End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- wikitext
+metrics:
+- accuracy
 model-index:
 - name: test_2_pretrain
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: wikitext wikitext-2-v1
+      type: wikitext
+      args: wikitext-2-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.2759307022812658
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,7 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test_2_pretrain
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the wikitext wikitext-2-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.1341
+- Accuracy: 0.2759
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.28011557471332055,
-    "eval_loss": 5.061196804046631,
-    "eval_runtime": 16.9445,
+    "eval_accuracy": 0.2759307022812658,
+    "eval_loss": 5.134091854095459,
+    "eval_runtime": 14.2134,
     "eval_samples": 249,
-    "eval_samples_per_second": 14.695,
-    "eval_steps_per_second": 1.889,
-    "perplexity": 157.77923419764554,
-    "train_loss": 5.833661626916525,
-    "train_runtime": 1259.5482,
+    "eval_samples_per_second": 17.519,
+    "eval_steps_per_second": 2.251,
+    "perplexity": 169.71012831307598,
+    "train_loss": 5.932113517488288,
+    "train_runtime": 1096.0478,
     "train_samples": 2346,
-    "train_samples_per_second": 5.588,
-    "train_steps_per_second": 1.398
+    "train_samples_per_second": 6.421,
+    "train_steps_per_second": 1.607
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.28011557471332055,
-    "eval_loss": 5.061196804046631,
-    "eval_runtime": 16.9445,
+    "eval_accuracy": 0.2759307022812658,
+    "eval_loss": 5.134091854095459,
+    "eval_runtime": 14.2134,
     "eval_samples": 249,
-    "eval_samples_per_second": 14.695,
-    "eval_steps_per_second": 1.889,
-    "perplexity": 157.77923419764554
+    "eval_samples_per_second": 17.519,
+    "eval_steps_per_second": 2.251,
+    "perplexity": 169.71012831307598
 }

runs/Jan16_13-13-03_0048b83c9bcc/events.out.tfevents.1705411947.0048b83c9bcc.21728.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b47b5ab6b07bd15d65933ce37967891ca85f94dc9d5715e585cb1954f0bbea
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 5.833661626916525,
-    "train_runtime": 1259.5482,
+    "train_loss": 5.932113517488288,
+    "train_runtime": 1096.0478,
     "train_samples": 2346,
-    "train_samples_per_second": 5.588,
-    "train_steps_per_second": 1.398
+    "train_samples_per_second": 6.421,
+    "train_steps_per_second": 1.607
 }

trainer_state.json

@@ -11,29 +11,29 @@
     {
       "epoch": 0.85,
       "learning_rate": 3.580352072685974e-05,
-      "loss": 6.4049,
+      "loss": 6.5491,
       "step": 500
     },
     {
       "epoch": 1.7,
       "learning_rate": 2.160704145371948e-05,
-      "loss": 5.7387,
+      "loss": 5.8268,
       "step": 1000
     },
     {
       "epoch": 2.56,
       "learning_rate": 7.410562180579217e-06,
-      "loss": 5.5475,
+      "loss": 5.6176,
       "step": 1500
     },
     {
       "epoch": 3.0,
       "step": 1761,
       "total_flos": 3677946642432000.0,
-      "train_loss": 5.833661626916525,
-      "train_runtime": 1259.5482,
-      "train_samples_per_second": 5.588,
-      "train_steps_per_second": 1.398
+      "train_loss": 5.932113517488288,
+      "train_runtime": 1096.0478,
+      "train_samples_per_second": 6.421,
+      "train_steps_per_second": 1.607
     }
   ],
   "logging_steps": 500,