Training in progress, step 12000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8dc9b7da6d26d633c2dd1a6298a08b45f5c5918ae1aaa6d997b662eb648987d
+oid sha256:4b8e8d3ec310b587a737b2ff1479785c95b383b0103a20c2616bcaa1b70cedfd
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5109c5ab50d16612c916165b2f1b379e87b9655586367244ed0f35eed2e9a8
+oid sha256:af1c4c4789099e3f06b7040705745688787a84de28b3c92b707a08bf66acedd5
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2650365deef6e7f360be9092deb581b50fcfc0981b456b54de45695f1dd87947
+oid sha256:de97c976c1994a7f2b52cd661dd45e50f8c59ea7f29046e2b153d031a5329003
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9300f32e301bd335f3fb5d2ba765ba95180c24ea46eaea685e58401c90015c1
+oid sha256:945dfe762c470357f0955a0e4fddcfadf68d636dfea2666def3fd34df1ab5189
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f730639438ee8fcdcc1e1cb83751cf1eada38bbe0ef956dce2851ca931960b8a
+oid sha256:3883b9681a4e564010f0c080b9a5c164f6cfc69d29380b6cdfc7bd14e3061a6c
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe934d44769ac7e9a840b774edada5ec3bca8cf109f459667d3c8dc00da8820d
+oid sha256:1bfa4cd8ff4ea106b4895cc38559e225da4381a514e25136b0ad798f67a76ec0
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b250b2b78856a4178b9411fc4c2c48db7ef90f84dc2088843965ef7dfde0aa6
+oid sha256:7bd3539150b8b4416c1ef3e8435df0b2b18db72a3b53e80a325b1d948246653b
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ca67d6482b0321beff26f4299075e123e65721ad7171ad8e9b4413b619f027
+oid sha256:414056302bb2c51030907ea288f267bbdafb5b349fed9bbe5df32046e41df462
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f545309b770f4b9aabc99027a1da637fdad2e36ae6df1f09d6f3e87c09353442
+oid sha256:217d507942f28f310e4eeed6bfba8d07fd2bb6dc167c4c4f66eda1c08b6318d6
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b930024c4c4916aafefd00a76494fc84038df46cd42e5e9dc314f9cb1f7dfe3
+oid sha256:06b43a58b72baf558b7e5624a89206c612752404e0e3755fa74aff6a8a856fea
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c259140dc729f7726e15f02d46430c5619fa08380b6000b04b9de5c5a519c4
+oid sha256:ef456277f681db2c07f1ff63be489edd84235ae448b25e8872b7c6ddb3f68afb
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.48,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -798,6 +798,164 @@
       "eval_samples_per_second": 17.03,
       "eval_steps_per_second": 0.545,
       "step": 10000
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 3.5040667057037354,
+      "learning_rate": 0.0025957538900165333,
+      "loss": 44.2118505859375,
+      "step": 10100
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 3.0154404640197754,
+      "learning_rate": 0.0025717060234955805,
+      "loss": 44.339365234375,
+      "step": 10200
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 3.0024242401123047,
+      "learning_rate": 0.0025475678057004796,
+      "loss": 44.2085009765625,
+      "step": 10300
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 2.868852138519287,
+      "learning_rate": 0.002523343051386793,
+      "loss": 44.1264453125,
+      "step": 10400
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.098557472229004,
+      "learning_rate": 0.0024990355889861417,
+      "loss": 44.0060986328125,
+      "step": 10500
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 2.94388747215271,
+      "learning_rate": 0.0024746492600011666,
+      "loss": 44.090751953125,
+      "step": 10600
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 3.172335147857666,
+      "learning_rate": 0.002450187918398426,
+      "loss": 44.108330078125,
+      "step": 10700
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 3.123621702194214,
+      "learning_rate": 0.0024256554299993214,
+      "loss": 44.00998046875,
+      "step": 10800
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 2.8541388511657715,
+      "learning_rate": 0.002401055671869152,
+      "loss": 43.941904296875,
+      "step": 10900
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.895085573196411,
+      "learning_rate": 0.0023763925317043903,
+      "loss": 43.792197265625,
+      "step": 11000
+    },
+    {
+      "epoch": 0.44,
+      "eval_accuracy": 0.20995894428152492,
+      "eval_loss": 43.750606536865234,
+      "eval_runtime": 6.9444,
+      "eval_samples_per_second": 18.0,
+      "eval_steps_per_second": 0.576,
+      "step": 11000
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 2.346236228942871,
+      "learning_rate": 0.0023516699072182786,
+      "loss": 43.9089990234375,
+      "step": 11100
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 2.3568971157073975,
+      "learning_rate": 0.002326891705524841,
+      "loss": 43.76560546875,
+      "step": 11200
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 3.0081124305725098,
+      "learning_rate": 0.0023020618425214144,
+      "loss": 43.808974609375,
+      "step": 11300
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 3.7043468952178955,
+      "learning_rate": 0.0022771842422697835,
+      "loss": 43.849228515625,
+      "step": 11400
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.2964367866516113,
+      "learning_rate": 0.0022522628363760323,
+      "loss": 43.599345703125,
+      "step": 11500
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 2.747478485107422,
+      "learning_rate": 0.002227301563369202,
+      "loss": 43.42494140625,
+      "step": 11600
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 2.878131866455078,
+      "learning_rate": 0.0022023043680788512,
+      "loss": 43.6928955078125,
+      "step": 11700
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 2.552713632583618,
+      "learning_rate": 0.0021772752010116247,
+      "loss": 43.6564453125,
+      "step": 11800
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 2.9993340969085693,
+      "learning_rate": 0.002152218017726923,
+      "loss": 43.607763671875,
+      "step": 11900
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.911576747894287,
+      "learning_rate": 0.002127136778211772,
+      "loss": 43.8162890625,
+      "step": 12000
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.21305474095796675,
+      "eval_loss": 43.4426155090332,
+      "eval_runtime": 7.5722,
+      "eval_samples_per_second": 16.508,
+      "eval_steps_per_second": 0.528,
+      "step": 12000
     }
   ],
   "logging_steps": 100,