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 RTE
       type: glue
       config: rte
       split: validation
@@ -29,9 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_add_GLUE_Experiment_rte_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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6930
+- Loss: 0.6926
 - Accuracy: 0.5271
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6926400661468506,
+    "eval_runtime": 0.5348,
+    "eval_samples": 277,
+    "eval_samples_per_second": 517.971,
+    "eval_steps_per_second": 5.61,
+    "train_loss": 0.6931220054626465,
+    "train_runtime": 130.999,
+    "train_samples": 2490,
+    "train_samples_per_second": 950.389,
+    "train_steps_per_second": 7.634
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6926400661468506,
+    "eval_runtime": 0.5348,
+    "eval_samples": 277,
+    "eval_samples_per_second": 517.971,
+    "eval_steps_per_second": 5.61
+}

logs/events.out.tfevents.1674759071.gera.2822633.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db27b783c44023061f8851f847db7d17d7487a8f16b831dcc972937ba7b865b4
+size 357

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.6931220054626465,
+    "train_runtime": 130.999,
+    "train_samples": 2490,
+    "train_samples_per_second": 950.389,
+    "train_steps_per_second": 7.634
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6926400661468506,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_rte_128/checkpoint-20",
+  "epoch": 6.0,
+  "global_step": 120,
+  "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": 0.6934,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6926400661468506,
+      "eval_runtime": 0.591,
+      "eval_samples_per_second": 468.723,
+      "eval_steps_per_second": 5.076,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6933,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6929883360862732,
+      "eval_runtime": 0.5159,
+      "eval_samples_per_second": 536.905,
+      "eval_steps_per_second": 5.815,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6931,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4657039711191336,
+      "eval_loss": 0.6933187246322632,
+      "eval_runtime": 0.5114,
+      "eval_samples_per_second": 541.605,
+      "eval_steps_per_second": 5.866,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6932,
+      "step": 80
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6928666830062866,
+      "eval_runtime": 0.5061,
+      "eval_samples_per_second": 547.347,
+      "eval_steps_per_second": 5.928,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6931,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6942214965820312,
+      "eval_runtime": 0.4994,
+      "eval_samples_per_second": 554.668,
+      "eval_steps_per_second": 6.007,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6926,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6929604411125183,
+      "eval_runtime": 0.5098,
+      "eval_samples_per_second": 543.359,
+      "eval_steps_per_second": 5.885,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "step": 120,
+      "total_flos": 356657204822016.0,
+      "train_loss": 0.6931220054626465,
+      "train_runtime": 130.999,
+      "train_samples_per_second": 950.389,
+      "train_steps_per_second": 7.634
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 50,
+  "total_flos": 356657204822016.0,
+  "trial_name": null,
+  "trial_params": null
+}