Upload 13 files

README.md

@@ -6,7 +6,7 @@ datasets:
 metrics:
 - rouge
 model-index:
-- name: small-3-6-t
+- name: small-3-6
   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-3-6-t
+# small-3-6
 
-This model is a fine-tuned version of [asy/cnndm/small-3-6](https://huggingface.co/asy/cnndm/small-3-6) on the cnn_dailymail 3.0.0 dataset.
+This model is a fine-tuned version of [cnn/small-3-6/](https://huggingface.co/cnn/small-3-6/) on the cnn_dailymail 3.0.0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.7320
 - Rouge1: 38.5733

all_results.json

@@ -6,13 +6,13 @@
     "eval_rouge2": 16.7984,
     "eval_rougeL": 27.1527,
     "eval_rougeLsum": 35.793,
-    "eval_runtime": 2928.1869,
+    "eval_runtime": 2973.3751,
     "eval_samples": 13368,
-    "eval_samples_per_second": 4.565,
-    "eval_steps_per_second": 1.141,
+    "eval_samples_per_second": 4.496,
+    "eval_steps_per_second": 1.124,
     "train_loss": 2.001928689168385,
-    "train_runtime": 25325.5133,
+    "train_runtime": 26117.7064,
     "train_samples": 287113,
-    "train_samples_per_second": 34.011,
-    "train_steps_per_second": 0.531
+    "train_samples_per_second": 32.979,
+    "train_steps_per_second": 0.515
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "asy/cnndm/small-3-6",
+  "_name_or_path": "cnn/small-3-6/",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

eval_results.json

@@ -6,8 +6,8 @@
     "eval_rouge2": 16.7984,
     "eval_rougeL": 27.1527,
     "eval_rougeLsum": 35.793,
-    "eval_runtime": 2928.1869,
+    "eval_runtime": 2973.3751,
     "eval_samples": 13368,
-    "eval_samples_per_second": 4.565,
-    "eval_steps_per_second": 1.141
+    "eval_samples_per_second": 4.496,
+    "eval_steps_per_second": 1.124
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 2.001928689168385,
-    "train_runtime": 25325.5133,
+    "train_runtime": 26117.7064,
     "train_samples": 287113,
-    "train_samples_per_second": 34.011,
-    "train_steps_per_second": 0.531
+    "train_samples_per_second": 32.979,
+    "train_steps_per_second": 0.515
 }

trainer_state.json

@@ -168,9 +168,9 @@
       "step": 13458,
       "total_flos": 2.6528666710694707e+17,
       "train_loss": 2.001928689168385,
-      "train_runtime": 25325.5133,
-      "train_samples_per_second": 34.011,
-      "train_steps_per_second": 0.531
+      "train_runtime": 26117.7064,
+      "train_samples_per_second": 32.979,
+      "train_steps_per_second": 0.515
     }
   ],
   "max_steps": 13458,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6efff05f8b72c2c4429a0e63741b1467364c7b7696f5db62baa8fe7fa92408
-size 3643
+oid sha256:5127cd381db677f1037d8ced9dd631ca715106159ded7ad6f265c1c84840ab31
+size 3707