Training in progress, step 500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb3a75c717ae752e110afc8848e94c023c92e5dd6ba4a394a1100fe749c803c0
+oid sha256:7c36d72b05089e24fbdb20f58edda2d589f745b59929423cb750fe3542e13898
 size 4115013

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7632102b51f9cd975997ce425386ca6b63be45da2f98ba12fd7afa7495fb1791
+oid sha256:e65a378301a7811cf0ef09053f95a65dcc2ca531c1d476902b59315ede5aeab0
 size 2329702453

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1e9f0a9c162250eb653e24c91d4bc635fee94c3dcf620662d23bf2c27723383
+oid sha256:c62b4adb9e39700227a9dfe709b9be3404fb7da10290b22d1a55586d48740a30
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2bdf107332819b8b0d87d6069d10ba2dda1f29f80df7e1966760b521b58e92a
+oid sha256:ee5d8512ea69f36ac3d76c8a2d1063766890ab26719024996676d7b75548920c
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7890519048206139,
-  "global_step": 400,
+  "epoch": 0.9863148810257675,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -294,11 +294,83 @@
       "eval_samples_per_second": 0.248,
       "eval_steps_per_second": 0.248,
       "step": 400
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0004536500579374276,
+      "loss": 0.2323,
+      "step": 410
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00045220162224797217,
+      "loss": 0.2222,
+      "step": 420
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0004507531865585168,
+      "loss": 0.2516,
+      "step": 430
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0004493047508690614,
+      "loss": 0.2851,
+      "step": 440
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.000447856315179606,
+      "loss": 0.2677,
+      "step": 450
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00044640787949015064,
+      "loss": 0.2447,
+      "step": 460
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00044495944380069523,
+      "loss": 0.3186,
+      "step": 470
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0004435110081112398,
+      "loss": 0.3035,
+      "step": 480
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0004420625724217845,
+      "loss": 0.3036,
+      "step": 490
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0004406141367323291,
+      "loss": 0.1972,
+      "step": 500
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0465357303619385,
+      "eval_rouge1": 0.1908791208791209,
+      "eval_rouge2": 0.10681818181818181,
+      "eval_rougeL": 0.17934065934065935,
+      "eval_rougeLsum": 0.19159340659340657,
+      "eval_runtime": 84.3482,
+      "eval_samples_per_second": 0.237,
+      "eval_steps_per_second": 0.237,
+      "step": 500
     }
   ],
   "max_steps": 3542,
   "num_train_epochs": 7,
-  "total_flos": 9736385735172096.0,
+  "total_flos": 1.2123850515499008e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7632102b51f9cd975997ce425386ca6b63be45da2f98ba12fd7afa7495fb1791
+oid sha256:e65a378301a7811cf0ef09053f95a65dcc2ca531c1d476902b59315ede5aeab0
 size 2329702453

runs/Feb08_05-23-30_74bc69b4becb/events.out.tfevents.1675836783.74bc69b4becb.290.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21105268d84f3f348f68abcded83c4611e07908cdda695737704011e1b70ca44
-size 8322
+oid sha256:1a4dba25a0bde9038c15a6af7ee58649a984a45ecfc3765c4e05acf774193a45
+size 10366