End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE STSB
       type: glue
       config: stsb
       split: validation
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Spearmanr
       type: spearmanr
-      value: 0.888916767465071
+      value: 0.8872483552831365
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,12 +31,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-uncased-stsb
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4680
-- Pearson: 0.8918
-- Spearmanr: 0.8889
-- Combined Score: 0.8904
+- Loss: 0.4676
+- Pearson: 0.8901
+- Spearmanr: 0.8872
+- Combined Score: 0.8887
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 16.0,
+    "eval_combined_score": 0.888660133343212,
+    "eval_loss": 0.467563271522522,
+    "eval_pearson": 0.8900719114032875,
+    "eval_runtime": 1.807,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 830.118,
+    "eval_spearmanr": 0.8872483552831365,
+    "eval_steps_per_second": 6.641,
+    "train_loss": 0.27670554220676424,
+    "train_runtime": 425.0079,
+    "train_samples": 5749,
+    "train_samples_per_second": 676.34,
+    "train_steps_per_second": 5.294
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 16.0,
+    "eval_combined_score": 0.888660133343212,
+    "eval_loss": 0.467563271522522,
+    "eval_pearson": 0.8900719114032875,
+    "eval_runtime": 1.807,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 830.118,
+    "eval_spearmanr": 0.8872483552831365,
+    "eval_steps_per_second": 6.641
+}

logs/events.out.tfevents.1674781721.serv-3331.2425873.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd67f035c8e3ce3c5777f135f019962c341e0d8b3142a4a67bb9f56a618891a
+size 473

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 16.0,
+    "train_loss": 0.27670554220676424,
+    "train_runtime": 425.0079,
+    "train_samples": 5749,
+    "train_samples_per_second": 676.34,
+    "train_steps_per_second": 5.294
+}

