Training in progress, step 120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbb11a70fcae64bec104647c5acced3c0cd79c0b44ee82b6f3f250254ec5e50
+oid sha256:dee7c0b39ba072977a286772c0af8b9fc2500ede55b83bc1199a158f6dfc1722
 size 3544920

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276032cb589b04e8986400fdcfd96f9c2efadabf7a09d727dbe49fe1f4f6afbe
+oid sha256:66a11f66a4c84be3caa48c29e8c74885ea6b56dddb765149269bfd08b8903328
 size 1140034381

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ae77db66de79b69f8a3d821bbb733e237d660fa8765e0a2763c1fceddcd297
+oid sha256:3ac223aa8ee652f038edd3082fd2a44bd13436ca909976cb75fcc2c2108ab8b1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ecf13dfb953ccd15ae617ed9a359fdf95573284a2df37f02a60ab75ef4e68b6
+oid sha256:f83af140ab0aa237edb30d0fe7c12244f0dd58eccf65131d8908858944652ecc
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6464646464646465,
-  "global_step": 80,
+  "epoch": 0.9696969696969697,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -124,11 +124,70 @@
       "eval_samples_per_second": 0.102,
       "eval_steps_per_second": 0.053,
       "step": 80
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.861788617886179e-05,
+      "loss": 3.3673,
+      "step": 85
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.794037940379404e-05,
+      "loss": 3.3792,
+      "step": 90
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.726287262872629e-05,
+      "loss": 3.5732,
+      "step": 95
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.6585365853658535e-05,
+      "loss": 3.2772,
+      "step": 100
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.6043360433604336e-05,
+      "loss": 3.3803,
+      "step": 105
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.5365853658536584e-05,
+      "loss": 3.2597,
+      "step": 110
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.468834688346884e-05,
+      "loss": 3.4085,
+      "step": 115
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.401084010840109e-05,
+      "loss": 3.2319,
+      "step": 120
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 3.166618824005127,
+      "eval_rouge2_fmeasure": 0.0,
+      "eval_rouge2_precision": 0.0,
+      "eval_rouge2_recall": 0.0,
+      "eval_runtime": 433.3435,
+      "eval_samples_per_second": 0.062,
+      "eval_steps_per_second": 0.032,
+      "step": 120
     }
   ],
   "max_steps": 369,
   "num_train_epochs": 3,
-  "total_flos": 3121802347806720.0,
+  "total_flos": 4682703521710080.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276032cb589b04e8986400fdcfd96f9c2efadabf7a09d727dbe49fe1f4f6afbe
+oid sha256:66a11f66a4c84be3caa48c29e8c74885ea6b56dddb765149269bfd08b8903328
 size 1140034381