Training in progress, step 24000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da60d3804c57e29e90c568ae5208c61903451533ab428233f16399bcbfdc9166
+oid sha256:7d1c6311d572f46a40ce4eb1f61e2424dd71806261ba704027aaaba0f53be1d3
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae80c44868efaca16e3497e99d1fc33821e44d73899ed13a47e498dc9e7e5f4f
+oid sha256:406e804c5931a6000ece6c45c72c2083479252e8a80b808997d89f3582f02d7c
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61863070aab8e3fd6186dff8c80983e46f5b6001d914499a18aecd5a02fce32e
+oid sha256:fcb26f09d74efdea654cd6f0c6e78cd3e7623b779d82863159c4f16bc5889ad4
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c56eb422b2956686f9277e34bc8cc34789a6a9f96cf48c8d1b348ee4c2ad32c
+oid sha256:929250de26e41d8c2bd1974c52ecfb0856cc75bc17b68237754cbebda202d823
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840cbc90b77dbf5757761c33cef483dae80038c8699a537b601bec429e4b01e9
+oid sha256:dd047aae276051c168a6ca7a4dc31647ad0f9fdb6b46bb26cce7430994cbd35b
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff0e24afa3409357bf39531523e499a8986d839d13150d8699023666917a09d
+oid sha256:f57c573bc192fc2295ea4932d408c4cde38e64faf388e178f6aa0d97bb4a5608
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905af1194cdc14999c18dad2fabad60fafc93ae7a1c0e79c4823b9eb13773481
+oid sha256:e97a8cd9c3363d0ad2e30f9c2a29774c5d7047232697e060cddc7c85b31c0b41
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67c497a04a0d73e36401384f5befb87de2150301460bc892a7b91a194cddf9c
+oid sha256:3e82abfebcf7dbe10548c9a7640e13daccea206911077357e8a8b41a7d71deaf
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1005ca97ab493a99758751af1ed27f7d6861f63a7b13198af207a82d4466553b
+oid sha256:7d2ef15daaa8b40793b1d85f9a922559042ab20cd3d4f334c812af308bbdd607
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f85e297907fbcb53b678fa9ba91187159d898c1cb97d3c43297e528ef7f91d
+oid sha256:084371fcc7045b3c000b45241abee083d78c6426437535d482510c54f8bccc10
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4367024a5082b707bb4697c2bda35f75c55af7bbf7b2a4d5e72a490087ab5da
+oid sha256:9cab327592548328ae2943f7e4c2b7e1f1745457edb6d6e98a239c4ffa106827
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.88,
+  "epoch": 0.96,
   "eval_steps": 1000,
-  "global_step": 22000,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -1746,6 +1746,164 @@
       "eval_samples_per_second": 18.232,
       "eval_steps_per_second": 0.583,
       "step": 22000
+    },
+    {
+      "epoch": 0.884,
+      "grad_norm": 1.0895456075668335,
+      "learning_rate": 0.0001315357457244073,
+      "loss": 41.9967822265625,
+      "step": 22100
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.9787936210632324,
+      "learning_rate": 0.000122716055463316,
+      "loss": 41.919248046875,
+      "step": 22200
+    },
+    {
+      "epoch": 0.892,
+      "grad_norm": 0.8595688343048096,
+      "learning_rate": 0.00011419304739439529,
+      "loss": 42.098642578125,
+      "step": 22300
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.8901764154434204,
+      "learning_rate": 0.00010596806847675766,
+      "loss": 42.3766357421875,
+      "step": 22400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9945716261863708,
+      "learning_rate": 9.80424185695874e-05,
+      "loss": 42.459091796875,
+      "step": 22500
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.9749753475189209,
+      "learning_rate": 9.041735022671139e-05,
+      "loss": 42.227529296875,
+      "step": 22600
+    },
+    {
+      "epoch": 0.908,
+      "grad_norm": 0.8896678686141968,
+      "learning_rate": 8.309406849864854e-05,
+      "loss": 41.9632080078125,
+      "step": 22700
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.9081159830093384,
+      "learning_rate": 7.607373074216573e-05,
+      "loss": 41.939306640625,
+      "step": 22800
+    },
+    {
+      "epoch": 0.916,
+      "grad_norm": 0.8322077989578247,
+      "learning_rate": 6.935744643737252e-05,
+      "loss": 42.21763671875,
+      "step": 22900
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8767455816268921,
+      "learning_rate": 6.294627701237876e-05,
+      "loss": 42.1103955078125,
+      "step": 23000
+    },
+    {
+      "epoch": 0.92,
+      "eval_accuracy": 0.22741544477028347,
+      "eval_loss": 42.044464111328125,
+      "eval_runtime": 7.5593,
+      "eval_samples_per_second": 16.536,
+      "eval_steps_per_second": 0.529,
+      "step": 23000
+    },
+    {
+      "epoch": 0.924,
+      "grad_norm": 0.8490807414054871,
+      "learning_rate": 5.6841235675552106e-05,
+      "loss": 42.408046875,
+      "step": 23100
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.8971438407897949,
+      "learning_rate": 5.1043287255389206e-05,
+      "loss": 42.293935546875,
+      "step": 23200
+    },
+    {
+      "epoch": 0.932,
+      "grad_norm": 0.8031958341598511,
+      "learning_rate": 4.555334804803857e-05,
+      "loss": 42.037109375,
+      "step": 23300
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.9145307540893555,
+      "learning_rate": 4.03722856724893e-05,
+      "loss": 42.266640625,
+      "step": 23400
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.105343222618103,
+      "learning_rate": 3.5500918933456085e-05,
+      "loss": 41.9810498046875,
+      "step": 23500
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 1.2218998670578003,
+      "learning_rate": 3.094001769197474e-05,
+      "loss": 42.188876953125,
+      "step": 23600
+    },
+    {
+      "epoch": 0.948,
+      "grad_norm": 0.8797289729118347,
+      "learning_rate": 2.669030274373663e-05,
+      "loss": 42.359853515625,
+      "step": 23700
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.8956351280212402,
+      "learning_rate": 2.2752445705175097e-05,
+      "loss": 42.1323095703125,
+      "step": 23800
+    },
+    {
+      "epoch": 0.956,
+      "grad_norm": 0.8726316690444946,
+      "learning_rate": 1.9127068907324184e-05,
+      "loss": 42.337939453125,
+      "step": 23900
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.1114789247512817,
+      "learning_rate": 1.581474529746729e-05,
+      "loss": 42.27337890625,
+      "step": 24000
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.22743890518084067,
+      "eval_loss": 42.037322998046875,
+      "eval_runtime": 7.0814,
+      "eval_samples_per_second": 17.652,
+      "eval_steps_per_second": 0.565,
+      "step": 24000
     }
   ],
   "logging_steps": 100,