Upload 13 files

README.md

@@ -6,7 +6,7 @@ datasets:
 metrics:
 - rouge
 model-index:
-- name: small-1-6-t
+- name: small-1-6
   results:
   - task:
       name: Summarization
@@ -26,9 +26,9 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# small-1-6-t
+# small-1-6
 
-This model is a fine-tuned version of [asy/cnndm/small-1-6](https://huggingface.co/asy/cnndm/small-1-6) on the cnn_dailymail 3.0.0 dataset.
+This model is a fine-tuned version of [cnn/small-1-6/](https://huggingface.co/cnn/small-1-6/) on the cnn_dailymail 3.0.0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.9557
 - Rouge1: 33.5775

all_results.json

@@ -6,13 +6,13 @@
     "eval_rouge2": 13.31,
     "eval_rougeL": 23.7214,
     "eval_rougeLsum": 30.9637,
-    "eval_runtime": 2616.5044,
+    "eval_runtime": 2653.6524,
     "eval_samples": 13368,
-    "eval_samples_per_second": 5.109,
-    "eval_steps_per_second": 1.277,
+    "eval_samples_per_second": 5.038,
+    "eval_steps_per_second": 1.259,
     "train_loss": 2.519211924293984,
-    "train_runtime": 15358.8719,
+    "train_runtime": 15932.3589,
     "train_samples": 287113,
-    "train_samples_per_second": 56.081,
-    "train_steps_per_second": 0.876
+    "train_samples_per_second": 54.062,
+    "train_steps_per_second": 0.845
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "asy/cnndm/small-1-6",
+  "_name_or_path": "cnn/small-1-6/",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

eval_results.json

@@ -6,8 +6,8 @@
     "eval_rouge2": 13.31,
     "eval_rougeL": 23.7214,
     "eval_rougeLsum": 30.9637,
-    "eval_runtime": 2616.5044,
+    "eval_runtime": 2653.6524,
     "eval_samples": 13368,
-    "eval_samples_per_second": 5.109,
-    "eval_steps_per_second": 1.277
+    "eval_samples_per_second": 5.038,
+    "eval_steps_per_second": 1.259
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 2.519211924293984,
-    "train_runtime": 15358.8719,
+    "train_runtime": 15932.3589,
     "train_samples": 287113,
-    "train_samples_per_second": 56.081,
-    "train_steps_per_second": 0.876
+    "train_samples_per_second": 54.062,
+    "train_steps_per_second": 0.845
 }

trainer_state.json

@@ -168,9 +168,9 @@
       "step": 13458,
       "total_flos": 2.285040933086085e+17,
       "train_loss": 2.519211924293984,
-      "train_runtime": 15358.8719,
-      "train_samples_per_second": 56.081,
-      "train_steps_per_second": 0.876
+      "train_runtime": 15932.3589,
+      "train_samples_per_second": 54.062,
+      "train_steps_per_second": 0.845
     }
   ],
   "max_steps": 13458,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3dd6d562817c1219b455cb4111d194607aa33139c86bfb42eb35167feb25f83
-size 3643
+oid sha256:3c1b03474c33158ff1497376100ee80287aca4b4cc2eead99f4797da164e3618
+size 3707