Training in progress, step 80

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74d5f1a45d708b38e5462a32098619a77d216416ff27973af946caa6c7fbf36
+oid sha256:3dbb11a70fcae64bec104647c5acced3c0cd79c0b44ee82b6f3f250254ec5e50
 size 3544920

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ebbce591f251737d83478299d728e89bf21826c0f2b1592542f198360b0762
+oid sha256:276032cb589b04e8986400fdcfd96f9c2efadabf7a09d727dbe49fe1f4f6afbe
 size 1140034381

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d74287cececdc4f6ced3ef29c8a8d27ff10637de332defa7d4dbb07c0865050
-size 14511
+oid sha256:04ae77db66de79b69f8a3d821bbb733e237d660fa8765e0a2763c1fceddcd297
+size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7345e2891e6c7505609bb455ba0e660aaff504ba8618e8322a39b4afd34a7832
+oid sha256:7ecf13dfb953ccd15ae617ed9a359fdf95573284a2df37f02a60ab75ef4e68b6
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32323232323232326,
-  "global_step": 40,
+  "epoch": 0.6464646464646465,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,11 +65,70 @@
       "eval_samples_per_second": 0.15,
       "eval_steps_per_second": 0.078,
       "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.4037940379403794e-05,
+      "loss": 3.5264,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.336043360433605e-05,
+      "loss": 3.6286,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.26829268292683e-05,
+      "loss": 3.4611,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.2005420054200545e-05,
+      "loss": 3.9319,
+      "step": 60
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.132791327913279e-05,
+      "loss": 3.7751,
+      "step": 65
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.065040650406504e-05,
+      "loss": 3.6241,
+      "step": 70
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.9972899728997295e-05,
+      "loss": 3.3906,
+      "step": 75
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.9295392953929537e-05,
+      "loss": 3.1815,
+      "step": 80
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 3.189028739929199,
+      "eval_rouge2_fmeasure": 0.0,
+      "eval_rouge2_precision": 0.0,
+      "eval_rouge2_recall": 0.0,
+      "eval_runtime": 265.9332,
+      "eval_samples_per_second": 0.102,
+      "eval_steps_per_second": 0.053,
+      "step": 80
     }
   ],
   "max_steps": 369,
   "num_train_epochs": 3,
-  "total_flos": 1560901173903360.0,
+  "total_flos": 3121802347806720.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ebbce591f251737d83478299d728e89bf21826c0f2b1592542f198360b0762
+oid sha256:276032cb589b04e8986400fdcfd96f9c2efadabf7a09d727dbe49fe1f4f6afbe
 size 1140034381