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 COLA
       type: glue
       config: cola
       split: validation
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.08118499547243287
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6915
-- Matthews Correlation: 0.0812
+- Loss: 0.6153
+- Matthews Correlation: 0.0
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 12.0,
-    "eval_loss": 0.6131083965301514,
+    "epoch": 9.0,
+    "eval_loss": 0.61527419090271,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.1058,
+    "eval_runtime": 1.7447,
     "eval_samples": 1043,
-    "eval_samples_per_second": 943.228,
-    "eval_steps_per_second": 4.522,
-    "train_loss": 0.5614397408915501,
-    "train_runtime": 434.3841,
+    "eval_samples_per_second": 597.816,
+    "eval_steps_per_second": 5.159,
+    "train_loss": 0.543749636876247,
+    "train_runtime": 541.9676,
     "train_samples": 8551,
-    "train_samples_per_second": 984.267,
-    "train_steps_per_second": 3.914
+    "train_samples_per_second": 788.885,
+    "train_steps_per_second": 6.181
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "eval_loss": 0.6131083965301514,
+    "epoch": 9.0,
+    "eval_loss": 0.61527419090271,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.1058,
+    "eval_runtime": 1.7447,
     "eval_samples": 1043,
-    "eval_samples_per_second": 943.228,
-    "eval_steps_per_second": 4.522
+    "eval_samples_per_second": 597.816,
+    "eval_steps_per_second": 5.159
 }

logs/events.out.tfevents.1674619494.garda.1933772.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d64c11e0c13780753cf00e730d891e2abbd3c61c178a0a9caad941b25ab798
+size 375

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 12.0,
-    "train_loss": 0.5614397408915501,
-    "train_runtime": 434.3841,
+    "epoch": 9.0,
+    "train_loss": 0.543749636876247,
+    "train_runtime": 541.9676,
     "train_samples": 8551,
-    "train_samples_per_second": 984.267,
-    "train_steps_per_second": 3.914
+    "train_samples_per_second": 788.885,
+    "train_steps_per_second": 6.181
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.6131083965301514,
-  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_cola/checkpoint-238",
-  "epoch": 12.0,
-  "global_step": 408,
+  "best_metric": 0.61527419090271,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_cola/checkpoint-268",
+  "epoch": 9.0,
+  "global_step": 603,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10,196 +10,151 @@
     {
       "epoch": 1.0,
       "learning_rate": 4.9e-05,
-      "loss": 0.6197,
-      "step": 34
+      "loss": 0.6122,
+      "step": 67
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.6238651871681213,
+      "eval_loss": 0.6183971762657166,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.0726,
-      "eval_samples_per_second": 972.413,
-      "eval_steps_per_second": 4.662,
-      "step": 34
+      "eval_runtime": 1.7411,
+      "eval_samples_per_second": 599.045,
+      "eval_steps_per_second": 5.169,
+      "step": 67
     },
     {
       "epoch": 2.0,
       "learning_rate": 4.8e-05,
       "loss": 0.6078,
-      "step": 68
+      "step": 134
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.6178815364837646,
+      "eval_loss": 0.6179646253585815,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.0582,
-      "eval_samples_per_second": 985.593,
-      "eval_steps_per_second": 4.725,
-      "step": 68
+      "eval_runtime": 1.7343,
+      "eval_samples_per_second": 601.399,
+      "eval_steps_per_second": 5.189,
+      "step": 134
     },
     {
       "epoch": 3.0,
       "learning_rate": 4.7e-05,
-      "loss": 0.6064,
-      "step": 102
+      "loss": 0.607,
+      "step": 201
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.6179934144020081,
+      "eval_loss": 0.6185427904129028,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.3387,
-      "eval_samples_per_second": 779.113,
-      "eval_steps_per_second": 3.735,
-      "step": 102
+      "eval_runtime": 1.7316,
+      "eval_samples_per_second": 602.316,
+      "eval_steps_per_second": 5.197,
+      "step": 201
     },
     {
       "epoch": 4.0,
       "learning_rate": 4.600000000000001e-05,
-      "loss": 0.6073,
-      "step": 136
+      "loss": 0.6052,
+      "step": 268
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.6175711750984192,
+      "eval_loss": 0.61527419090271,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.1189,
-      "eval_samples_per_second": 932.188,
-      "eval_steps_per_second": 4.469,
-      "step": 136
+      "eval_runtime": 1.7366,
+      "eval_samples_per_second": 600.599,
+      "eval_steps_per_second": 5.183,
+      "step": 268
     },
     {
       "epoch": 5.0,
       "learning_rate": 4.5e-05,
-      "loss": 0.6069,
-      "step": 170
+      "loss": 0.5822,
+      "step": 335
     },
