Training in progress, step 360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:717aeabd41162df58c589016e262864ca577bac403e982cd24e9397df8d808b9
+oid sha256:3786ba93365a1ee7b1ae5886a0f9a4c711aab7ed233d909a2f3d469512b6005f
 size 3545432

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7dc2e0c6eac7de952444cda2f8a83b2d8ea1e3e332c7b71d88efa3373715d8
+oid sha256:9373701b4d3cd12bb97d502c54292e9ac07566346dda7a7d5485ed8c5163afc4
 size 1140034381

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2ebb2a66011e7d1a3811ef684f1282f4aaec21ae4f3b25e3ee99eaee99d42d
+oid sha256:6203e50d371e7fa8a5f28de7e01da29302f09791f7fb1158a31d3b5b121115d0
 size 14511

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:964c2be91d4357cef5d0efd7d9436b648b6eb7a171890a57465951684d53da2f
+oid sha256:083f1a4a1187ab20495ecc4456f9059e4e2102fc6106c30448967df2a7b52303
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.591919191919192,
-  "global_step": 320,
+  "epoch": 2.915151515151515,
+  "global_step": 360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -478,11 +478,70 @@
       "eval_samples_per_second": 0.054,
       "eval_steps_per_second": 0.028,
       "step": 320
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.368563685636857e-06,
+      "loss": 3.5124,
+      "step": 325
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.6910569105691056e-06,
+      "loss": 3.128,
+      "step": 330
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 5.013550135501355e-06,
+      "loss": 3.6112,
+      "step": 335
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.336043360433605e-06,
+      "loss": 3.0695,
+      "step": 340
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.6585365853658537e-06,
+      "loss": 3.4197,
+      "step": 345
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 3.116531165311653e-06,
+      "loss": 3.2216,
+      "step": 350
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.4390243902439027e-06,
+      "loss": 3.1863,
+      "step": 355
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.7615176151761518e-06,
+      "loss": 3.3628,
+      "step": 360
+    },
+    {
+      "epoch": 2.92,
+      "eval_loss": 3.125962972640991,
+      "eval_rouge2_fmeasure": 0.0,
+      "eval_rouge2_precision": 0.0,
+      "eval_rouge2_recall": 0.0,
+      "eval_runtime": 439.7386,
+      "eval_samples_per_second": 0.061,
+      "eval_steps_per_second": 0.032,
+      "step": 360
     }
   ],
   "max_steps": 369,
   "num_train_epochs": 3,
-  "total_flos": 1.248720939122688e+16,
+  "total_flos": 1.404811056513024e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7dc2e0c6eac7de952444cda2f8a83b2d8ea1e3e332c7b71d88efa3373715d8
+oid sha256:9373701b4d3cd12bb97d502c54292e9ac07566346dda7a7d5485ed8c5163afc4
 size 1140034381