Training in progress, step 620000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34fa3fbc162567eded2c54001cc8f21167119645a7ad5d9438d4d6580d7e0aaf
+oid sha256:9a097619eaa9ef720984e4ddd9dde8f3b697ba4e3a54ad0e09caff9a338f70f3
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7fc5d60355a8dfd752019852cdb15ae9d272ab89ceb9fe9acfccaaa3393cce
+oid sha256:6297a4aa090b90aa3635b3517c4b127894ad2c42e14fd6d228c6743ce17aee7d
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd344a2f09d330c943a3dd3d04668fe450de22ee225e64c890f4722c7155791f
+oid sha256:7ef2eb325ca73aeb9167731426720e192b4dc476427d6c01affc7b3b2a3e583b
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7587b2027544c125ad8875c396124abeaa8b26e560f514a758d79f5c77d1245e
+oid sha256:3ef8f093c13597a9033ad0961b449077de3ab17c6b5e598e7ffe900737a37b62
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b98e6e4730ae83aa0bbaf43b6a70f2dbea908df991dba53b4ba6b61ef5a4bc51
+oid sha256:e20445f0abf4410bec575adab612ba675a2a9e22a555ffb2b2fb85961556a332
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fae6c192050786077eb0c3ad856996ecc90d4abf868828c40917e34e278ddf8
+oid sha256:20bb77018a33c479ea4b69c28339611c22b8e8641554d8590d8198df56a8bc21
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04edc224f8d5fe4b319f5145ba3be953f45d1403c8d037fe0f2d7e1df55860c5
+oid sha256:34450b80230704bfaa6dfc6f8672078f09277102e090e32e505412e8b0a06323
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd673ae46299e38ec0092baeee3dfcef9b18e2fdce8cd906ed6e5311b6eb2f0
+oid sha256:0f073590871f68cf52e503ea996a2b041d76f54fc155c63b39985473c3a2c6e9
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba46334d5cfb098826b8bc46bdfd08caddd05dd0a2ad976845aaf16ed9488107
+oid sha256:eb10ba8d357eb68fad272ff5bc8fb10ce9e5818ee9a6bd185f2331209c9c5eee
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:071dfcafc848e779fb2959117671810686f513947ddff515a5f53d88a149a7ef
+oid sha256:9bdc5c8f1d9880eb7b2e1404af5eeae63b870215c24de51ca47db7d2d9d87809
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1451fdba239492a726627053577a5d97726556e48bcec30f5b94d6df5305247b
+oid sha256:5e0be0a1dddd0483c31953c97f497ac534ef42fa519c13cb1ceaab964eeaafea
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2194195562912054,
-  "global_step": 610000,
+  "epoch": 1.2394100408205695,
+  "global_step": 620000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7326,11 +7326,131 @@
       "learning_rate": 6.058179638667089e-05,
       "loss": 0.3027,
       "step": 610000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.047062257725395e-05,
+      "loss": 0.3035,
+      "step": 610500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.035950216040917e-05,
+      "loss": 0.303,
+      "step": 611000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.0248435439935516e-05,
+      "loss": 0.3031,
+      "step": 611500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.0137422719485145e-05,
+      "loss": 0.3032,
+      "step": 612000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.0026464302562636e-05,
+      "loss": 0.303,
+      "step": 612500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.991556049252401e-05,
+      "loss": 0.303,
+      "step": 613000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.980471159257609e-05,
+      "loss": 0.3031,
+      "step": 613500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.969391790577551e-05,
+      "loss": 0.3026,
+      "step": 614000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.958317973502798e-05,
+      "loss": 0.3026,
+      "step": 614500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.947249738308747e-05,
+      "loss": 0.3024,
+      "step": 615000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.9361871152555254e-05,
+      "loss": 0.3031,
+      "step": 615500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.925130134587924e-05,
+      "loss": 0.3021,
+      "step": 616000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.914078826535307e-05,
+      "loss": 0.3021,
+      "step": 616500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.903033221311528e-05,
+      "loss": 0.3023,
+      "step": 617000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.891993349114847e-05,
+      "loss": 0.3025,
+      "step": 617500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.880959240127858e-05,
+      "loss": 0.3021,
+      "step": 618000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.86993092451739e-05,
+      "loss": 0.3022,
+      "step": 618500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.858908432434438e-05,
+      "loss": 0.3021,
+      "step": 619000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.847891794014074e-05,
+      "loss": 0.3017,
+      "step": 619500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5.8368810393753684e-05,
+      "loss": 0.3021,
+      "step": 620000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.124028700869167e+22,
+  "total_flos": 4.191638959928546e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7fc5d60355a8dfd752019852cdb15ae9d272ab89ceb9fe9acfccaaa3393cce
+oid sha256:6297a4aa090b90aa3635b3517c4b127894ad2c42e14fd6d228c6743ce17aee7d
 size 449450757