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-bleu
-  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-bleu
 
-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: 0.0804
+- Bleu: 0.0
+- Gen Len: 69.0
 
 ## Model description
 

all_results.json

@@ -1,14 +1,15 @@
 {
     "epoch": 3.0,
     "eval_bleu": 0.0,
-    "eval_loss": 0.06549184769392014,
-    "eval_runtime": 91.236,
-    "eval_samples": 4,
-    "eval_samples_per_second": 0.044,
-    "eval_steps_per_second": 0.011,
-    "train_loss": 0.30118698178579983,
-    "train_runtime": 460.6288,
-    "train_samples": 1044,
-    "train_samples_per_second": 6.799,
-    "train_steps_per_second": 1.7
+    "eval_gen_len": 69.0,
+    "eval_loss": 0.08041258901357651,
+    "eval_runtime": 107.5329,
+    "eval_samples": 8,
+    "eval_samples_per_second": 0.074,
+    "eval_steps_per_second": 0.019,
+    "train_loss": 0.27109126508768794,
+    "train_runtime": 953.4562,
+    "train_samples": 2088,
+    "train_samples_per_second": 6.57,
+    "train_steps_per_second": 1.642
 }

eval_results.json

@@ -1,9 +1,10 @@
 {
     "epoch": 3.0,
     "eval_bleu": 0.0,
-    "eval_loss": 0.06549184769392014,
-    "eval_runtime": 91.236,
-    "eval_samples": 4,
-    "eval_samples_per_second": 0.044,
-    "eval_steps_per_second": 0.011
+    "eval_gen_len": 69.0,
+    "eval_loss": 0.08041258901357651,
+    "eval_runtime": 107.5329,
+    "eval_samples": 8,
+    "eval_samples_per_second": 0.074,
+    "eval_steps_per_second": 0.019
 }

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": 0.30118698178579983,
-    "train_runtime": 460.6288,
-    "train_samples": 1044,
-    "train_samples_per_second": 6.799,
-    "train_steps_per_second": 1.7
+    "train_loss": 0.27109126508768794,
+    "train_runtime": 953.4562,
+    "train_samples": 2088,
+    "train_samples_per_second": 6.57,
+    "train_steps_per_second": 1.642
 }

trainer_state.json

@@ -3,32 +3,44 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 783,
+  "global_step": 1566,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.403575989782887e-05,
+      "loss": 0.3118,
+      "step": 500
+    },
     {
       "epoch": 1.92,
       "learning_rate": 1.8071519795657726e-05,
-      "loss": 0.3211,
-      "step": 500
+      "loss": 0.2617,
+      "step": 1000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.1072796934865904e-06,
+      "loss": 0.2432,
+      "step": 1500
     },
     {
       "epoch": 3.0,
-      "step": 783,
-      "total_flos": 38260492861440.0,
-      "train_loss": 0.30118698178579983,
-      "train_runtime": 460.6288,
-      "train_samples_per_second": 6.799,
-      "train_steps_per_second": 1.7
+      "step": 1566,
+      "total_flos": 73168104062976.0,
+      "train_loss": 0.27109126508768794,
+      "train_runtime": 953.4562,
+      "train_samples_per_second": 6.57,
+      "train_steps_per_second": 1.642
     }
   ],
   "logging_steps": 500,
-  "max_steps": 783,
+  "max_steps": 1566,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 38260492861440.0,
+  "total_flos": 73168104062976.0,
   "trial_name": null,
   "trial_params": null
 }