trainer_state.json

@@ -0,0 +1,297 @@
+{
+  "best_metric": 0.467563271522522,
+  "best_model_checkpoint": "bert-base-uncased-stsb/checkpoint-405",
+  "epoch": 16.0,
+  "global_step": 720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9e-05,
+      "loss": 2.3939,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.8669424314450545,
+      "eval_loss": 0.7357739210128784,
+      "eval_pearson": 0.8685755423007867,
+      "eval_runtime": 1.7899,
+      "eval_samples_per_second": 838.047,
+      "eval_spearmanr": 0.8653093205893221,
+      "eval_steps_per_second": 6.704,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5084,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.8817024026311009,
+      "eval_loss": 0.4959274232387543,
+      "eval_pearson": 0.8835499319431416,
+      "eval_runtime": 1.8904,
+      "eval_samples_per_second": 793.472,
+      "eval_spearmanr": 0.8798548733190602,
+      "eval_steps_per_second": 6.348,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3332,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.8830424042805828,
+      "eval_loss": 0.5002294778823853,
+      "eval_pearson": 0.8845983194550131,
+      "eval_runtime": 1.7849,
+      "eval_samples_per_second": 840.372,
+      "eval_spearmanr": 0.8814864891061525,
+      "eval_steps_per_second": 6.723,
+      "step": 135
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2202,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.884027594644461,
+      "eval_loss": 0.49616172909736633,
+      "eval_pearson": 0.8853772464084825,
+      "eval_runtime": 1.7819,
+      "eval_samples_per_second": 841.798,
+      "eval_spearmanr": 0.8826779428804395,
+      "eval_steps_per_second": 6.734,
+      "step": 180
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1642,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.8851559075960755,
+      "eval_loss": 0.4848300516605377,
+      "eval_pearson": 0.8863668340718929,
+      "eval_runtime": 1.8823,
+      "eval_samples_per_second": 796.911,
+      "eval_spearmanr": 0.8839449811202581,
+      "eval_steps_per_second": 6.375,
+      "step": 225
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1312,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.8868904906964868,
+      "eval_loss": 0.4987306594848633,
+      "eval_pearson": 0.8871816692617982,
+      "eval_runtime": 1.7899,
+      "eval_samples_per_second": 838.028,
+      "eval_spearmanr": 0.8865993121311755,
+      "eval_steps_per_second": 6.704,
+      "step": 270
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1057,
+      "step": 315
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.8871304533099161,
+      "eval_loss": 0.48401013016700745,
+      "eval_pearson": 0.8895023644406298,
+      "eval_runtime": 1.9098,
+      "eval_samples_per_second": 785.417,
+      "eval_spearmanr": 0.8847585421792025,
+      "eval_steps_per_second": 6.283,
+      "step": 315
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0935,
+      "step": 360
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.886344403337854,
+      "eval_loss": 0.47526636719703674,
+      "eval_pearson": 0.8886827383247353,
+      "eval_runtime": 1.7838,
+      "eval_samples_per_second": 840.882,
+      "eval_spearmanr": 0.8840060683509728,
+      "eval_steps_per_second": 6.727,
+      "step": 360
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.0835,
+      "step": 405
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.888660133343212,
+      "eval_loss": 0.467563271522522,
+      "eval_pearson": 0.8900719114032875,
+      "eval_runtime": 1.7889,
+      "eval_samples_per_second": 838.488,
+      "eval_spearmanr": 0.8872483552831365,
+      "eval_steps_per_second": 6.708,
+      "step": 405
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0749,
+      "step": 450
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": 0.8884183632324383,
+      "eval_loss": 0.4808439016342163,
+      "eval_pearson": 0.890111270118646,
+      "eval_runtime": 1.7905,
+      "eval_samples_per_second": 837.747,
+      "eval_spearmanr": 0.8867254563462307,
+      "eval_steps_per_second": 6.702,
+      "step": 450
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.0625,
+      "step": 495
+    },
+    {
+      "epoch": 11.0,
+      "eval_combined_score": 0.8875345134615957,
+      "eval_loss": 0.4759939908981323,
+      "eval_pearson": 0.889342341727969,
+      "eval_runtime": 1.7877,
+      "eval_samples_per_second": 839.048,
+      "eval_spearmanr": 0.8857266851952224,
+      "eval_steps_per_second": 6.712,
+      "step": 495
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 3.8e-05,
+      "loss": 0.0607,
+      "step": 540
+    },
+    {
+      "epoch": 12.0,
+      "eval_combined_score": 0.887907305549823,
+      "eval_loss": 0.5113100409507751,
+      "eval_pearson": 0.8899088296955776,
+      "eval_runtime": 1.788,
+      "eval_samples_per_second": 838.938,
+      "eval_spearmanr": 0.8859057814040685,
+      "eval_steps_per_second": 6.712,
+      "step": 540
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 3.7e-05,
+      "loss": 0.0564,
+      "step": 585
+    },
+    {
+      "epoch": 13.0,
+      "eval_combined_score": 0.8879569844044926,
+      "eval_loss": 0.49183163046836853,
+      "eval_pearson": 0.8899557069416996,
+      "eval_runtime": 1.7827,
+      "eval_samples_per_second": 841.434,
+      "eval_spearmanr": 0.8859582618672855,
+      "eval_steps_per_second": 6.731,
+      "step": 585
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.0495,
+      "step": 630
+    },
+    {
+      "epoch": 14.0,
+      "eval_combined_score": 0.8886638639375843,
+      "eval_loss": 0.4748876094818115,
+      "eval_pearson": 0.8905056415691001,
+      "eval_runtime": 1.7871,
+      "eval_samples_per_second": 839.331,
+      "eval_spearmanr": 0.8868220863060686,
+      "eval_steps_per_second": 6.715,
+      "step": 630
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 3.5e-05,
+      "loss": 0.0446,
+      "step": 675
+    },
+    {
+      "epoch": 15.0,
+      "eval_combined_score": 0.8871798551227542,
+      "eval_loss": 0.4889337122440338,
+      "eval_pearson": 0.8887869415264754,
+      "eval_runtime": 1.7866,
+      "eval_samples_per_second": 839.579,
+      "eval_spearmanr": 0.885572768719033,
+      "eval_steps_per_second": 6.717,
+      "step": 675
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.045,
+      "step": 720
+    },
+    {
+      "epoch": 16.0,
+      "eval_combined_score": 0.8903753954306897,
+      "eval_loss": 0.4679853618144989,
+      "eval_pearson": 0.8918340233963084,
+      "eval_runtime": 1.7855,
+      "eval_samples_per_second": 840.1,
+      "eval_spearmanr": 0.888916767465071,
+      "eval_steps_per_second": 6.721,
+      "step": 720
+    },
+    {
+      "epoch": 16.0,
+      "step": 720,
+      "total_flos": 1.2100895336562688e+16,
+      "train_loss": 0.27670554220676424,
+      "train_runtime": 425.0079,
+      "train_samples_per_second": 676.34,
+      "train_steps_per_second": 5.294
+    }
+  ],
+  "max_steps": 2250,
+  "num_train_epochs": 50,
+  "total_flos": 1.2100895336562688e+16,
+  "trial_name": null,
+  "trial_params": null
+}