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 MNLI
       type: glue
       config: mnli
       split: validation_matched
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.31818644931227713
+      value: 0.3522172497965826
 ---
 
 <!-- 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_add_GLUE_Experiment_mnli_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 MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0987
-- Accuracy: 0.3182
+- Loss: 1.0985
+- Accuracy: 0.3522
 
 ## Model description
 

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.3544574630667346,
+    "eval_accuracy_mm": 0.3522172497965826,
+    "eval_loss": 1.0984911918640137,
+    "eval_loss_mm": 1.0985033512115479,
+    "eval_runtime": 17.4594,
+    "eval_runtime_mm": 17.3772,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 562.162,
+    "eval_samples_per_second_mm": 565.798,
+    "eval_steps_per_second": 4.41,
+    "eval_steps_per_second_mm": 4.431,
+    "train_loss": 1.0986432768064496,
+    "train_runtime": 20712.8857,
+    "train_samples": 392702,
+    "train_samples_per_second": 947.965,
+    "train_steps_per_second": 7.406
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.3544574630667346,
+    "eval_accuracy_mm": 0.3522172497965826,
+    "eval_loss": 1.0984911918640137,
+    "eval_loss_mm": 1.0985033512115479,
+    "eval_runtime": 17.4594,
+    "eval_runtime_mm": 17.3772,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 562.162,
+    "eval_samples_per_second_mm": 565.798,
+    "eval_steps_per_second": 4.41,
+    "eval_steps_per_second_mm": 4.431
+}

logs/events.out.tfevents.1674783782.gera.2823283.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99cce7216cf95b1b8cb31e631432c189f37ab446f6bf2e462a513af5f126a3da
+size 698

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 1.0986432768064496,
+    "train_runtime": 20712.8857,
+    "train_samples": 392702,
+    "train_samples_per_second": 947.965,
+    "train_steps_per_second": 7.406
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 1.0984911918640137,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_mnli_256/checkpoint-15340",
+  "epoch": 10.0,
+  "global_step": 30680,
+  "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": 1.0987,
+      "step": 3068
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.098777413368225,
+      "eval_runtime": 17.5509,
+      "eval_samples_per_second": 559.231,
+      "eval_steps_per_second": 4.387,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 1.0987,
+      "step": 6136
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0986140966415405,
+      "eval_runtime": 17.4915,
+      "eval_samples_per_second": 561.131,
+      "eval_steps_per_second": 4.402,
+      "step": 6136
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 1.0986,
+      "step": 9204
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.0988407135009766,
+      "eval_runtime": 17.529,
+      "eval_samples_per_second": 559.93,
+      "eval_steps_per_second": 4.393,
+      "step": 9204
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.0986,
+      "step": 12272
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.098751425743103,
+      "eval_runtime": 17.6284,
+      "eval_samples_per_second": 556.771,
+      "eval_steps_per_second": 4.368,
+      "step": 12272
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 1.0986,
+      "step": 15340
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0984911918640137,
+      "eval_runtime": 17.4397,
+      "eval_samples_per_second": 562.795,
+      "eval_steps_per_second": 4.415,
+      "step": 15340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.0986,
+      "step": 18408
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.0986493825912476,
+      "eval_runtime": 17.4712,
+      "eval_samples_per_second": 561.781,
+      "eval_steps_per_second": 4.407,
+      "step": 18408
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 1.0986,
+      "step": 21476
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.0989376306533813,
+      "eval_runtime": 17.4516,
+      "eval_samples_per_second": 562.412,
+      "eval_steps_per_second": 4.412,
+      "step": 21476
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 1.0986,
+      "step": 24544
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0985747575759888,
+      "eval_runtime": 17.5984,
+      "eval_samples_per_second": 557.721,
+      "eval_steps_per_second": 4.375,
+      "step": 24544
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 1.0986,
+      "step": 27612
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0985636711120605,
+      "eval_runtime": 17.4957,
+      "eval_samples_per_second": 560.994,
+      "eval_steps_per_second": 4.401,
+      "step": 27612
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 1.0986,
+      "step": 30680
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0986591577529907,
+      "eval_runtime": 17.4485,
+      "eval_samples_per_second": 562.514,
+      "eval_steps_per_second": 4.413,
+      "step": 30680
+    },
+    {
+      "epoch": 10.0,
+      "step": 30680,
+      "total_flos": 1.0122133036335104e+17,
+      "train_loss": 1.0986432768064496,
+      "train_runtime": 20712.8857,
+      "train_samples_per_second": 947.965,
+      "train_steps_per_second": 7.406
+    }
+  ],
+  "max_steps": 153400,
+  "num_train_epochs": 50,
+  "total_flos": 1.0122133036335104e+17,
+  "trial_name": null,
+  "trial_params": null
+}