Training in progress, step 28000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9436f8f8b607b1ee593a8f3b0b8b83e30fe390053f20fd17d06fad5fa1c3800
+oid sha256:72852881cb27f03d68aee156701d9ed4abca3e02139d1f3812166937936c6930
 size 3871543575

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6ca84a97e8c4a7948040e06ceceb51817c0b2cbd17f232026f4dbe0b459e8f
+oid sha256:ccfdfe1dd57bf2350531d07b5f6b9ea9f61b2ea739f511397abc3f3034b989bd
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8f258a77a5626bb48a10d9b85a8386b171d5dd6f4cd303281f19063ab68e5f
-size 14575
+oid sha256:4991eb3f924760cf4a9e1e172b7a6f137205a9c97add30e32a7b852475b57b1c
+size 14511

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f431083eeb6d9fc00bf62f51e90febacbb78f3e6a99dc9fc4278d2be5a055df8
+oid sha256:efb484ebd13275de377f305282b7e5e723e42ba1a1a11aeb0a9898c9fca5c12c
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4a6d62e8eba1babe503704efa95eb56e2c5e9222374877c14b70b7d65166a96
+oid sha256:303647ce6cd04dfc3f358ec168c62515611763039c425f1bf0082c6ae4113cb6
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6291220601650397,
-  "global_step": 24000,
+  "epoch": 0.733975736859213,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -294,11 +294,59 @@
       "learning_rate": 1.5149282428923398e-05,
       "loss": 1.3745,
       "step": 24000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.4211771280398977e-05,
+      "loss": 1.3667,
+      "step": 24500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3292548922523571e-05,
+      "loss": 1.3644,
+      "step": 25000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2393173670911351e-05,
+      "loss": 1.338,
+      "step": 25500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.1515170195285154e-05,
+      "loss": 1.3728,
+      "step": 26000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.0660026934773603e-05,
+      "loss": 1.3354,
+      "step": 26500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.82919357462835e-06,
+      "loss": 1.342,
+      "step": 27000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.024078588639035e-06,
+      "loss": 1.3398,
+      "step": 27500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.246046851412012e-06,
+      "loss": 1.3244,
+      "step": 28000
     }
   ],
   "max_steps": 38148,
   "num_train_epochs": 1,
-  "total_flos": 2.6437433869983744e+16,
+  "total_flos": 3.0843724697985024e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6ca84a97e8c4a7948040e06ceceb51817c0b2cbd17f232026f4dbe0b459e8f
+oid sha256:ccfdfe1dd57bf2350531d07b5f6b9ea9f61b2ea739f511397abc3f3034b989bd
 size 1944201353

runs/Jun18_17-52-03_85d30a282e1b/events.out.tfevents.1687112276.85d30a282e1b.283.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e58edc503b7e7e09ead300ec65b6ae8e84d0206ee2b89ccb7ed0d3fed326b214
-size 5742
+oid sha256:95b59199deca4c67e4efb69b372b3968be640ed5eb995cd37ecb0b21502dbdc1
+size 7022