Training in progress, step 660000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a709bb9b0b3c828f8b50355fccc149df56cd5cb7375483821c8238981190f88a
+oid sha256:c13a1aabb55645ee7d8c9a39cabd5e3e69e05fa709ca2239844b15bdd30302d5
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974538bed07bd80c498e8194c0b7cce0454bcf1e87696f84a11179198e2f301b
+oid sha256:8b6424ffbfec0c9949ea3ff6f9d6b5e679bcfec47db34c19a76c19d60c5c035e
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff2305055086f0b6360f4f51a015a13846329ab47afa029cfcf438d19aff04a
+oid sha256:48456504425e2a16ea8cb0437d989984020206f6effe31410687734a003ad2d9
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b74d61c126edbf5148b356cd53fce0162983b4e7f65c357ac9a130843a11b7f
+oid sha256:cd9b4bca6bd83b006db8937c0610ee297003c2866f42e0f8719ca89654449c3e
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1872f0c0f09704c71b4597aab59c53404102ae5a68b0af6472e50532c123a280
+oid sha256:198a0ebe3caffa0ab0c1c5d4dffacfd0299f7ae8b7e248bd062c8fdead171625
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.22239464826834,
-  "global_step": 657000,
+  "epoch": 17.30103490578897,
+  "global_step": 660000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7890,11 +7890,47 @@
       "learning_rate": 2.3530772397233141e-07,
       "loss": 0.9995,
       "step": 657000
+    },
+    {
+      "epoch": 17.24,
+      "learning_rate": 2.3313253961150916e-07,
+      "loss": 1.0093,
+      "step": 657500
+    },
+    {
+      "epoch": 17.25,
+      "learning_rate": 2.3096696389660693e-07,
+      "loss": 1.0065,
+      "step": 658000
+    },
+    {
+      "epoch": 17.26,
+      "learning_rate": 2.2881100600692208e-07,
+      "loss": 1.0142,
+      "step": 658500
+    },
+    {
+      "epoch": 17.27,
+      "learning_rate": 2.2666467508098367e-07,
+      "loss": 1.021,
+      "step": 659000
+    },
+    {
+      "epoch": 17.29,
+      "learning_rate": 2.2453224398342994e-07,
+      "loss": 1.0065,
+      "step": 659500
+    },
+    {
+      "epoch": 17.3,
+      "learning_rate": 2.22405174938064e-07,
+      "loss": 1.0271,
+      "step": 660000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.797151420425585e+17,
+  "total_flos": 7.830074924298732e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974538bed07bd80c498e8194c0b7cce0454bcf1e87696f84a11179198e2f301b
+oid sha256:8b6424ffbfec0c9949ea3ff6f9d6b5e679bcfec47db34c19a76c19d60c5c035e
 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:ee87d82742882942179150264ca9f1413c2de5123ccd5c9a216f75cf720f4ab0
-size 6381
+oid sha256:e7e9f325eeaeaf12223f32ad9a86ae8a0e517d344ae4db4045e42288c209c342
+size 7341