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
@@ -29,9 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_add_GLUE_Experiment_logit_kd_cola_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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6842
+- Loss: 0.6833
 - Matthews Correlation: 0.0
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.6832791566848755,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.7478,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 596.745,
+    "eval_steps_per_second": 5.149,
+    "train_loss": 0.7850639172454379,
+    "train_runtime": 427.859,
+    "train_samples": 8551,
+    "train_samples_per_second": 999.278,
+    "train_steps_per_second": 7.83
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.6832791566848755,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.7478,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 596.745,
+    "eval_steps_per_second": 5.149
+}

logs/events.out.tfevents.1674947778.serv-3334.518319.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b35c41e76f28d351ca59002542223e5e45061187fd588ca1dce558e0634877
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.7850639172454379,
+    "train_runtime": 427.859,
+    "train_samples": 8551,
+    "train_samples_per_second": 999.278,
+    "train_steps_per_second": 7.83
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.6832791566848755,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_cola_128/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": 0.827,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6868772506713867,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7541,
+      "eval_samples_per_second": 594.605,
+      "eval_steps_per_second": 5.131,
+      "step": 67
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7971,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6872267723083496,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7228,
+      "eval_samples_per_second": 605.408,
+      "eval_steps_per_second": 5.224,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7968,
+      "step": 201
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6836860179901123,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7255,
+      "eval_samples_per_second": 604.467,
+      "eval_steps_per_second": 5.216,
+      "step": 201
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.7956,
+      "step": 268
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6842570900917053,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7397,
+      "eval_samples_per_second": 599.522,
+      "eval_steps_per_second": 5.173,
+      "step": 268
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7957,
+      "step": 335
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6832791566848755,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7232,
+      "eval_samples_per_second": 605.281,
+      "eval_steps_per_second": 5.223,
+      "step": 335
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.7934,
+      "step": 402
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6834461688995361,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7268,
+      "eval_samples_per_second": 604.008,
+      "eval_steps_per_second": 5.212,
+      "step": 402
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.7822,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.7013595104217529,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7245,
+      "eval_samples_per_second": 604.825,
+      "eval_steps_per_second": 5.219,
+      "step": 469
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.7636,
+      "step": 536
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.6835333704948425,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7322,
+      "eval_samples_per_second": 602.132,
+      "eval_steps_per_second": 5.196,
+      "step": 536
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.7509,
+      "step": 603
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.6878620982170105,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7282,
+      "eval_samples_per_second": 603.508,
+      "eval_steps_per_second": 5.208,
+      "step": 603
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.7482,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.6841844320297241,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.7455,
+      "eval_samples_per_second": 597.547,
+      "eval_steps_per_second": 5.156,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "step": 670,
+      "total_flos": 2041349301862400.0,
+      "train_loss": 0.7850639172454379,
+      "train_runtime": 427.859,
+      "train_samples_per_second": 999.278,
+      "train_steps_per_second": 7.83
+    }
+  ],
+  "max_steps": 3350,
+  "num_train_epochs": 50,
+  "total_flos": 2041349301862400.0,
+  "trial_name": null,
+  "trial_params": null
+}