Training in progress, step 160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee7c0b39ba072977a286772c0af8b9fc2500ede55b83bc1199a158f6dfc1722
+oid sha256:4dc7b5a5ba3656e7e3ba33577f9d5c221551eb9ac38a8241da63b379cad73607
 size 3544920

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a11f66a4c84be3caa48c29e8c74885ea6b56dddb765149269bfd08b8903328
+oid sha256:694ade40292a0236fc581f36db7f75221ac5f2bf62938e0d5acefb6040f8d4ce
 size 1140034381

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac223aa8ee652f038edd3082fd2a44bd13436ca909976cb75fcc2c2108ab8b1
-size 14575
+oid sha256:5134742d8a3e0eb4235ccb75ae0c32f1d18107769b8c95d8a28999819cb8fa18
+size 14511

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83af140ab0aa237edb30d0fe7c12244f0dd58eccf65131d8908858944652ecc
+oid sha256:5e25f2c0298e32eb32bc4fd13a32a452c19048d5a88e784c5908ed1a05a2bbb1
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9696969696969697,
-  "global_step": 120,
+  "epoch": 1.2929292929292928,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -183,11 +183,70 @@
       "eval_samples_per_second": 0.062,
       "eval_steps_per_second": 0.032,
       "step": 120
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 3.6139,
+      "step": 125
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.265582655826558e-05,
+      "loss": 3.5873,
+      "step": 130
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.197831978319784e-05,
+      "loss": 3.3622,
+      "step": 135
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.130081300813008e-05,
+      "loss": 3.4854,
+      "step": 140
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.0623306233062334e-05,
+      "loss": 3.4429,
+      "step": 145
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.9945799457994585e-05,
+      "loss": 3.1618,
+      "step": 150
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 3.428,
+      "step": 155
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.859078590785908e-05,
+      "loss": 3.2305,
+      "step": 160
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 3.152249336242676,
+      "eval_rouge2_fmeasure": 0.0037,
+      "eval_rouge2_precision": 0.0062,
+      "eval_rouge2_recall": 0.0026,
+      "eval_runtime": 372.2318,
+      "eval_samples_per_second": 0.073,
+      "eval_steps_per_second": 0.038,
+      "step": 160
     }
   ],
   "max_steps": 369,
   "num_train_epochs": 3,
-  "total_flos": 4682703521710080.0,
+  "total_flos": 6243604695613440.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a11f66a4c84be3caa48c29e8c74885ea6b56dddb765149269bfd08b8903328
+oid sha256:694ade40292a0236fc581f36db7f75221ac5f2bf62938e0d5acefb6040f8d4ce
 size 1140034381