End of training

README.md

@@ -3,25 +3,25 @@ library_name: transformers
 tags:
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceFW/fineweb
 metrics:
 - accuracy
 model-index:
 - name: T5Laa-Large-WeightedLoss
   results:
   - task:
-      name: Sequence-to-sequence Language Modeling
-      type: text2text-generation
+      name: Causal Language Modeling
+      type: text-generation
     dataset:
-      name: generator
-      type: generator
+      name: HuggingFaceFW/fineweb sample-350BT
+      type: HuggingFaceFW/fineweb
       config: default
       split: train
-      args: default
+      args: sample-350BT
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.03652915851272016
+      value: 0.03652074363992172
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,13 +29,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # T5Laa-Large-WeightedLoss
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the HuggingFaceFW/fineweb sample-350BT dataset.
 It achieves the following results on the evaluation set:
-- Perplexity: 186.2719
-- Loss: 5.2272
+- Perplexity: 186.1024
+- Loss: 5.2263
 - Accuracy: 0.0365
-- Lookahead Perplexity: 1785.8340
-- Lookahead Loss: 7.4876
+- Lookahead Perplexity: 1785.6071
+- Lookahead Loss: 7.4875
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "eval_accuracy": 0.03652074363992172,
+    "eval_lookahead_loss": 7.4875137342453,
+    "eval_loss": 5.226296901702881,
+    "eval_perplexity": 186.10237056707334,
+    "eval_runtime": 490.6633,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 20.381,
+    "eval_steps_per_second": 5.095,
+    "total_flos": 4.833448717656785e+18,
+    "train_loss": 1.2404409057926387,
+    "train_runtime": 78461.8603,
+    "train_samples": 2000000,
+    "train_samples_per_second": 26.728,
+    "train_steps_per_second": 6.682
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_accuracy": 0.03652074363992172,
+    "eval_lookahead_loss": 7.4875137342453,
+    "eval_loss": 5.226296901702881,
+    "eval_perplexity": 186.10237056707334,
+    "eval_runtime": 490.6633,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 20.381,
+    "eval_steps_per_second": 5.095
+}

runs/Oct04_12-19-27_gpu23.viking2.yor.alces.network/events.out.tfevents.1759656120.gpu23.viking2.yor.alces.network.3198493.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682284128fd937e7a16b3e6c46683778515aed16c28258b8962c0917d541a79c
+size 596

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 4.833448717656785e+18,
+    "train_loss": 1.2404409057926387,
+    "train_runtime": 78461.8603,
+    "train_samples": 2000000,
+    "train_samples_per_second": 26.728,
+    "train_steps_per_second": 6.682
+}