Training in progress, step 190000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5acc2861e7396e81698a045ce779c528c1589b7b78bde65686da82c4408ddb
+oid sha256:a79698e8ce41155df8f2ac96cd99d16ef6b016cb4ff277c5445301a3db1fa101
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48649d1b881cb101c25c27c14decb38dce780e3aea5787ee35216eccf1c8fd9
+oid sha256:16799df5e196079b65225695fe6105fc300cf5157671e1537af93401d1b8d74a
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd995b6d6c5baa6e5ed73d97b87a49724ad2e0d0f8e35c78d6e562318a4660ea
+oid sha256:8d372c7ec90718e7e982db780f8d7b62ea26c5068bb213efc91ce4e4dbff2188
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6650ce86ed3c7c5c7fbe55b75f320b30724b552ef56b063389bed584cfcfd3a4
-size 14439
+oid sha256:200bd99b77ad19fc80e27fc902aca5e36eebe6570a18efbc020b994d75bc6fba
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca377902b93ec16a61eb5ef6b00da3d0b2f00ee9310c5dd7863b3027def19ecc
+oid sha256:c0f78dbe211932d0c37e15c11f906dcb55aae5aedb42250507005f499cf4150e
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0979b9f8cf08248ef7cf31dc7f9e5488be3d1a638741d1d3e358d69c0f25d13d
+oid sha256:fb7cd6974be7a03bcf0342d3707956fc7f1e60ef89c3b2bd3445ff8c5a29e4db
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdbc1873940bd05dec6fa8ddeee78ddbd4cf0afa60b7658d7e729096721589da
+oid sha256:4347385b2c0f1e2d9aeca7fb88e1c942d1dae99e52563bdfa6c48a7a4a2bf97f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7486371340876814,
-  "global_step": 180000,
+  "epoch": 2.9013391970925526,
+  "global_step": 190000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1338,11 +1338,85 @@
       "eval_samples_per_second": 983.42,
       "eval_steps_per_second": 15.735,
       "step": 180000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 0.00014353363063128005,
+      "loss": 0.3183,
+      "step": 181000
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 0.0001434361090155131,
+      "loss": 0.3177,
+      "step": 182000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 0.00014333789367262136,
+      "loss": 0.3178,
+      "step": 183000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.00014323898567667202,
+      "loss": 0.3177,
+      "step": 184000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.00014313938610930712,
+      "loss": 0.3171,
+      "step": 185000
+    },
+    {
+      "epoch": 2.82,
+      "eval_runtime": 1.0441,
+      "eval_samples_per_second": 957.721,
+      "eval_steps_per_second": 15.324,
+      "step": 185000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.00014303909605973154,
+      "loss": 0.3167,
+      "step": 186000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.0001429381166247012,
+      "loss": 0.3168,
+      "step": 187000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 0.00014283644890851103,
+      "loss": 0.3164,
+      "step": 188000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00014273409402298291,
+      "loss": 0.3161,
+      "step": 189000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.00014263105308745343,
+      "loss": 0.3155,
+      "step": 190000
+    },
+    {
+      "epoch": 2.9,
+      "eval_runtime": 1.0119,
+      "eval_samples_per_second": 988.212,
+      "eval_steps_per_second": 15.811,
+      "step": 190000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.261803384409951e+22,
+  "total_flos": 1.3319036454402982e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48649d1b881cb101c25c27c14decb38dce780e3aea5787ee35216eccf1c8fd9
+oid sha256:16799df5e196079b65225695fe6105fc300cf5157671e1537af93401d1b8d74a
 size 449471589