Training in progress, step 590000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b97846fdadb13ecc89b990ffbfaea31753c6d134e7f9621ae4b97949baa934
+oid sha256:4bd1f4862280bc4f9f20cf61fc91f853df59d4ca3541b026db7600611b178d50
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa443f36220a6aedf6cdecc3aeff249f36151b40d145c313b87e4861b40ff1fd
+oid sha256:6e98866b99e3ecd40c53531087e5d2e3191cf9fd862f418f5c2164fc106076e1
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d5d975ea5032a4fee732b488751ac503809f97c5a97fc5c150420015f63f59
+oid sha256:ab3dcf04e4677cd69d3fbe91cb1ae1601851f3937f4fd0e788d25fd8dd5a9a5c
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82301dbdc2050c96e50026f93aa4a52314ec8c01629cc7c0f11d3b9284b02b76
+oid sha256:6068ed85b429651ab3dcdb9d8c131e8794f545bafa654289904ead8dcf71a796
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d36b524e1cf3ff7280f1a861b656a4601e1aba26fdfd644ce781041d1557cce
+oid sha256:96d9c6af477a0b5f695c5b258b6a01aca5fc7cfa2d38303757339b849dbd7d3e
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3917b54ce5dc7eb641cdd78fd0a0978e80de79358c1b36b12caa3239317201
+oid sha256:567a88294b09dd010f920f0bbc226b5e5f9189a07eafb2d3246224b7bdd85b03
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0700e353e4c24bd7f45605feb5effc0f098726a45e4d629bd16e4e957a9c77ec
+oid sha256:56ebaee321096ea2774b004b42a63721b74b8260bf65ca91c67dcab0fe39ddf6
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e36ee885f405ec22767d367631414e77bd2075c1685f36abd539895982834c63
+oid sha256:400b8eee678f22dae7d12f6670127ef9e783a9bd2487ab20a30cddd0d1ae18fc
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2aa2af79afdb15eab0a4b81e658e0ca231ea26b65610b0c397f93863155288c
+oid sha256:6ace2fdb32ece5ddc2b6164c2a1d1ed057e126355e32ac6d8db09bc2cd476da7
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34064d25a5effc83313a5d222ba9faf999237374d1682da4cf3a153062ce8826
+oid sha256:90d67e927134f71d028c643f8c9e8a2e214f618d0796c97003c322009d54ac2a
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c71db5ce47ed1c5dbb7d289f7c4a19b86b1dd82f2d4ad56f966c11daf1c69624
+oid sha256:4c3d2e37603fc85abdaa1469887efb3190e7c384dc663afb9c8011e46abae231
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1594481027031134,
-  "global_step": 580000,
+  "epoch": 1.1794385872324773,
+  "global_step": 590000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6966,11 +6966,131 @@
       "learning_rate": 6.733836259675233e-05,
       "loss": 0.3055,
       "step": 580000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.722454623985994e-05,
+      "loss": 0.3046,
+      "step": 580500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.71107648105703e-05,
+      "loss": 0.3051,
+      "step": 581000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.69970186199575e-05,
+      "loss": 0.305,
+      "step": 581500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.688330797899925e-05,
+      "loss": 0.3048,
+      "step": 582000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.676963319857618e-05,
+      "loss": 0.3049,
+      "step": 582500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.665599458947072e-05,
+      "loss": 0.3056,
+      "step": 583000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.654239246236651e-05,
+      "loss": 0.3043,
+      "step": 583500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.642882712784742e-05,
+      "loss": 0.3049,
+      "step": 584000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.631529889639679e-05,
+      "loss": 0.3052,
+      "step": 584500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.620180807839639e-05,
+      "loss": 0.3046,
+      "step": 585000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.608835498412583e-05,
+      "loss": 0.3042,
+      "step": 585500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.597493992376152e-05,
+      "loss": 0.3047,
+      "step": 586000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.586156320737592e-05,
+      "loss": 0.305,
+      "step": 586500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.574822514493664e-05,
+      "loss": 0.3049,
+      "step": 587000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.56349260463056e-05,
+      "loss": 0.3044,
+      "step": 587500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.552166622123824e-05,
+      "loss": 0.3045,
+      "step": 588000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.540844597938256e-05,
+      "loss": 0.3046,
+      "step": 588500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.52952656302784e-05,
+      "loss": 0.3045,
+      "step": 589000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.518212548335651e-05,
+      "loss": 0.3044,
+      "step": 589500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.506902584793773e-05,
+      "loss": 0.3043,
+      "step": 590000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 3.9212060895439885e+22,
+  "total_flos": 3.988811683155628e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa443f36220a6aedf6cdecc3aeff249f36151b40d145c313b87e4861b40ff1fd
+oid sha256:6e98866b99e3ecd40c53531087e5d2e3191cf9fd862f418f5c2164fc106076e1
 size 449450757