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: 0.06458977172993104
+      value: 0.03419936685461868
 ---
 
 <!-- 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_128
 
-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: 2.7224
-- Pearson: 0.0576
-- Spearmanr: 0.0646
-- Combined Score: 0.0611
+- Loss: 2.2820
+- Pearson: 0.0445
+- Spearmanr: 0.0342
+- Combined Score: 0.0393
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.039335224561396875,
+    "eval_loss": 2.2820277214050293,
+    "eval_pearson": 0.044471082268175074,
+    "eval_runtime": 2.6274,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 570.896,
+    "eval_spearmanr": 0.03419936685461868,
+    "eval_steps_per_second": 4.567,
+    "train_loss": 2.3818013678656684,
+    "train_runtime": 422.3907,
+    "train_samples": 5749,
+    "train_samples_per_second": 680.531,
+    "train_steps_per_second": 5.327
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.039335224561396875,
+    "eval_loss": 2.2820277214050293,
+    "eval_pearson": 0.044471082268175074,
+    "eval_runtime": 2.6274,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 570.896,
+    "eval_spearmanr": 0.03419936685461868,
+    "eval_steps_per_second": 4.567
+}

logs/events.out.tfevents.1674763855.gera.2822633.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf7924638e319f3388493b388f1f98c9baf2a640c6f8b9b99c262c4e99abeeb
+size 473

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 2.3818013678656684,
+    "train_runtime": 422.3907,
+    "train_samples": 5749,
+    "train_samples_per_second": 680.531,
+    "train_steps_per_second": 5.327
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 2.2820277214050293,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_stsb_128/checkpoint-225",
+  "epoch": 10.0,
+  "global_step": 450,
+  "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": 5.0491,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": -0.009661110131200412,
+      "eval_loss": 2.673527956008911,
+      "eval_pearson": -0.009432536095992792,
+      "eval_runtime": 2.6143,
+      "eval_samples_per_second": 573.76,
+      "eval_spearmanr": -0.009889684166408032,
+      "eval_steps_per_second": 4.59,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 2.2021,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.035915815248946034,
+      "eval_loss": 3.1488900184631348,
+      "eval_pearson": 0.0388729868652795,
+      "eval_runtime": 2.6022,
+      "eval_samples_per_second": 576.446,
+      "eval_spearmanr": 0.032958643632612576,
+      "eval_steps_per_second": 4.612,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 2.1522,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.03414201896321308,
+      "eval_loss": 2.294278383255005,
+      "eval_pearson": 0.04126469756043918,
+      "eval_runtime": 2.5955,
+      "eval_samples_per_second": 577.918,
+      "eval_spearmanr": 0.027019340365986983,
+      "eval_steps_per_second": 4.623,
+      "step": 135
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.125,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.03479033491041533,
+      "eval_loss": 2.5078067779541016,
+      "eval_pearson": 0.04213331357681536,
+      "eval_runtime": 2.6144,
+      "eval_samples_per_second": 573.742,
+      "eval_spearmanr": 0.02744735624401531,
+      "eval_steps_per_second": 4.59,
+      "step": 180
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 2.1328,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.039335224561396875,
+      "eval_loss": 2.2820277214050293,
+      "eval_pearson": 0.044471082268175074,
+      "eval_runtime": 2.6013,
+      "eval_samples_per_second": 576.639,
+      "eval_spearmanr": 0.03419936685461868,
+      "eval_steps_per_second": 4.613,
+      "step": 225
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.0676,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.04283970726741554,
+      "eval_loss": 2.3671822547912598,
+      "eval_pearson": 0.04640494844469042,
+      "eval_runtime": 2.5927,
+      "eval_samples_per_second": 578.549,
+      "eval_spearmanr": 0.03927446609014065,
+      "eval_steps_per_second": 4.628,
+      "step": 270
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 2.0545,
+      "step": 315
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.04847201129678821,
+      "eval_loss": 2.638590097427368,
+      "eval_pearson": 0.05061239002541665,
+      "eval_runtime": 2.6077,
+      "eval_samples_per_second": 575.224,
+      "eval_spearmanr": 0.04633163256815977,
+      "eval_steps_per_second": 4.602,
+      "step": 315
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 2.0677,
+      "step": 360
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.056532370731233586,
+      "eval_loss": 2.439668655395508,
+      "eval_pearson": 0.055629829404637586,
+      "eval_runtime": 2.6086,
+      "eval_samples_per_second": 575.032,
+      "eval_spearmanr": 0.05743491205782958,
+      "eval_steps_per_second": 4.6,
+      "step": 360
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 1.9988,
+      "step": 405
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.061504697595369195,
+      "eval_loss": 2.4024319648742676,
+      "eval_pearson": 0.06005072095227411,
+      "eval_runtime": 2.6497,
+      "eval_samples_per_second": 566.092,
+      "eval_spearmanr": 0.06295867423846428,
+      "eval_steps_per_second": 4.529,
+      "step": 405
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 1.9683,
+      "step": 450
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": 0.061095618493805876,
+      "eval_loss": 2.722409963607788,
+      "eval_pearson": 0.05760146525768071,
+      "eval_runtime": 2.6637,
+      "eval_samples_per_second": 563.119,
+      "eval_spearmanr": 0.06458977172993104,
+      "eval_steps_per_second": 4.505,
+      "step": 450
+    },
+    {
+      "epoch": 10.0,
+      "step": 450,
+      "total_flos": 1372426600448000.0,
+      "train_loss": 2.3818013678656684,
+      "train_runtime": 422.3907,
+      "train_samples_per_second": 680.531,
+      "train_steps_per_second": 5.327
+    }
+  ],
+  "max_steps": 2250,
+  "num_train_epochs": 50,
+  "total_flos": 1372426600448000.0,
+  "trial_name": null,
+  "trial_params": null
+}