Training in progress, step 657000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46484171f9b6c5ac946d864e246abccda92dd4f25ee62ce6099d28cc729da487
+oid sha256:a709bb9b0b3c828f8b50355fccc149df56cd5cb7375483821c8238981190f88a
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86b09a69f43945d8bf2d66867995e93a245540aa345dcd0cd225e099d63d33e
+oid sha256:974538bed07bd80c498e8194c0b7cce0454bcf1e87696f84a11179198e2f301b
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:936cadd1d64a617d3c80546b4e9ae3b5969c939f4794ae3e639825fdaca492b9
+oid sha256:0ff2305055086f0b6360f4f51a015a13846329ab47afa029cfcf438d19aff04a
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9763dfb7cc467a3044703e2e59550f35dc18ba90b54d9372192d8a07f59078ce
+oid sha256:2b74d61c126edbf5148b356cd53fce0162983b4e7f65c357ac9a130843a11b7f
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da4e619cef69a82f65fefd8d8bf453d1ca59509aaa3224e842dd273c6e04dad3
+oid sha256:1872f0c0f09704c71b4597aab59c53404102ae5a68b0af6472e50532c123a280
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.143754390747713,
-  "global_step": 654000,
+  "epoch": 17.22239464826834,
+  "global_step": 657000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7854,11 +7854,47 @@
       "learning_rate": 2.485511429528359e-07,
       "loss": 1.0151,
       "step": 654000
+    },
+    {
+      "epoch": 17.16,
+      "learning_rate": 2.463229956273269e-07,
+      "loss": 1.0074,
+      "step": 654500
+    },
+    {
+      "epoch": 17.17,
+      "learning_rate": 2.4409992626537676e-07,
+      "loss": 1.0127,
+      "step": 655000
+    },
+    {
+      "epoch": 17.18,
+      "learning_rate": 2.4188641906152306e-07,
+      "loss": 1.0101,
+      "step": 655500
+    },
+    {
+      "epoch": 17.2,
+      "learning_rate": 2.3968688171094404e-07,
+      "loss": 1.0122,
+      "step": 656000
+    },
+    {
+      "epoch": 17.21,
+      "learning_rate": 2.374925077590484e-07,
+      "loss": 1.0292,
+      "step": 656500
+    },
+    {
+      "epoch": 17.22,
+      "learning_rate": 2.3530772397233141e-07,
+      "loss": 0.9995,
+      "step": 657000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.764147094555607e+17,
+  "total_flos": 7.797151420425585e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86b09a69f43945d8bf2d66867995e93a245540aa345dcd0cd225e099d63d33e
+oid sha256:974538bed07bd80c498e8194c0b7cce0454bcf1e87696f84a11179198e2f301b
 size 1944201353

runs/Jun05_15-52-52_cc80fbc5a73c/events.out.tfevents.1685980427.cc80fbc5a73c.10476.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8043880ae85a6e32e1326bf6b812681b2b5ebe8b05f856a8bc0415f862862253
-size 5421
+oid sha256:ee87d82742882942179150264ca9f1413c2de5123ccd5c9a216f75cf720f4ab0
+size 6381