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: 0.07003830521003132
+      value: 0.041438738522880283
 ---
 
 <!-- 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_logit_kd_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: 1.2214
-- Pearson: 0.0666
-- Spearmanr: 0.0700
-- Combined Score: 0.0683
+- Loss: 1.1505
+- Pearson: 0.0470
+- Spearmanr: 0.0414
+- Combined Score: 0.0442
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.04421394291851102,
+    "eval_loss": 1.1504948139190674,
+    "eval_pearson": 0.04698914731414176,
+    "eval_runtime": 2.4499,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 612.263,
+    "eval_spearmanr": 0.041438738522880283,
+    "eval_steps_per_second": 4.898,
+    "train_loss": 1.2339968151516385,
+    "train_runtime": 263.7899,
+    "train_samples": 5749,
+    "train_samples_per_second": 1089.693,
+    "train_steps_per_second": 8.53
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.04421394291851102,
+    "eval_loss": 1.1504948139190674,
+    "eval_pearson": 0.04698914731414176,
+    "eval_runtime": 2.4499,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 612.263,
+    "eval_spearmanr": 0.041438738522880283,
+    "eval_steps_per_second": 4.898
+}

logs/events.out.tfevents.1674975735.serv-3334.518319.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b3f433ffd2a688e393c0dace729ef0e54d27ddd95b58220e4af9cffed644bd
+size 473

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 1.2339968151516385,
+    "train_runtime": 263.7899,
+    "train_samples": 5749,
+    "train_samples_per_second": 1089.693,
+    "train_steps_per_second": 8.53
+}

trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": 1.1504948139190674,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_stsb_128/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": 2.524,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": -0.01736734231487362,
+      "eval_loss": 1.360716700553894,
+      "eval_pearson": -0.00663663554659777,
+      "eval_runtime": 2.4294,
+      "eval_samples_per_second": 617.427,
+      "eval_spearmanr": -0.02809804908314947,
+      "eval_steps_per_second": 4.939,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 1.0877,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.04715345879740872,
+      "eval_loss": 1.1729449033737183,
+      "eval_pearson": 0.04463194868937297,
+      "eval_runtime": 2.4375,
+      "eval_samples_per_second": 615.373,
+      "eval_spearmanr": 0.049674968905444455,
+      "eval_steps_per_second": 4.923,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 1.0648,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.04421394291851102,
+      "eval_loss": 1.1504948139190674,
+      "eval_pearson": 0.04698914731414176,
+      "eval_runtime": 2.44,
+      "eval_samples_per_second": 614.756,
+      "eval_spearmanr": 0.041438738522880283,
+      "eval_steps_per_second": 4.918,
+      "step": 135
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.0737,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.046832979635148,
+      "eval_loss": 1.1564427614212036,
+      "eval_pearson": 0.04721941129058438,
+      "eval_runtime": 2.4235,
+      "eval_samples_per_second": 618.935,
+      "eval_spearmanr": 0.04644654797971162,
+      "eval_steps_per_second": 4.951,
+      "step": 180
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 1.0445,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.05520806466844213,
+      "eval_loss": 1.1971248388290405,
+      "eval_pearson": 0.052931152302893685,
+      "eval_runtime": 2.4387,
+      "eval_samples_per_second": 615.085,
+      "eval_spearmanr": 0.057484977033990574,
+      "eval_steps_per_second": 4.921,
+      "step": 225
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.0296,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.06521746724840925,
+      "eval_loss": 1.172328233718872,
+      "eval_pearson": 0.05777555561817145,
+      "eval_runtime": 2.424,
+      "eval_samples_per_second": 618.82,
+      "eval_spearmanr": 0.07265937887864705,
+      "eval_steps_per_second": 4.951,
+      "step": 270
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 1.026,
+      "step": 315
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.06137059081122272,
+      "eval_loss": 1.2734508514404297,
+      "eval_pearson": 0.062103519281422596,
+      "eval_runtime": 2.4342,
+      "eval_samples_per_second": 616.228,
+      "eval_spearmanr": 0.06063766234102283,
+      "eval_steps_per_second": 4.93,
+      "step": 315
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 1.0216,
+      "step": 360
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.06830693724297929,
+      "eval_loss": 1.221414566040039,
+      "eval_pearson": 0.06657556927592724,
+      "eval_runtime": 2.4254,
+      "eval_samples_per_second": 618.464,
+      "eval_spearmanr": 0.07003830521003132,
+      "eval_steps_per_second": 4.948,
+      "step": 360
+    },
+    {
+      "epoch": 8.0,
+      "step": 360,
+      "total_flos": 1097941280358400.0,
+      "train_loss": 1.2339968151516385,
+      "train_runtime": 263.7899,
+      "train_samples_per_second": 1089.693,
+      "train_steps_per_second": 8.53
+    }
+  ],
+  "max_steps": 2250,
+  "num_train_epochs": 50,
+  "total_flos": 1097941280358400.0,
+  "trial_name": null,
+  "trial_params": null
+}