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: 0.11818409443621868
+      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_logit_kd_cola_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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7918
-- Matthews Correlation: 0.1182
+- Loss: 0.6753
+- Matthews Correlation: 0.0
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.6752915978431702,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.9493,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 535.058,
+    "eval_steps_per_second": 4.617,
+    "train_loss": 0.6987472420308127,
+    "train_runtime": 459.0273,
+    "train_samples": 8551,
+    "train_samples_per_second": 931.426,
+    "train_steps_per_second": 7.298
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.6752915978431702,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.9493,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 535.058,
+    "eval_steps_per_second": 4.617
+}

logs/events.out.tfevents.1675029964.serv-3334.1016902.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a816d65f9ddd140191b9a00c327eff41b6dce7d0b530eaecb9ec5453c7872517
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.6987472420308127,
+    "train_runtime": 459.0273,
+    "train_samples": 8551,
+    "train_samples_per_second": 931.426,
+    "train_steps_per_second": 7.298
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.6752915978431702,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_cola_256/checkpoint-335",
+  "epoch": 10.0,
+  "global_step": 670,
+  "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": 0.8155,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6866856813430786,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8883,
+      "eval_samples_per_second": 552.344,
+      "eval_steps_per_second": 4.766,
+      "step": 67
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.797,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6862117648124695,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8997,
+      "eval_samples_per_second": 549.042,
+      "eval_steps_per_second": 4.738,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7961,
+      "step": 201
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6835954189300537,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8895,
+      "eval_samples_per_second": 552.012,
+      "eval_steps_per_second": 4.763,
+      "step": 201
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.7944,
+      "step": 268
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6820743083953857,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.89,
+      "eval_samples_per_second": 551.842,
+      "eval_steps_per_second": 4.762,
+      "step": 268
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7863,
+      "step": 335
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6752915978431702,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8919,
+      "eval_samples_per_second": 551.283,
+      "eval_steps_per_second": 4.757,
+      "step": 335
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.7138,
+      "step": 402
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6790478229522705,
+      "eval_matthews_correlation": 0.10850458893694606,
+      "eval_runtime": 1.8885,
+      "eval_samples_per_second": 552.291,
+      "eval_steps_per_second": 4.766,
+      "step": 402
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6262,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.7237713932991028,
+      "eval_matthews_correlation": 0.12306256417772918,
+      "eval_runtime": 1.8926,
+      "eval_samples_per_second": 551.092,
+      "eval_steps_per_second": 4.755,
+      "step": 469
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5782,
+      "step": 536
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.728486180305481,
+      "eval_matthews_correlation": 0.1280618805073397,
+      "eval_runtime": 1.8913,
+      "eval_samples_per_second": 551.473,
+      "eval_steps_per_second": 4.759,
+      "step": 536
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5482,
+      "step": 603
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.7484392523765564,
+      "eval_matthews_correlation": 0.1280618805073397,
+      "eval_runtime": 1.8977,
+      "eval_samples_per_second": 549.598,
+      "eval_steps_per_second": 4.742,
+      "step": 603
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.5318,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.7918062210083008,
+      "eval_matthews_correlation": 0.11818409443621868,
+      "eval_runtime": 1.949,
+      "eval_samples_per_second": 535.158,
+      "eval_steps_per_second": 4.618,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "step": 670,
+      "total_flos": 2252431677194240.0,
+      "train_loss": 0.6987472420308127,
+      "train_runtime": 459.0273,
+      "train_samples_per_second": 931.426,
+      "train_steps_per_second": 7.298
+    }
+  ],
+  "max_steps": 3350,
+  "num_train_epochs": 50,
+  "total_flos": 2252431677194240.0,
+  "trial_name": null,
+  "trial_params": null
+}