medium_test

all_results.json

@@ -1,28 +1,28 @@
 {
-    "epoch": 2.95,
-    "eval_gen_len": 33.1429,
-    "eval_loss": 0.4828817844390869,
-    "eval_rouge1": 80.6131,
-    "eval_rouge2": 73.305,
-    "eval_rougeL": 79.6954,
-    "eval_rougeLsum": 79.6954,
-    "eval_runtime": 2.536,
+    "epoch": 3.0,
+    "eval_gen_len": 32.4286,
+    "eval_loss": 0.6024884581565857,
+    "eval_rouge1": 81.6007,
+    "eval_rouge2": 75.1196,
+    "eval_rougeL": 81.4213,
+    "eval_rougeLsum": 81.4956,
+    "eval_runtime": 2.4585,
     "eval_samples": 7,
-    "eval_samples_per_second": 2.76,
-    "eval_steps_per_second": 0.789,
-    "predict_gen_len": 33.1429,
-    "predict_loss": 0.4828817844390869,
-    "predict_rouge1": 80.6131,
-    "predict_rouge2": 73.305,
-    "predict_rougeL": 79.6954,
-    "predict_rougeLsum": 79.6954,
-    "predict_runtime": 2.541,
+    "eval_samples_per_second": 2.847,
+    "eval_steps_per_second": 0.814,
+    "predict_gen_len": 32.4286,
+    "predict_loss": 0.6024884581565857,
+    "predict_rouge1": 81.6007,
+    "predict_rouge2": 75.1196,
+    "predict_rougeL": 81.4213,
+    "predict_rougeLsum": 81.4956,
+    "predict_runtime": 2.535,
     "predict_samples": 7,
-    "predict_samples_per_second": 2.755,
-    "predict_steps_per_second": 0.787,
-    "train_loss": 0.7666861640082465,
-    "train_runtime": 31.051,
+    "predict_samples_per_second": 2.761,
+    "predict_steps_per_second": 0.789,
+    "train_loss": 0.2226855363795366,
+    "train_runtime": 43.1557,
     "train_samples": 252,
-    "train_samples_per_second": 24.347,
-    "train_steps_per_second": 1.449
+    "train_samples_per_second": 17.518,
+    "train_steps_per_second": 4.379
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Vamsi/T5_Paraphrase_Paws",
+  "_name_or_path": "prithivida/parrot_paraphraser_on_T5",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

eval_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 2.95,
-    "eval_gen_len": 33.1429,
-    "eval_loss": 0.4828817844390869,
-    "eval_rouge1": 80.6131,
-    "eval_rouge2": 73.305,
-    "eval_rougeL": 79.6954,
-    "eval_rougeLsum": 79.6954,
-    "eval_runtime": 2.536,
+    "epoch": 3.0,
+    "eval_gen_len": 32.4286,
+    "eval_loss": 0.6024884581565857,
+    "eval_rouge1": 81.6007,
+    "eval_rouge2": 75.1196,
+    "eval_rougeL": 81.4213,
+    "eval_rougeLsum": 81.4956,
+    "eval_runtime": 2.4585,
     "eval_samples": 7,
-    "eval_samples_per_second": 2.76,
-    "eval_steps_per_second": 0.789
+    "eval_samples_per_second": 2.847,
+    "eval_steps_per_second": 0.814
 }

generated_predictions.txt

@@ -1,7 +1,7 @@
-Danny Bazil Riley started working as general manager at a commercial real estate firm at an annual base salary of #36;70,000. Soon after a financial planner stopped by his desk to drop off brochures about insurance benefits available through his employer. But at 32, "buying insurance was the furthest thing from my mind," Riley says.
+After earning a PH.D. in Sociology Danny Bazil Riley started to work as the general manager at a commercial real estate firm at an annual base salary of #36;70,000. Soon after, a financial planner stopped by his desk to drop off brochures about insurance benefits available through his employer ### END
 Short-sellers, Wall Street's dwindling band of ultra-cynics, are seeing green again ### END
 Soaring crude prices ### outlook for earnings are expected to hang over the stock market next ### END
-OPEC can do nothing to douse scorching oil prices when markets are already oversupplied by 2.8 million barrels per day (bpd) of crude ### END
+OPEC can do nothing to douse scorching oil prices ### markets are already oversupplied by 2.8 million barrels per day (bpd) of crude ### END
 Non-OPEC oil exporters should consider increasing output to cool record crude prices ### END
 The auction for Google Inc.'s highly anticipated initial public offering got off to a rocky start on Friday ### END
 The dollar tumbled broadly on Friday ### END

predict_results.json

@@ -1,12 +1,12 @@
 {
-    "predict_gen_len": 33.1429,
-    "predict_loss": 0.4828817844390869,
-    "predict_rouge1": 80.6131,
-    "predict_rouge2": 73.305,
-    "predict_rougeL": 79.6954,
-    "predict_rougeLsum": 79.6954,
-    "predict_runtime": 2.541,
+    "predict_gen_len": 32.4286,
+    "predict_loss": 0.6024884581565857,
+    "predict_rouge1": 81.6007,
+    "predict_rouge2": 75.1196,
+    "predict_rougeL": 81.4213,
+    "predict_rougeLsum": 81.4956,
+    "predict_runtime": 2.535,
     "predict_samples": 7,
-    "predict_samples_per_second": 2.755,
-    "predict_steps_per_second": 0.787
+    "predict_samples_per_second": 2.761,
+    "predict_steps_per_second": 0.789
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bfd4f9feaf2691d94dc1e0bbb2677fb114aa0a1a4ed1f7370504cf292a19bdb
+oid sha256:0e92c6fd36fd7bae27e500790aae82c06d5810d9119113512024bfd270cc29b0
 size 891644863

tokenizer_config.json

@@ -1 +1 @@
-{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": "C:\\Users\\peter/.cache\\huggingface\\transformers\\ca670222dc28504dc97cb6136cadc777e4158e3b346f98b99064406f5ac6eac0.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "name_or_path": "Vamsi/T5_Paraphrase_Paws", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "prithivida/parrot_paraphraser_on_T5", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.95,
-    "train_loss": 0.7666861640082465,
-    "train_runtime": 31.051,
+    "epoch": 3.0,
+    "train_loss": 0.2226855363795366,
+    "train_runtime": 43.1557,
     "train_samples": 252,
-    "train_samples_per_second": 24.347,
-    "train_steps_per_second": 1.449
+    "train_samples_per_second": 17.518,
+    "train_steps_per_second": 4.379
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf8d9c3c9936cb871cebcdaea9f4bf6dce8ca2eca8a689ec8e0471393131ba89
+oid sha256:f54511f437804c9424ca64937a125d5979070916cc062e4a470a0c85309693fb
 size 3055