End of training

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: pszemraj/tFINE-850m-24x24-v0.4-flan_aug
 tags:
@@ -16,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tFINE-850m-24x24-v0.4-flan_aug-infinity-instruct-7m-T2T_en-1024-v5
 
-This model is a fine-tuned version of [pszemraj/tFINE-850m-24x24-v0.4-flan_aug](https://huggingface.co/pszemraj/tFINE-850m-24x24-v0.4-flan_aug) on an unknown dataset.
+This model is a fine-tuned version of [pszemraj/tFINE-850m-24x24-v0.4-flan_aug](https://huggingface.co/pszemraj/tFINE-850m-24x24-v0.4-flan_aug) on the pszemraj/infinity-instruct-7m-T2T_en dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1526
-- Rouge1: 40.1804
-- Rouge2: 23.1008
-- Rougel: 32.3484
-- Rougelsum: 38.2103
-- Gen Len: 422.225
-- Num Input Tokens Seen: 421585440
+- Loss: 1.1478
+- Rouge1: 38.4805
+- Rouge2: 22.5971
+- Rougel: 31.1093
+- Rougelsum: 36.596
+- Gen Len: 441.475
+- Num Input Tokens Seen: 435513684
 
 ## Model description
 

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 0.9999924371336737,
+    "eval_gen_len": 441.475,
+    "eval_loss": 1.1477829217910767,
+    "eval_rouge1": 38.4805,
+    "eval_rouge2": 22.5971,
+    "eval_rougeL": 31.1093,
+    "eval_rougeLsum": 36.596,
+    "eval_runtime": 1460.0731,
+    "eval_samples": 200,
+    "eval_samples_per_second": 0.137,
+    "eval_steps_per_second": 0.034,
+    "num_input_tokens_seen": 435513684,
+    "total_flos": 2.1022605922963784e+18,
+    "train_loss": 1.4536694422503678,
+    "train_runtime": 158351.1039,
+    "train_samples": 1586697,
+    "train_samples_per_second": 10.02,
+    "train_steps_per_second": 0.078
+}

eval_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.9999924371336737,
+    "eval_gen_len": 441.475,
+    "eval_loss": 1.1477829217910767,
+    "eval_rouge1": 38.4805,
+    "eval_rouge2": 22.5971,
+    "eval_rougeL": 31.1093,
+    "eval_rougeLsum": 36.596,
+    "eval_runtime": 1460.0731,
+    "eval_samples": 200,
+    "eval_samples_per_second": 0.137,
+    "eval_steps_per_second": 0.034,
+    "num_input_tokens_seen": 435513684
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.9999924371336737,
+    "num_input_tokens_seen": 435513684,
+    "total_flos": 2.1022605922963784e+18,
+    "train_loss": 1.4536694422503678,
+    "train_runtime": 158351.1039,
+    "train_samples": 1586697,
+    "train_samples_per_second": 10.02,
+    "train_steps_per_second": 0.078
+}