End of training

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: pszemraj/tFINE-850m-24x24-v0.5-instruct-L1
 tags:
@@ -14,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tFINE-850m-24x24-v0.5-instruct-L1-infinity-instruct-7m-T2T_en-1024-v2
 
-This model is a fine-tuned version of [pszemraj/tFINE-850m-24x24-v0.5-instruct-L1](https://huggingface.co/pszemraj/tFINE-850m-24x24-v0.5-instruct-L1) on an unknown dataset.
+This model is a fine-tuned version of [pszemraj/tFINE-850m-24x24-v0.5-instruct-L1](https://huggingface.co/pszemraj/tFINE-850m-24x24-v0.5-instruct-L1) on the pszemraj/infinity-instruct-7m-T2T_en dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2595
-- Num Input Tokens Seen: 568955808
+- Loss: 1.2542
+- Num Input Tokens Seen: 750938410
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.254249095916748,
+    "eval_runtime": 14.3091,
+    "eval_samples": 150,
+    "eval_samples_per_second": 10.483,
+    "eval_steps_per_second": 0.699,
+    "num_input_tokens_seen": 750938410,
+    "total_flos": 3.6248418467253043e+18,
+    "train_loss": 1.2696220230851407,
+    "train_runtime": 79988.0702,
+    "train_samples": 1013227,
+    "train_samples_per_second": 12.667,
+    "train_steps_per_second": 0.099
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.254249095916748,
+    "eval_runtime": 14.3091,
+    "eval_samples": 150,
+    "eval_samples_per_second": 10.483,
+    "eval_steps_per_second": 0.699,
+    "num_input_tokens_seen": 750938410
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "num_input_tokens_seen": 750938410,
+    "total_flos": 3.6248418467253043e+18,
+    "train_loss": 1.2696220230851407,
+    "train_runtime": 79988.0702,
+    "train_samples": 1013227,
+    "train_samples_per_second": 12.667,
+    "train_steps_per_second": 0.099
+}