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: 0.62190524707081
+      value: 0.6144222945484134
 ---
 
 <!-- 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. -->
 
 # distilbert_sa_GLUE_Experiment_mnli_384
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8953
-- Accuracy: 0.6219
+- Loss: 0.8561
+- Accuracy: 0.6144
 
 ## Model description
 

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6141619969434539,
+    "eval_accuracy_mm": 0.6144222945484134,
+    "eval_loss": 0.848714292049408,
+    "eval_loss_mm": 0.8561075925827026,
+    "eval_runtime": 5.7245,
+    "eval_runtime_mm": 5.5321,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1714.546,
+    "eval_samples_per_second_mm": 1777.257,
+    "eval_steps_per_second": 6.813,
+    "eval_steps_per_second_mm": 7.05,
+    "train_loss": 0.8036706678248757,
+    "train_runtime": 5092.3208,
+    "train_samples": 392702,
+    "train_samples_per_second": 3855.825,
+    "train_steps_per_second": 15.062
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6141619969434539,
+    "eval_accuracy_mm": 0.6144222945484134,
+    "eval_loss": 0.848714292049408,
+    "eval_loss_mm": 0.8561075925827026,
+    "eval_runtime": 5.7245,
+    "eval_runtime_mm": 5.5321,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1714.546,
+    "eval_samples_per_second_mm": 1777.257,
+    "eval_steps_per_second": 6.813,
+    "eval_steps_per_second_mm": 7.05
+}

logs/events.out.tfevents.1674635454.gera.3187217.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51240997092fb87b1a47bf4bce646f3b0e59a26e935ac590a5f2eab0b4dae239
+size 686

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.8036706678248757,
+    "train_runtime": 5092.3208,
+    "train_samples": 392702,
+    "train_samples_per_second": 3855.825,
+    "train_steps_per_second": 15.062
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.848714292049408,
+  "best_model_checkpoint": "distilbert_sa_GLUE_Experiment_mnli_384/checkpoint-7670",
+  "epoch": 10.0,
+  "global_step": 15340,
+  "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": 1.0075,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5303107488537953,
+      "eval_loss": 0.9587203860282898,
+      "eval_runtime": 5.6935,
+      "eval_samples_per_second": 1723.896,
+      "eval_steps_per_second": 6.85,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.9233,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5728986245542537,
+      "eval_loss": 0.9005416631698608,
+      "eval_runtime": 5.5438,
+      "eval_samples_per_second": 1770.436,
+      "eval_steps_per_second": 7.035,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.8749,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5887926642893531,
+      "eval_loss": 0.8833683133125305,
+      "eval_runtime": 5.9778,
+      "eval_samples_per_second": 1641.912,
+      "eval_steps_per_second": 6.524,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.8389,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.610697911360163,
+      "eval_loss": 0.8563822507858276,
+      "eval_runtime": 5.6621,
+      "eval_samples_per_second": 1733.461,
+      "eval_steps_per_second": 6.888,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.50006518904824e-05,
+      "loss": 0.8058,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6141619969434539,
+      "eval_loss": 0.848714292049408,
+      "eval_runtime": 5.565,
+      "eval_samples_per_second": 1763.688,
+      "eval_steps_per_second": 7.008,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.40013037809648e-05,
+      "loss": 0.776,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6220071319409067,
+      "eval_loss": 0.8578256368637085,
+      "eval_runtime": 5.8496,
+      "eval_samples_per_second": 1677.901,
+      "eval_steps_per_second": 6.667,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3001955671447194e-05,
+      "loss": 0.7467,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6187468160978095,
+      "eval_loss": 0.8617885708808899,
+      "eval_runtime": 5.8167,
+      "eval_samples_per_second": 1687.379,
+      "eval_steps_per_second": 6.705,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.20019556714472e-05,
+      "loss": 0.7171,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6206826286296485,
+      "eval_loss": 0.8828079104423523,
+      "eval_runtime": 5.7638,
+      "eval_samples_per_second": 1702.865,
+      "eval_steps_per_second": 6.766,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.10026075619296e-05,
+      "loss": 0.6876,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6292409577177789,
+      "eval_loss": 0.890081524848938,
+      "eval_runtime": 5.7709,
+      "eval_samples_per_second": 1700.785,
+      "eval_steps_per_second": 6.758,
+      "step": 13806
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.00026075619296e-05,
+      "loss": 0.6589,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.62190524707081,
+      "eval_loss": 0.8952736854553223,
+      "eval_runtime": 5.7281,
+      "eval_samples_per_second": 1713.472,
+      "eval_steps_per_second": 6.808,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "step": 15340,
+      "total_flos": 1.0787244155600896e+17,
+      "train_loss": 0.8036706678248757,
+      "train_runtime": 5092.3208,
+      "train_samples_per_second": 3855.825,
+      "train_steps_per_second": 15.062
+    }
+  ],
+  "max_steps": 76700,
+  "num_train_epochs": 50,
+  "total_flos": 1.0787244155600896e+17,
+  "trial_name": null,
+  "trial_params": null
+}