End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.4620938628158845
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_rte
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on an unknown 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: 0.5556
-- Accuracy: 0.4801
+- Loss: 0.5404
+- Accuracy: 0.4621
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.4620938628158845,
+    "eval_loss": 0.5403890609741211,
+    "eval_runtime": 0.737,
+    "eval_samples": 277,
+    "eval_samples_per_second": 375.846,
+    "eval_steps_per_second": 4.071,
+    "train_loss": 0.21857677858840052,
+    "train_runtime": 6161.1259,
+    "train_samples": 145398,
+    "train_samples_per_second": 1179.963,
+    "train_steps_per_second": 9.219
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.4620938628158845,
+    "eval_loss": 0.5403890609741211,
+    "eval_runtime": 0.737,
+    "eval_samples": 277,
+    "eval_samples_per_second": 375.846,
+    "eval_steps_per_second": 4.071
+}

logs/events.out.tfevents.1675401831.serv-3329.2671356.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9724ea587a74bcc0416a99471bf3e96dedbb97dbd1889c4967d3da8e673498bf
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.21857677858840052,
+    "train_runtime": 6161.1259,
+    "train_samples": 145398,
+    "train_samples_per_second": 1179.963,
+    "train_steps_per_second": 9.219
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.5403890609741211,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_rte/checkpoint-2272",
+  "epoch": 7.0,
+  "global_step": 7952,
+  "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": 0.2735,
+      "step": 1136
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4657039711191336,
+      "eval_loss": 0.5752855539321899,
+      "eval_runtime": 0.7236,
+      "eval_samples_per_second": 382.814,
+      "eval_steps_per_second": 4.146,
+      "step": 1136
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2182,
+      "step": 2272
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4620938628158845,
+      "eval_loss": 0.5403890609741211,
+      "eval_runtime": 0.7138,
+      "eval_samples_per_second": 388.063,
+      "eval_steps_per_second": 4.203,
+      "step": 2272
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2119,
+      "step": 3408
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.47653429602888087,
+      "eval_loss": 0.5687434077262878,
+      "eval_runtime": 0.716,
+      "eval_samples_per_second": 386.892,
+      "eval_steps_per_second": 4.19,
+      "step": 3408
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2089,
+      "step": 4544
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.48375451263537905,
+      "eval_loss": 0.5697432160377502,
+      "eval_runtime": 0.7118,
+      "eval_samples_per_second": 389.139,
+      "eval_steps_per_second": 4.214,
+      "step": 4544
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2072,
+      "step": 5680
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.48014440433212996,
+      "eval_loss": 0.5590192079544067,
+      "eval_runtime": 0.7136,
+      "eval_samples_per_second": 388.179,
+      "eval_steps_per_second": 4.204,
+      "step": 5680
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2057,
+      "step": 6816
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.48375451263537905,
+      "eval_loss": 0.5585924983024597,
+      "eval_runtime": 0.7129,
+      "eval_samples_per_second": 388.565,
+      "eval_steps_per_second": 4.208,
+      "step": 6816
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2047,
+      "step": 7952
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.48014440433212996,
+      "eval_loss": 0.5555509924888611,
+      "eval_runtime": 0.7091,
+      "eval_samples_per_second": 390.621,
+      "eval_steps_per_second": 4.231,
+      "step": 7952
+    },
+    {
+      "epoch": 7.0,
+      "step": 7952,
+      "total_flos": 3.1911928058085376e+16,
+      "train_loss": 0.21857677858840052,
+      "train_runtime": 6161.1259,
+      "train_samples_per_second": 1179.963,
+      "train_steps_per_second": 9.219
+    }
+  ],
+  "max_steps": 56800,
+  "num_train_epochs": 50,
+  "total_flos": 3.1911928058085376e+16,
+  "trial_name": null,
+  "trial_params": null
+}