Training in progress, step 200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc7b5a5ba3656e7e3ba33577f9d5c221551eb9ac38a8241da63b379cad73607
+oid sha256:5fb09faafe86c3f8a3809c282ff2b33e506a3661a79e5616b8276d0b82097d48
 size 3544920

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694ade40292a0236fc581f36db7f75221ac5f2bf62938e0d5acefb6040f8d4ce
+oid sha256:897b7b593f9821dbb0e2ae6d611894c506aa52d82fe38b6c5255a258f0b4cb62
 size 1140034381

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5134742d8a3e0eb4235ccb75ae0c32f1d18107769b8c95d8a28999819cb8fa18
-size 14511
+oid sha256:46c7746ace7f5308e25daef2d7e569acf6cec5538b3a1f0aa281a80ddbbed1a8
+size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e25f2c0298e32eb32bc4fd13a32a452c19048d5a88e784c5908ed1a05a2bbb1
+oid sha256:da8d90b6a7613e88ebb00326afe3e46f5e2c7dab4f2323f113d4b53f6fc1eea8
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2929292929292928,
-  "global_step": 160,
+  "epoch": 1.6161616161616161,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -242,11 +242,70 @@
       "eval_samples_per_second": 0.073,
       "eval_steps_per_second": 0.038,
       "step": 160
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.7913279132791332e-05,
+      "loss": 3.0798,
+      "step": 165
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.7235772357723577e-05,
+      "loss": 3.2169,
+      "step": 170
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.6558265582655828e-05,
+      "loss": 3.4364,
+      "step": 175
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.588075880758808e-05,
+      "loss": 3.2353,
+      "step": 180
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5203252032520324e-05,
+      "loss": 3.4389,
+      "step": 185
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.4525745257452575e-05,
+      "loss": 3.2847,
+      "step": 190
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.3848238482384823e-05,
+      "loss": 3.0442,
+      "step": 195
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.3170731707317075e-05,
+      "loss": 3.2043,
+      "step": 200
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 3.1420483589172363,
+      "eval_rouge2_fmeasure": 0.0032,
+      "eval_rouge2_precision": 0.0041,
+      "eval_rouge2_recall": 0.0026,
+      "eval_runtime": 417.3311,
+      "eval_samples_per_second": 0.065,
+      "eval_steps_per_second": 0.034,
+      "step": 200
     }
   ],
   "max_steps": 369,
   "num_train_epochs": 3,
-  "total_flos": 6243604695613440.0,
+  "total_flos": 7804505869516800.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694ade40292a0236fc581f36db7f75221ac5f2bf62938e0d5acefb6040f8d4ce
+oid sha256:897b7b593f9821dbb0e2ae6d611894c506aa52d82fe38b6c5255a258f0b4cb62
 size 1140034381