     {
       "epoch": 5.0,
-      "eval_loss": 0.6172661781311035,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.1205,
-      "eval_samples_per_second": 930.859,
-      "eval_steps_per_second": 4.462,
-      "step": 170
+      "eval_loss": 0.6292034983634949,
+      "eval_matthews_correlation": 0.05057353484097579,
+      "eval_runtime": 1.7382,
+      "eval_samples_per_second": 600.051,
+      "eval_steps_per_second": 5.178,
+      "step": 335
     },
     {
       "epoch": 6.0,
       "learning_rate": 4.4000000000000006e-05,
-      "loss": 0.6043,
-      "step": 204
+      "loss": 0.5193,
+      "step": 402
     },
     {
       "epoch": 6.0,
-      "eval_loss": 0.6166184544563293,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2344,
-      "eval_samples_per_second": 844.955,
-      "eval_steps_per_second": 4.051,
-      "step": 204
+      "eval_loss": 0.6421763896942139,
+      "eval_matthews_correlation": 0.074290264269209,
+      "eval_runtime": 1.7355,
+      "eval_samples_per_second": 600.967,
+      "eval_steps_per_second": 5.186,
+      "step": 402
     },
     {
       "epoch": 7.0,
       "learning_rate": 4.3e-05,
-      "loss": 0.6004,
-      "step": 238
+      "loss": 0.4783,
+      "step": 469
     },
     {
       "epoch": 7.0,
-      "eval_loss": 0.6131083965301514,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.1421,
-      "eval_samples_per_second": 913.231,
-      "eval_steps_per_second": 4.378,
-      "step": 238
+      "eval_loss": 0.7020387649536133,
+      "eval_matthews_correlation": 0.06292685160191117,
+      "eval_runtime": 1.7327,
+      "eval_samples_per_second": 601.938,
+      "eval_steps_per_second": 5.194,
+      "step": 469
     },
     {
       "epoch": 8.0,
       "learning_rate": 4.2e-05,
-      "loss": 0.5842,
-      "step": 272
+      "loss": 0.4504,
+      "step": 536
     },
     {
       "epoch": 8.0,
-      "eval_loss": 0.6240708231925964,
-      "eval_matthews_correlation": 0.0951039122870703,
-      "eval_runtime": 1.1486,
-      "eval_samples_per_second": 908.065,
-      "eval_steps_per_second": 4.353,
-      "step": 272
+      "eval_loss": 0.7421594858169556,
+      "eval_matthews_correlation": 0.08342146557730178,
+      "eval_runtime": 1.7355,
+      "eval_samples_per_second": 600.992,
+      "eval_steps_per_second": 5.186,
+      "step": 536
     },
     {
       "epoch": 9.0,
       "learning_rate": 4.1e-05,
-      "loss": 0.5192,
-      "step": 306
+      "loss": 0.4315,
+      "step": 603
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.6915299296379089,
+      "eval_matthews_correlation": 0.08118499547243287,
+      "eval_runtime": 1.743,
+      "eval_samples_per_second": 598.381,
+      "eval_steps_per_second": 5.163,
+      "step": 603
     },
     {
       "epoch": 9.0,
-      "eval_loss": 0.6361746191978455,
-      "eval_matthews_correlation": 0.059760920069176514,
-      "eval_runtime": 1.2007,
-      "eval_samples_per_second": 868.661,
-      "eval_steps_per_second": 4.164,
-      "step": 306
-    },
-    {
-      "epoch": 10.0,
-      "learning_rate": 4e-05,
-      "loss": 0.4884,
-      "step": 340
-    },
-    {
-      "epoch": 10.0,
-      "eval_loss": 0.7009902596473694,
-      "eval_matthews_correlation": 0.08008155523655092,
-      "eval_runtime": 1.1475,
-      "eval_samples_per_second": 908.97,
-      "eval_steps_per_second": 4.357,
-      "step": 340
-    },
-    {
-      "epoch": 11.0,
-      "learning_rate": 3.9000000000000006e-05,
-      "loss": 0.4559,
-      "step": 374
-    },
-    {
-      "epoch": 11.0,
-      "eval_loss": 0.6731011867523193,
-      "eval_matthews_correlation": 0.09051190856095573,
-      "eval_runtime": 1.1134,
-      "eval_samples_per_second": 936.763,
-      "eval_steps_per_second": 4.491,
-      "step": 374
-    },
-    {
-      "epoch": 12.0,
-      "learning_rate": 3.8e-05,
-      "loss": 0.4367,
-      "step": 408
-    },
-    {
-      "epoch": 12.0,
-      "eval_loss": 0.6893478035926819,
-      "eval_matthews_correlation": 0.09007205990892461,
-      "eval_runtime": 1.2098,
-      "eval_samples_per_second": 862.13,
-      "eval_steps_per_second": 4.133,
-      "step": 408
-    },
-    {
-      "epoch": 12.0,
-      "step": 408,
-      "total_flos": 3258721140473856.0,
-      "train_loss": 0.5614397408915501,
-      "train_runtime": 434.3841,
-      "train_samples_per_second": 984.267,
-      "train_steps_per_second": 3.914
+      "step": 603,
+      "total_flos": 2412992519995392.0,
+      "train_loss": 0.543749636876247,
+      "train_runtime": 541.9676,
+      "train_samples_per_second": 788.885,
+      "train_steps_per_second": 6.181
     }
   ],
-  "max_steps": 1700,
+  "max_steps": 3350,
   "num_train_epochs": 50,
-  "total_flos": 3258721140473856.0,
+  "total_flos": 2412992519995392.0,
   "trial_name": null,
   "trial_params": null
 }