End of training

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: BEE-spoke-data/tFINE-680m-e32-d16-gqa-1024
 tags:
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tFINE-680m-e32-d16-gqa-1024-flan-subsets-deduped-1024
 
-This model is a fine-tuned version of [BEE-spoke-data/tFINE-680m-e32-d16-gqa-1024](https://huggingface.co/BEE-spoke-data/tFINE-680m-e32-d16-gqa-1024) on an unknown dataset.
+This model is a fine-tuned version of [BEE-spoke-data/tFINE-680m-e32-d16-gqa-1024](https://huggingface.co/BEE-spoke-data/tFINE-680m-e32-d16-gqa-1024) on the pszemraj/flan-subsets-deduped dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.9999466719486831,
+    "num_input_tokens_seen": 2313940996,
+    "total_flos": 9.029436409798197e+18,
+    "train_loss": 0.7368571982491552,
+    "train_runtime": 130509.2663,
+    "train_samples": 4200414,
+    "train_samples_per_second": 32.185,
+    "train_steps_per_second": 0.126
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.9999466719486831,
+    "num_input_tokens_seen": 2313940996,
+    "total_flos": 9.029436409798197e+18,
+    "train_loss": 0.7368571982491552,
+    "train_runtime": 130509.2663,
+    "train_samples": 4200414,
+    "train_samples_per_second": 32.185,
+    "train_steps_per_second": 0.126
+}