End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
+- hi
 license: apache-2.0
 base_model: t5-small
 tags:
 - generated_from_trainer
 datasets:
 - opus100
+metrics:
+- bleu
 model-index:
 - name: english-hindi
-  results: []
+  results:
+  - task:
+      name: Translation
+      type: translation
+    dataset:
+      name: opus100 en-hi
+      type: opus100
+      config: en-hi
+      split: validation
+      args: en-hi
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +33,11 @@ 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: 0.0653
+- Bleu: 0.0
+- Gen Len: 97.5
 
 ## Model description
 

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 3.0,
     "eval_bleu": 0.0,
     "eval_gen_len": 97.5,
-    "eval_loss": 0.06751515716314316,
-    "eval_runtime": 90.3612,
+    "eval_loss": 0.06529662758111954,
+    "eval_runtime": 89.6426,
     "eval_samples": 4,
-    "eval_samples_per_second": 0.044,
+    "eval_samples_per_second": 0.045,
     "eval_steps_per_second": 0.011,
-    "train_loss": 0.29867087957350535,
-    "train_runtime": 457.9667,
+    "train_loss": 0.30248128956761855,
+    "train_runtime": 458.563,
     "train_samples": 1044,
-    "train_samples_per_second": 6.839,
-    "train_steps_per_second": 1.71
+    "train_samples_per_second": 6.83,
+    "train_steps_per_second": 1.708
 }

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 3.0,
     "eval_bleu": 0.0,
     "eval_gen_len": 97.5,
-    "eval_loss": 0.06751515716314316,
-    "eval_runtime": 90.3612,
+    "eval_loss": 0.06529662758111954,
+    "eval_runtime": 89.6426,
     "eval_samples": 4,
-    "eval_samples_per_second": 0.044,
+    "eval_samples_per_second": 0.045,
     "eval_steps_per_second": 0.011
 }

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.29867087957350535,
-    "train_runtime": 457.9667,
+    "train_loss": 0.30248128956761855,
+    "train_runtime": 458.563,
     "train_samples": 1044,
-    "train_samples_per_second": 6.839,
-    "train_steps_per_second": 1.71
+    "train_samples_per_second": 6.83,
+    "train_steps_per_second": 1.708
 }

trainer_state.json

@@ -11,17 +11,17 @@
     {
       "epoch": 1.92,
       "learning_rate": 1.8071519795657726e-05,
-      "loss": 0.3184,
+      "loss": 0.3225,
       "step": 500
     },
     {
       "epoch": 3.0,
       "step": 783,
       "total_flos": 38260492861440.0,
-      "train_loss": 0.29867087957350535,
-      "train_runtime": 457.9667,
-      "train_samples_per_second": 6.839,
-      "train_steps_per_second": 1.71
+      "train_loss": 0.30248128956761855,
+      "train_runtime": 458.563,
+      "train_samples_per_second": 6.83,
+      "train_steps_per_second": 1.708
     }
   ],
   "logging_steps": 500,