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: T5Laa2-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: 0.037367906066536206
+      value: 0.03730665362035225
 ---
 
 <!-- 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. -->
 
 # T5Laa2-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: 184.6505
-- Loss: 5.2185
-- Accuracy: 0.0374
-- Lookahead Perplexity: 2090.0473
-- Lookahead Loss: 7.6449
+- Perplexity: 184.5759
+- Loss: 5.2181
+- Accuracy: 0.0373
+- Lookahead Perplexity: 2089.7438
+- Lookahead Loss: 7.6448
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "eval_accuracy": 0.03730665362035225,
+    "eval_lookahead_loss": 7.644796759986877,
+    "eval_loss": 5.2180609703063965,
+    "eval_perplexity": 184.57593863292408,
+    "eval_runtime": 492.01,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 20.325,
+    "eval_steps_per_second": 5.081,
+    "total_flos": 4.833448717656785e+18,
+    "train_loss": 2.1971652193460613,
+    "train_runtime": 166030.7788,
+    "train_samples": 2000000,
+    "train_samples_per_second": 12.631,
+    "train_steps_per_second": 3.158
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_accuracy": 0.03730665362035225,
+    "eval_lookahead_loss": 7.644796759986877,
+    "eval_loss": 5.2180609703063965,
+    "eval_perplexity": 184.57593863292408,
+    "eval_runtime": 492.01,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 20.325,
+    "eval_steps_per_second": 5.081
+}

runs/Oct09_06-03-54_gpu22.viking2.yor.alces.network/events.out.tfevents.1760155049.gpu22.viking2.yor.alces.network.3252474.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a554ea2ead726f27c653d74b8060027aa9a86e1a82c5221945627fe08a408d
+size 596

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 4.833448717656785e+18,
+    "train_loss": 2.1971652193460613,
+    "train_runtime": 166030.7788,
+    "train_samples": 2000000,
+    "train_samples_per_second": 12.631,
+    "train_steps_per_second": 3.158
+}