Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57bcf9aadb84dfa8897b2e4530b987a9c127fd8f62e36d334273f6f79ba49fd4
+oid sha256:3c4aa0a739cabddc45470d8fd65d8bbcc21e009d7c0b5a463fe31977531b0d03
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:222f7b426772c1ffb9f700de36da891361e9e0f275abce60101e6d83da4257b2
+oid sha256:6363f2bb80c8ec7f96e53d882d5e3ccab1d00f995f0853f15c2c53f1e4e2a2a3
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ffdf794aa37bf66c11fbf3a25c5c6e95b77bf37b30e60af016fc9124d0bcb99
+oid sha256:88b48f43625e8919759a700846736ad1c67a9fb02b424ca27c045fdf11ebec4d
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81af6df700759cf275cafea0cdaf381ba3c2b41fab7e7379341c665c147ed0de
+oid sha256:a3df8bbf0aa54958cebb063d8843254a6ca7fa9a4ecc3a91470b305106963beb
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55b42bedc0f28bff9c30b7bebe80ce64a5aa5c0c36daab2e46abff72980db18
+oid sha256:0c2aba2784b08e863f59f03cfa3309c63893fb49cde8f0070f10410339e4d7fd
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef44384c481d885f2114df6c79173cd8acc16cb1ee47046bf46031abdcc9c81b
+oid sha256:827e90af5517da4bb9113a66cb2136b09f8d4c852d96861d993b1d3b68201f38
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41a4b4c8c4b93050c780cbd4537fecb50bacfb6229c463432858be6d6a803f6
+oid sha256:4db1556f9cda170711f81bfb9343feab14e545a26997a7968c5820a578a542c7
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79aee2c3afea7ec6ffe3ac7b43481b7334a7abba51e0d4f2ed2312cd5550aeb
+oid sha256:165ab5fc90c8c3dd2e6e924be06814806faf1d60acb8d14cc4b0676f6f5737f1
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c918f0602d1108574e113fb8e32d725731b2c86339c03552c0229840eb091bf8
+oid sha256:017ce61066c39ae46b1e2925435311fe07b1d409bfd8cdcf79a1c7f1a9b9127b
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f462384e1628ac3068742a9ce939fc67956eb63350336c85c9bc3aee27af07
+oid sha256:64b97a485d2b1a72ff869a0ba55eed82c522e3229735d8894bfab7c67a78fe16
 size 14469

last-checkpoint/trainer_state.json

@@ -11,82 +11,82 @@
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 0.7191144824028015,
+      "grad_norm": 0.7426957488059998,
       "learning_rate": 0.003920764340590609,
-      "loss": 67.510126953125,
+      "loss": 72.8711376953125,
       "step": 100
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.1416715542521994,
-      "eval_loss": 62.5124397277832,
-      "eval_runtime": 23.2064,
-      "eval_samples_per_second": 5.386,
-      "eval_steps_per_second": 0.172,
+      "eval_accuracy": 0.14167057673509287,
+      "eval_loss": 67.97270202636719,
+      "eval_runtime": 22.8453,
+      "eval_samples_per_second": 5.472,
+      "eval_steps_per_second": 0.175,
       "step": 100
     },
     {
       "epoch": 0.2,
-      "grad_norm": 0.7917912006378174,
+      "grad_norm": 0.8975178003311157,
       "learning_rate": 0.003650943793925548,
-      "loss": 60.964296875,
+      "loss": 66.589296875,
       "step": 200
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.14520723362658847,
-      "eval_loss": 59.7275390625,
-      "eval_runtime": 7.0415,
-      "eval_samples_per_second": 17.752,
-      "eval_steps_per_second": 0.568,
+      "eval_accuracy": 0.14497360703812318,
+      "eval_loss": 65.53248596191406,
+      "eval_runtime": 6.8987,
+      "eval_samples_per_second": 18.119,
+      "eval_steps_per_second": 0.58,
       "step": 200
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.6012804508209229,
+      "grad_norm": 0.7394354939460754,
       "learning_rate": 0.0032162636906540357,
-      "loss": 58.9265185546875,
+      "loss": 64.9186376953125,
       "step": 300
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.14982697947214077,
-      "eval_loss": 58.20082092285156,
-      "eval_runtime": 6.9154,
-      "eval_samples_per_second": 18.076,
-      "eval_steps_per_second": 0.578,
+      "eval_accuracy": 0.14910752688172044,
+      "eval_loss": 64.25424194335938,
+      "eval_runtime": 6.8571,
+      "eval_samples_per_second": 18.229,
+      "eval_steps_per_second": 0.583,
       "step": 300
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.5591040849685669,
+      "grad_norm": 0.6404462456703186,
       "learning_rate": 0.0026601302141692667,
-      "loss": 57.6960791015625,
+      "loss": 63.8567431640625,
       "step": 400
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.15061388074291301,
-      "eval_loss": 57.27326965332031,
-      "eval_runtime": 6.7764,
-      "eval_samples_per_second": 18.446,
-      "eval_steps_per_second": 0.59,
+      "eval_accuracy": 0.1506871945259042,
+      "eval_loss": 63.51411056518555,
+      "eval_runtime": 6.8447,
+      "eval_samples_per_second": 18.262,
+      "eval_steps_per_second": 0.584,
       "step": 400
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.6106539368629456,
+      "grad_norm": 0.809869110584259,
       "learning_rate": 0.002038077610206693,
-      "loss": 57.197861328125,
+      "loss": 63.562841796875,
       "step": 500
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.15304692082111437,
-      "eval_loss": 56.594947814941406,
-      "eval_runtime": 6.936,
-      "eval_samples_per_second": 18.022,
-      "eval_steps_per_second": 0.577,
+      "eval_accuracy": 0.15301075268817205,
+      "eval_loss": 63.00912857055664,
+      "eval_runtime": 6.7809,
+      "eval_samples_per_second": 18.434,
+      "eval_steps_per_second": 0.59,
       "step": 500
     }
   ],