Training in progress, step 320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d327d6055b26512249f738b530183f923a688879d89aee01c1a7f129ad20292b
+oid sha256:717aeabd41162df58c589016e262864ca577bac403e982cd24e9397df8d808b9
 size 3545432

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e431d6677e21cb70645f73a949e7a206eba6b539e4319051fde1cf766602b528
+oid sha256:af7dc2e0c6eac7de952444cda2f8a83b2d8ea1e3e332c7b71d88efa3373715d8
 size 1140034381

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b11dc40821345160db396d3d3b1fc931f4d0a9c790f3c549a309cd06fb1f698
-size 14575
+oid sha256:1b2ebb2a66011e7d1a3811ef684f1282f4aaec21ae4f3b25e3ee99eaee99d42d
+size 14511

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329548916d80d2326c3e9113fcfe22537334086ae18a4696a380e612ee2dcea2
+oid sha256:964c2be91d4357cef5d0efd7d9436b648b6eb7a171890a57465951684d53da2f
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.268686868686869,
-  "global_step": 280,
+  "epoch": 2.591919191919192,
+  "global_step": 320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -419,11 +419,70 @@
       "eval_samples_per_second": 0.061,
       "eval_steps_per_second": 0.032,
       "step": 280
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.1788617886178862e-05,
+      "loss": 3.0182,
+      "step": 285
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 3.4221,
+      "step": 290
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.0433604336043361e-05,
+      "loss": 3.1717,
+      "step": 295
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 3.309,
+      "step": 300
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 9.078590785907859e-06,
+      "loss": 3.215,
+      "step": 305
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 8.401084010840109e-06,
+      "loss": 3.2693,
+      "step": 310
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.723577235772358e-06,
+      "loss": 3.3973,
+      "step": 315
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.046070460704607e-06,
+      "loss": 3.3138,
+      "step": 320
+    },
+    {
+      "epoch": 2.59,
+      "eval_loss": 3.127232074737549,
+      "eval_rouge2_fmeasure": 0.0,
+      "eval_rouge2_precision": 0.0,
+      "eval_rouge2_recall": 0.0,
+      "eval_runtime": 495.8047,
+      "eval_samples_per_second": 0.054,
+      "eval_steps_per_second": 0.028,
+      "step": 320
     }
   ],
   "max_steps": 369,
   "num_train_epochs": 3,
-  "total_flos": 1.092630821732352e+16,
+  "total_flos": 1.248720939122688e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e431d6677e21cb70645f73a949e7a206eba6b539e4319051fde1cf766602b528
+oid sha256:af7dc2e0c6eac7de952444cda2f8a83b2d8ea1e3e332c7b71d88efa3373715d8
 size 1140034381