,
+ "eval_steps_per_second": 0.515,
+ "step": 126
+ },
+ {
+ "epoch": 2.0634920634920633,
+ "grad_norm": 8.226648330688477,
+ "learning_rate": 1.560846560846561e-05,
+ "loss": 0.8773,
+ "step": 130
+ },
+ {
+ "epoch": 2.2222222222222223,
+ "grad_norm": 7.533337593078613,
+ "learning_rate": 1.2962962962962962e-05,
+ "loss": 0.727,
+ "step": 140
+ },
+ {
+ "epoch": 2.380952380952381,
+ "grad_norm": 13.123467445373535,
+ "learning_rate": 1.0317460317460318e-05,
+ "loss": 0.7423,
+ "step": 150
+ },
+ {
+ "epoch": 2.5396825396825395,
+ "grad_norm": 6.599626541137695,
+ "learning_rate": 7.671957671957672e-06,
+ "loss": 0.6751,
+ "step": 160
+ },
+ {
+ "epoch": 2.6984126984126986,
+ "grad_norm": 7.168008804321289,
+ "learning_rate": 5.026455026455026e-06,
+ "loss": 0.7262,
+ "step": 170
+ },
+ {
+ "epoch": 2.857142857142857,
+ "grad_norm": 11.771849632263184,
+ "learning_rate": 2.3809523809523808e-06,
+ "loss": 0.6361,
+ "step": 180
+ },
+ {
+ "epoch": 3.0,
+ "eval_accuracy": 0.591,
+ "eval_f1": 0.5878857105251075,
+ "eval_loss": 0.9685279726982117,
+ "eval_precision": 0.5895730080885607,
+ "eval_recall": 0.591,
+ "eval_runtime": 31.1599,
+ "eval_samples_per_second": 32.093,
+ "eval_steps_per_second": 0.513,
+ "step": 189
+ },
+ {
+ "epoch": 3.0,
+ "step": 189,
+ "total_flos": 789354427392000.0,
+ "train_loss": 1.0597923823765345,
+ "train_runtime": 392.6959,
+ "train_samples_per_second": 7.639,
+ "train_steps_per_second": 0.481
+ }
+ ],
+ "logging_steps": 10,
+ "max_steps": 189,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "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": 789354427392000.0,
+ "train_batch_size": 16,
+ "trial_name": null,
+ "trial_params": null
+}