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: 0.060373490039481906
+      value: 0.02173520720193955
 ---
 
 <!-- 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. -->
 
 # mobilebert_add_GLUE_Experiment_stsb_256
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the glue dataset.
+This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4995
-- Pearson: 0.0614
-- Spearmanr: 0.0604
-- Combined Score: 0.0609
+- Loss: 2.2965
+- Pearson: 0.0399
+- Spearmanr: 0.0217
+- Combined Score: 0.0308
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.030822169467473876,
+    "eval_loss": 2.2965381145477295,
+    "eval_pearson": 0.039909131733008196,
+    "eval_runtime": 2.9565,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 507.365,
+    "eval_spearmanr": 0.02173520720193955,
+    "eval_steps_per_second": 4.059,
+    "train_loss": 2.3563860363430447,
+    "train_runtime": 347.9343,
+    "train_samples": 5749,
+    "train_samples_per_second": 826.162,
+    "train_steps_per_second": 6.467
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.030822169467473876,
+    "eval_loss": 2.2965381145477295,
+    "eval_pearson": 0.039909131733008196,
+    "eval_runtime": 2.9565,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 507.365,
+    "eval_spearmanr": 0.02173520720193955,
+    "eval_steps_per_second": 4.059
+}

logs/events.out.tfevents.1674762772.gera.2823283.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e29c07fe9637d5cb4e87e3c90c70e3ba32a82e31ee2198935309e6c026aa9f6
+size 473

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 2.3563860363430447,
+    "train_runtime": 347.9343,
+    "train_samples": 5749,
+    "train_samples_per_second": 826.162,
+    "train_steps_per_second": 6.467
+}

trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": 2.2965381145477295,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_stsb_256/checkpoint-135",
+  "epoch": 8.0,
+  "global_step": 360,
+  "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": 4.3289,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.016869338769549977,
+      "eval_loss": 2.5185155868530273,
+      "eval_pearson": 0.015152034772122189,
+      "eval_runtime": 2.6668,
+      "eval_samples_per_second": 562.482,
+      "eval_spearmanr": 0.018586642766977766,
+      "eval_steps_per_second": 4.5,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 2.1532,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.031155825147051168,
+      "eval_loss": 2.5569276809692383,
+      "eval_pearson": 0.03878201425375371,
+      "eval_runtime": 2.6592,
+      "eval_samples_per_second": 564.09,
+      "eval_spearmanr": 0.023529636040348627,
+      "eval_steps_per_second": 4.513,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 2.1161,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.030822169467473876,
+      "eval_loss": 2.2965381145477295,
+      "eval_pearson": 0.039909131733008196,
+      "eval_runtime": 2.7354,
+      "eval_samples_per_second": 548.375,
+      "eval_spearmanr": 0.02173520720193955,
+      "eval_steps_per_second": 4.387,
+      "step": 135
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.1083,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.034664425266159364,
+      "eval_loss": 2.4191055297851562,
+      "eval_pearson": 0.0409414178434408,
+      "eval_runtime": 2.6813,
+      "eval_samples_per_second": 559.437,
+      "eval_spearmanr": 0.028387432688877935,
+      "eval_steps_per_second": 4.475,
+      "step": 180
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 2.0885,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.04204090753651958,
+      "eval_loss": 2.5610482692718506,
+      "eval_pearson": 0.0458438458890056,
+      "eval_runtime": 2.7067,
+      "eval_samples_per_second": 554.172,
+      "eval_spearmanr": 0.03823796918403356,
+      "eval_steps_per_second": 4.433,
+      "step": 225
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.0602,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.0458476409316318,
+      "eval_loss": 2.378797769546509,
+      "eval_pearson": 0.047272793574367096,
+      "eval_runtime": 2.6789,
+      "eval_samples_per_second": 559.941,
+      "eval_spearmanr": 0.04442248828889651,
+      "eval_steps_per_second": 4.48,
+      "step": 270
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 2.0283,
+      "step": 315
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.05492669237451248,
+      "eval_loss": 2.4458703994750977,
+      "eval_pearson": 0.05710597845528931,
+      "eval_runtime": 2.6878,
+      "eval_samples_per_second": 558.076,
+      "eval_spearmanr": 0.05274740629373566,
+      "eval_steps_per_second": 4.465,
+      "step": 315
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 1.9677,
+      "step": 360
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.06091007949651277,
+      "eval_loss": 2.4995479583740234,
+      "eval_pearson": 0.06144666895354363,
+      "eval_runtime": 2.6805,
+      "eval_samples_per_second": 559.594,
+      "eval_spearmanr": 0.060373490039481906,
+      "eval_steps_per_second": 4.477,
+      "step": 360
+    },
+    {
+      "epoch": 8.0,
+      "step": 360,
+      "total_flos": 1185435401322496.0,
+      "train_loss": 2.3563860363430447,
+      "train_runtime": 347.9343,
+      "train_samples_per_second": 826.162,
+      "train_steps_per_second": 6.467
+    }
+  ],
+  "max_steps": 2250,
+  "num_train_epochs": 50,
+  "total_flos": 1185435401322496.0,
+  "trial_name": null,
+  "trial_params": null
+}