End of training

README.md

@@ -1,4 +1,7 @@
 ---
+language:
+- en
+- hi
 license: apache-2.0
 base_model: t5-small
 tags:
@@ -15,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # english-hindi
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus100 dataset.
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus100 en-hi dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0816
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 3.0,
     "eval_bleu": 0.0,
-    "eval_loss": 0.07966260612010956,
-    "eval_runtime": 114.5298,
+    "eval_loss": 0.08162859082221985,
+    "eval_runtime": 0.5668,
     "eval_samples": 8,
-    "eval_samples_per_second": 0.07,
-    "eval_steps_per_second": 0.017,
-    "train_loss": 0.27012521614669077,
-    "train_runtime": 925.0114,
+    "eval_samples_per_second": 14.114,
+    "eval_steps_per_second": 3.529,
+    "train_loss": 0.2691089805515333,
+    "train_runtime": 914.55,
     "train_samples": 2088,
-    "train_samples_per_second": 6.772,
-    "train_steps_per_second": 1.693
+    "train_samples_per_second": 6.849,
+    "train_steps_per_second": 1.712
 }

eval_results.json

@@ -1,9 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_bleu": 0.0,
-    "eval_loss": 0.07966260612010956,
-    "eval_runtime": 114.5298,
+    "eval_loss": 0.08162859082221985,
+    "eval_runtime": 0.5668,
     "eval_samples": 8,
-    "eval_samples_per_second": 0.07,
-    "eval_steps_per_second": 0.017
+    "eval_samples_per_second": 14.114,
+    "eval_steps_per_second": 3.529
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.27012521614669077,
-    "train_runtime": 925.0114,
+    "train_loss": 0.2691089805515333,
+    "train_runtime": 914.55,
     "train_samples": 2088,
-    "train_samples_per_second": 6.772,
-    "train_steps_per_second": 1.693
+    "train_samples_per_second": 6.849,
+    "train_steps_per_second": 1.712
 }

trainer_state.json

@@ -11,29 +11,29 @@
     {
       "epoch": 0.96,
       "learning_rate": 3.403575989782887e-05,
-      "loss": 0.3117,
+      "loss": 0.3102,
       "step": 500
     },
     {
       "epoch": 1.92,
       "learning_rate": 1.8071519795657726e-05,
-      "loss": 0.2609,
+      "loss": 0.2601,
       "step": 1000
     },
     {
       "epoch": 2.87,
       "learning_rate": 2.1072796934865904e-06,
-      "loss": 0.2413,
+      "loss": 0.2405,
       "step": 1500
     },
     {
       "epoch": 3.0,
       "step": 1566,
       "total_flos": 73168104062976.0,
-      "train_loss": 0.27012521614669077,
-      "train_runtime": 925.0114,
-      "train_samples_per_second": 6.772,
-      "train_steps_per_second": 1.693
+      "train_loss": 0.2691089805515333,
+      "train_runtime": 914.55,
+      "train_samples_per_second": 6.849,
+      "train_steps_per_second": 1.712
     }
   ],
   "logging_steps": 500,