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: T5Lae-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: 0.02610743639921722
+      value: 0.026029158512720158
 ---
 
 <!-- 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. -->
 
 # T5Lae-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: 56.6355
-- Loss: 4.0366
-- Accuracy: 0.0261
-- Lookahead Perplexity: 672.8140
-- Lookahead Loss: 6.5115
+- Perplexity: 56.6106
+- Loss: 4.0362
+- Accuracy: 0.0260
+- Lookahead Perplexity: 672.4668
+- Lookahead Loss: 6.5110
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "eval_accuracy": 0.026029158512720158,
+    "eval_lookahead_loss": 6.510952686786651,
+    "eval_loss": 4.036196708679199,
+    "eval_perplexity": 56.61062614576278,
+    "eval_runtime": 502.5542,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 19.898,
+    "eval_steps_per_second": 4.975,
+    "total_flos": 4.621498060193661e+18,
+    "train_loss": 0.2757485848851502,
+    "train_runtime": 24028.7714,
+    "train_samples": 2000000,
+    "train_samples_per_second": 87.277,
+    "train_steps_per_second": 21.819
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_accuracy": 0.026029158512720158,
+    "eval_lookahead_loss": 6.510952686786651,
+    "eval_loss": 4.036196708679199,
+    "eval_perplexity": 56.61062614576278,
+    "eval_runtime": 502.5542,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 19.898,
+    "eval_steps_per_second": 4.975
+}

runs/Oct02_11-42-07_gpu23.viking2.yor.alces.network/events.out.tfevents.1759426779.gpu23.viking2.yor.alces.network.1856724.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39410f128a4af8b7192c39f4b305961b7e63876faed0aeff90d1541ec58ed2d4
+size 596

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 4.621498060193661e+18,
+    "train_loss": 0.2757485848851502,
+    "train_runtime": 24028.7714,
+    "train_samples": 2000000,
+    "train_samples_per_second": 87.277,
+    "train_steps_per_second": 21.819
+}