Upload 13 files

README.md

@@ -6,7 +6,7 @@ datasets:
 metrics:
 - rouge
 model-index:
-- name: small-2-6-t
+- name: small-2-6
   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-2-6-t
+# small-2-6
 
-This model is a fine-tuned version of [asy/cnndm/small-2-6/](https://huggingface.co/asy/cnndm/small-2-6/) on the cnn_dailymail 3.0.0 dataset.
+This model is a fine-tuned version of [cnn/small-2-6/](https://huggingface.co/cnn/small-2-6/) on the cnn_dailymail 3.0.0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.8186
 - Rouge1: 36.8241

all_results.json

@@ -6,13 +6,13 @@
     "eval_rouge2": 15.5366,
     "eval_rougeL": 25.7939,
     "eval_rougeLsum": 33.9987,
-    "eval_runtime": 2895.1594,
+    "eval_runtime": 2940.0108,
     "eval_samples": 13368,
-    "eval_samples_per_second": 4.617,
-    "eval_steps_per_second": 1.154,
+    "eval_samples_per_second": 4.547,
+    "eval_steps_per_second": 1.137,
     "train_loss": 2.1428533047548393,
-    "train_runtime": 18639.2458,
+    "train_runtime": 19152.4549,
     "train_samples": 287113,
-    "train_samples_per_second": 46.211,
-    "train_steps_per_second": 0.722
+    "train_samples_per_second": 44.973,
+    "train_steps_per_second": 0.703
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "asy/cnndm/small-2-6/",
+  "_name_or_path": "cnn/small-2-6/",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

eval_results.json

@@ -6,8 +6,8 @@
     "eval_rouge2": 15.5366,
     "eval_rougeL": 25.7939,
     "eval_rougeLsum": 33.9987,
-    "eval_runtime": 2895.1594,
+    "eval_runtime": 2940.0108,
     "eval_samples": 13368,
-    "eval_samples_per_second": 4.617,
-    "eval_steps_per_second": 1.154
+    "eval_samples_per_second": 4.547,
+    "eval_steps_per_second": 1.137
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 2.1428533047548393,
-    "train_runtime": 18639.2458,
+    "train_runtime": 19152.4549,
     "train_samples": 287113,
-    "train_samples_per_second": 46.211,
-    "train_steps_per_second": 0.722
+    "train_samples_per_second": 44.973,
+    "train_steps_per_second": 0.703
 }

trainer_state.json

@@ -168,9 +168,9 @@
       "step": 13458,
       "total_flos": 2.4076495124138803e+17,
       "train_loss": 2.1428533047548393,
-      "train_runtime": 18639.2458,
-      "train_samples_per_second": 46.211,
-      "train_steps_per_second": 0.722
+      "train_runtime": 19152.4549,
+      "train_samples_per_second": 44.973,
+      "train_steps_per_second": 0.703
     }
   ],
   "max_steps": 13458,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08155c889cb72a78ddd30a185fb53e42d1c84af4bd0f6bb896261b52826ff100
-size 3643
+oid sha256:9d39a5cd2672486ff40d8dc32363ebf1a136ab4beb6f5ee593c485030f64d336
+size 3707