Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e018a196e11e9728021449b82e7214a32c0d53e48e4487bdf835eeaacaf4e76
+oid sha256:69ca6905e70e7a92d02eeddbdeb7103009b83d9f0f234789efb4904d68ed5838
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351028c2121581b19074f8296d27ae228170a1a469e41080403091bd2454dea0
+oid sha256:82cc3acf680d85a95964b4366417613a590457a2020ce3a7574762bb50f5df4d
 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": 0.7302449345588684,
+      "grad_norm": 1.0674346685409546,
       "learning_rate": 0.003920764340590609,
-      "loss": 67.6101513671875,
+      "loss": 59.4722705078125,
       "step": 100
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.14093548387096774,
-      "eval_loss": 62.60755157470703,
-      "eval_runtime": 22.8701,
-      "eval_samples_per_second": 5.466,
-      "eval_steps_per_second": 0.175,
+      "eval_accuracy": 0.14505767350928642,
+      "eval_loss": 57.5521240234375,
+      "eval_runtime": 23.0144,
+      "eval_samples_per_second": 5.431,
+      "eval_steps_per_second": 0.174,
       "step": 100
     },
     {
       "epoch": 0.2,
-      "grad_norm": 0.8270155787467957,
+      "grad_norm": 0.8365403413772583,
       "learning_rate": 0.003650943793925548,
-      "loss": 61.0553955078125,
+      "loss": 57.0307275390625,
       "step": 200
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.14555327468230694,
-      "eval_loss": 59.78960418701172,
-      "eval_runtime": 7.035,
-      "eval_samples_per_second": 17.768,
-      "eval_steps_per_second": 0.569,
+      "eval_accuracy": 0.14682111436950146,
+      "eval_loss": 56.763153076171875,
+      "eval_runtime": 6.889,
+      "eval_samples_per_second": 18.145,
+      "eval_steps_per_second": 0.581,
       "step": 200
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.6493133306503296,
+      "grad_norm": 0.6420626044273376,
       "learning_rate": 0.0032162636906540357,
-      "loss": 58.9980078125,
+      "loss": 56.4287109375,
       "step": 300
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.15011827956989246,
-      "eval_loss": 58.25105285644531,
-      "eval_runtime": 6.9492,
-      "eval_samples_per_second": 17.988,
-      "eval_steps_per_second": 0.576,
+      "eval_accuracy": 0.15105865102639296,
+      "eval_loss": 56.29315185546875,
+      "eval_runtime": 7.4741,
+      "eval_samples_per_second": 16.724,
+      "eval_steps_per_second": 0.535,
       "step": 300
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.5908206105232239,
+      "grad_norm": 0.6022240519523621,
       "learning_rate": 0.0026601302141692667,
-      "loss": 57.7524462890625,
+      "loss": 56.0290380859375,
       "step": 400
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.15085630498533725,
-      "eval_loss": 57.304725646972656,
-      "eval_runtime": 6.82,
-      "eval_samples_per_second": 18.329,
-      "eval_steps_per_second": 0.587,
+      "eval_accuracy": 0.1521642228739003,
+      "eval_loss": 55.97286605834961,
+      "eval_runtime": 6.9186,
+      "eval_samples_per_second": 18.067,
+      "eval_steps_per_second": 0.578,
       "step": 400
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.6619788408279419,
+      "grad_norm": 0.6007410287857056,
       "learning_rate": 0.002038077610206693,
-      "loss": 57.25951171875,
+      "loss": 56.0603759765625,
       "step": 500
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.15302541544477027,
-      "eval_loss": 56.62392807006836,
-      "eval_runtime": 6.8533,
-      "eval_samples_per_second": 18.239,
-      "eval_steps_per_second": 0.584,
+      "eval_accuracy": 0.15361681329423266,
+      "eval_loss": 55.698612213134766,
+      "eval_runtime": 6.7281,
+      "eval_samples_per_second": 18.579,
+      "eval_steps_per_second": 0.595,
       "step": 500
     }
   ],