Training in progress, step 240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb09faafe86c3f8a3809c282ff2b33e506a3661a79e5616b8276d0b82097d48
+oid sha256:be720761f0e10b60ecbc47900152f65973bd708bf66af4cbd26d0e647c2fc9ea
 size 3544920

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897b7b593f9821dbb0e2ae6d611894c506aa52d82fe38b6c5255a258f0b4cb62
+oid sha256:279001289160111f69989bdbd63e59b46d9353e04b8efe5c45c0ee36ea822c2b
 size 1140034381

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c7746ace7f5308e25daef2d7e569acf6cec5538b3a1f0aa281a80ddbbed1a8
+oid sha256:fdc259941b88629c38a5d42d50c6190d622a9bb02d68782819b22239cb26f270
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8d90b6a7613e88ebb00326afe3e46f5e2c7dab4f2323f113d4b53f6fc1eea8
+oid sha256:df343fa90fcddafb2dfc655c399dcd6fb9788397b581ec853a351289fbf07315
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6161616161616161,
-  "global_step": 200,
+  "epoch": 1.9393939393939394,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,11 +301,70 @@
       "eval_samples_per_second": 0.065,
       "eval_steps_per_second": 0.034,
       "step": 200
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2.2493224932249323e-05,
+      "loss": 3.4208,
+      "step": 205
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.181571815718157e-05,
+      "loss": 3.7157,
+      "step": 210
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.1138211382113822e-05,
+      "loss": 3.0534,
+      "step": 215
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.046070460704607e-05,
+      "loss": 3.2667,
+      "step": 220
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.978319783197832e-05,
+      "loss": 3.3489,
+      "step": 225
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.9105691056910573e-05,
+      "loss": 3.3139,
+      "step": 230
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.842818428184282e-05,
+      "loss": 3.3155,
+      "step": 235
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.775067750677507e-05,
+      "loss": 3.603,
+      "step": 240
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 3.135263681411743,
+      "eval_rouge2_fmeasure": 0.0,
+      "eval_rouge2_precision": 0.0,
+      "eval_rouge2_recall": 0.0,
+      "eval_runtime": 517.2838,
+      "eval_samples_per_second": 0.052,
+      "eval_steps_per_second": 0.027,
+      "step": 240
     }
   ],
   "max_steps": 369,
   "num_train_epochs": 3,
-  "total_flos": 7804505869516800.0,
+  "total_flos": 9365407043420160.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897b7b593f9821dbb0e2ae6d611894c506aa52d82fe38b6c5255a258f0b4cb62
+oid sha256:279001289160111f69989bdbd63e59b46d9353e04b8efe5c45c0ee36ea822c2b
 size 1140034381