Training in progress, step 180000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9a70132918b6ab165a91d577d712613356dca52075d5c7c05f34314005b476
+oid sha256:6f5acc2861e7396e81698a045ce779c528c1589b7b78bde65686da82c4408ddb
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e4608999d97a58a30e39361b70b419f5aef3e2535ed3ca55c26e98dfa526a2
+oid sha256:d48649d1b881cb101c25c27c14decb38dce780e3aea5787ee35216eccf1c8fd9
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef92b44093f62f1441b173acbe3fd1139e94c5c223ed6a54381a9d3cb2f5c022
+oid sha256:bd995b6d6c5baa6e5ed73d97b87a49724ad2e0d0f8e35c78d6e562318a4660ea
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:161efcaf59347006251947d35ba8e577aead293e95ee199281ec31fb424a8671
-size 14503
+oid sha256:6650ce86ed3c7c5c7fbe55b75f320b30724b552ef56b063389bed584cfcfd3a4
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b4db0eb85867b5e22ab5799a8329f0f5930ac32c5205c1b81fbef9bb0ad0ab
-size 14439
+oid sha256:ca377902b93ec16a61eb5ef6b00da3d0b2f00ee9310c5dd7863b3027def19ecc
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9a9a05da89d28b0f8404cc60f79e71945e2a52c47886846fb03eae29b9b7e7
+oid sha256:0979b9f8cf08248ef7cf31dc7f9e5488be3d1a638741d1d3e358d69c0f25d13d
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e6e6dbb6845e268a54a5a558c86918603b34b6bae9a32a1510a924b34f03635
+oid sha256:cdbc1873940bd05dec6fa8ddeee78ddbd4cf0afa60b7658d7e729096721589da
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.59593507108281,
-  "global_step": 170000,
+  "epoch": 2.7486371340876814,
+  "global_step": 180000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1264,11 +1264,85 @@
       "eval_samples_per_second": 850.656,
       "eval_steps_per_second": 13.611,
       "step": 170000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.00014447046094149437,
+      "loss": 0.3221,
+      "step": 171000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.00014437993399594003,
+      "loss": 0.3216,
+      "step": 172000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 0.0001442887030017421,
+      "loss": 0.3217,
+      "step": 173000
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 0.00014419676895658807,
+      "loss": 0.3208,
+      "step": 174000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.000144104132865854,
+      "loss": 0.3207,
+      "step": 175000
+    },
+    {
+      "epoch": 2.67,
+      "eval_runtime": 1.0679,
+      "eval_samples_per_second": 936.423,
+      "eval_steps_per_second": 14.983,
+      "step": 175000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.0001440107957425933,
+      "loss": 0.3203,
+      "step": 176000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0001439167586075258,
+      "loss": 0.3201,
+      "step": 177000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 0.0001438220224890265,
+      "loss": 0.3191,
+      "step": 178000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 0.00014372658842311449,
+      "loss": 0.3195,
+      "step": 179000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.00014363045745344137,
+      "loss": 0.3191,
+      "step": 180000
+    },
+    {
+      "epoch": 2.75,
+      "eval_runtime": 1.0169,
+      "eval_samples_per_second": 983.42,
+      "eval_steps_per_second": 15.735,
+      "step": 180000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.191703123379604e+22,
+  "total_flos": 1.261803384409951e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e4608999d97a58a30e39361b70b419f5aef3e2535ed3ca55c26e98dfa526a2
+oid sha256:d48649d1b881cb101c25c27c14decb38dce780e3aea5787ee35216eccf1c8fd9
 size 449471589