End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -14,7 +16,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE MRPC
       type: glue
       config: mrpc
       split: validation
@@ -22,10 +24,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6740196078431373
+      value: 0.6838235294117647
     - name: F1
       type: f1
-      value: 0.7646017699115043
+      value: 0.8122270742358079
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_mrpc_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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8759
-- Accuracy: 0.6740
-- F1: 0.7646
-- Combined Score: 0.7193
+- Loss: 0.6220
+- Accuracy: 0.6838
+- F1: 0.8122
+- Combined Score: 0.7480
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6220306158065796,
+    "eval_runtime": 0.9446,
+    "eval_samples": 408,
+    "eval_samples_per_second": 431.924,
+    "eval_steps_per_second": 4.235,
+    "train_loss": 0.5728841470700446,
+    "train_runtime": 394.8059,
+    "train_samples": 3668,
+    "train_samples_per_second": 464.532,
+    "train_steps_per_second": 3.673
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6220306158065796,
+    "eval_runtime": 0.9446,
+    "eval_samples": 408,
+    "eval_samples_per_second": 431.924,
+    "eval_steps_per_second": 4.235
+}

logs/events.out.tfevents.1674647431.garda.227848.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5c1218070b5ba9f6db132d044fe666b6aa0eae050a8a7e7a726dd54c352258
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.0,
+    "train_loss": 0.5728841470700446,
+    "train_runtime": 394.8059,
+    "train_samples": 3668,
+    "train_samples_per_second": 464.532,
+    "train_steps_per_second": 3.673
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_metric": 0.6220306158065796,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_mrpc_128/checkpoint-174",
+  "epoch": 11.0,
+  "global_step": 319,
+  "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": 0.6454,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6240925788879395,
+      "eval_runtime": 0.9198,
+      "eval_samples_per_second": 443.56,
+      "eval_steps_per_second": 4.349,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.63,
+      "step": 58
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6239135265350342,
+      "eval_runtime": 0.9227,
+      "eval_samples_per_second": 442.171,
+      "eval_steps_per_second": 4.335,
+      "step": 58
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6312,
+      "step": 87
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.624621570110321,
+      "eval_runtime": 0.9248,
+      "eval_samples_per_second": 441.173,
+      "eval_steps_per_second": 4.325,
+      "step": 87
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6305,
+      "step": 116
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6246717572212219,
+      "eval_runtime": 0.9218,
+      "eval_samples_per_second": 442.621,
+      "eval_steps_per_second": 4.339,
+      "step": 116
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6295,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.622620165348053,
+      "eval_runtime": 0.9166,
+      "eval_samples_per_second": 445.114,
+      "eval_steps_per_second": 4.364,
+      "step": 145
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6276,
+      "step": 174
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6220306158065796,
+      "eval_runtime": 0.9219,
+      "eval_samples_per_second": 442.585,
+      "eval_steps_per_second": 4.339,
+      "step": 174
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6261,
+      "step": 203
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6227583885192871,
+      "eval_runtime": 0.9198,
+      "eval_samples_per_second": 443.567,
+      "eval_steps_per_second": 4.349,
+      "step": 203
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6007,
+      "step": 232
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6372549019607843,
+      "eval_combined_score": 0.6940483264012676,
+      "eval_f1": 0.7508417508417509,
+      "eval_loss": 0.6694559454917908,
+      "eval_runtime": 0.9218,
+      "eval_samples_per_second": 442.629,
+      "eval_steps_per_second": 4.339,
+      "step": 232
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5159,
+      "step": 261
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7407990974167444,
+      "eval_f1": 0.7830687830687831,
+      "eval_loss": 0.6622989773750305,
+      "eval_runtime": 0.9175,
+      "eval_samples_per_second": 444.67,
+      "eval_steps_per_second": 4.36,
+      "step": 261
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.4232,
+      "step": 290
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.678921568627451,
+      "eval_combined_score": 0.7235315807739024,
+      "eval_f1": 0.768141592920354,
+      "eval_loss": 0.6506969332695007,
+      "eval_runtime": 0.9232,
+      "eval_samples_per_second": 441.928,
+      "eval_steps_per_second": 4.333,
+      "step": 290
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.3418,
+      "step": 319
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6740196078431373,
+      "eval_combined_score": 0.7193106888773209,
+      "eval_f1": 0.7646017699115043,
+      "eval_loss": 0.8758987188339233,
+      "eval_runtime": 0.9222,
+      "eval_samples_per_second": 442.439,
+      "eval_steps_per_second": 4.338,
+      "step": 319
+    },
+    {
+      "epoch": 11.0,
+      "step": 319,
+      "total_flos": 961678216790016.0,
+      "train_loss": 0.5728841470700446,
+      "train_runtime": 394.8059,
+      "train_samples_per_second": 464.532,
+      "train_steps_per_second": 3.673
+    }
+  ],
+  "max_steps": 1450,
+  "num_train_epochs": 50,
+  "total_flos": 961678216790016.0,
+  "trial_name": null,
+  "trial_params": null
+}