End of training

README.md

@@ -2,11 +2,24 @@
 library_name: transformers
 tags:
 - generated_from_trainer
+datasets:
+- HuggingFaceFW/fineweb
 metrics:
 - accuracy
 model-index:
 - name: T5LA
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: HuggingFaceFW/fineweb sample-10BT
+      type: HuggingFaceFW/fineweb
+      args: sample-10BT
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.032223235792499715
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # T5LA
 
-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 HuggingFaceFW/fineweb sample-10BT dataset.
 It achieves the following results on the evaluation set:
+- Loss: 5.5467
 - Accuracy: 0.0322
-- Loss: 5.5470
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 2.1069,
-    "eval_accuracy": 0.03222160319607959,
+    "eval_accuracy": 0.032223235792499715,
     "eval_loss": 5.5467119216918945,
-    "eval_runtime": 174.2027,
+    "eval_runtime": 132.3636,
     "eval_samples": 10000,
-    "eval_samples_per_second": 20.625,
-    "eval_steps_per_second": 1.292,
+    "eval_samples_per_second": 27.145,
+    "eval_steps_per_second": 1.7,
     "perplexity": 256.3931277119759,
     "total_flos": 9.182034338135409e+17,
     "train_loss": 0.0,
-    "train_runtime": 908.1395,
+    "train_runtime": 1033.1844,
     "train_samples": 1000000,
-    "train_samples_per_second": 3523.688,
-    "train_steps_per_second": 220.23
+    "train_samples_per_second": 3097.221,
+    "train_steps_per_second": 193.576
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 2.1069,
-    "eval_accuracy": 0.03222160319607959,
+    "eval_accuracy": 0.032223235792499715,
     "eval_loss": 5.5467119216918945,
-    "eval_runtime": 174.2027,
+    "eval_runtime": 132.3636,
     "eval_samples": 10000,
-    "eval_samples_per_second": 20.625,
-    "eval_steps_per_second": 1.292,
+    "eval_samples_per_second": 27.145,
+    "eval_steps_per_second": 1.7,
     "perplexity": 256.3931277119759
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 2.1069,
     "total_flos": 9.182034338135409e+17,
     "train_loss": 0.0,
-    "train_runtime": 908.1395,
+    "train_runtime": 1033.1844,
     "train_samples": 1000000,
-    "train_samples_per_second": 3523.688,
-    "train_steps_per_second": 220.23
+    "train_samples_per_second": 3097.221,
+    "train_steps_per_second": 193.576
 }

trainer_state.json

@@ -2313,9 +2313,9 @@
       "step": 100000,
       "total_flos": 9.182034338135409e+17,
       "train_loss": 0.0,
-      "train_runtime": 908.1395,
-      "train_samples_per_second": 3523.688,
-      "train_steps_per_second": 220.23
+      "train_runtime": 1033.1844,
+      "train_samples_per_second": 3097.221,
+      "train_steps_per_second": 193.576
     }
   ],
   "logging_steps": 500,