End of training

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: BEE-spoke-data/tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024
 tags:
@@ -14,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024-infinity-instruct-7m-T2T_en-1024-v2
 
-This model is a fine-tuned version of [BEE-spoke-data/tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024](https://huggingface.co/BEE-spoke-data/tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024) on an unknown dataset.
+This model is a fine-tuned version of [BEE-spoke-data/tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024](https://huggingface.co/BEE-spoke-data/tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024) on the pszemraj/infinity-instruct-7m-T2T_en dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1160
-- Num Input Tokens Seen: 785755388
+- Loss: 1.1159
+- Num Input Tokens Seen: 810839096
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.1158816814422607,
+    "eval_runtime": 6.3937,
+    "eval_samples": 150,
+    "eval_samples_per_second": 23.461,
+    "eval_steps_per_second": 2.972,
+    "num_input_tokens_seen": 810839096,
+    "total_flos": 4.0772707408255386e+18,
+    "train_loss": 1.171214375919653,
+    "train_runtime": 248208.7734,
+    "train_samples": 2641663,
+    "train_samples_per_second": 10.643,
+    "train_steps_per_second": 0.083
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.1158816814422607,
+    "eval_runtime": 6.3937,
+    "eval_samples": 150,
+    "eval_samples_per_second": 23.461,
+    "eval_steps_per_second": 2.972,
+    "num_input_tokens_seen": 810839096
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "num_input_tokens_seen": 810839096,
+    "total_flos": 4.0772707408255386e+18,
+    "train_loss": 1.171214375919653,
+    "train_runtime": 248208.7734,
+    "train_samples": 2641663,
+    "train_samples_per_second": 10.643,
+    "train_steps_per_second": 0.083
+}