Training in progress, step 585000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f1a48804678162ab3aecf919d1b706d10ef7258fab83c58318f53ff5a3fa94b
+oid sha256:800f47d6c105599f23476b36ba02ef6cd898b37ec9f6ea6c11464b383ba2cbd7
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ddb0d445df94c4cc297a21738ebeae7340f5cb1491611529b9010ef16e2285e
+oid sha256:ade14b8fcd7033799d31d7c0b3638db665d1101ba6c901b224e22e4630967f0f
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1be13f5c1447e7a1f0c568d6b3ce9d67f06043aea7e6a6adb6d516e1a9e08df
+oid sha256:d89a086ff98497212b3403fb71dd7cca09fd28ce2e72380eabd270a7198bf63d
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f64a459349cb576f0b208442db510e681babf73815faf743d1f75670b079e6
+oid sha256:8a56e5f53e3690fa8d88396102c5e72891424a69c9adf23f31ba1d7ae3b5bd5e
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0011f6c0eaad524da3d93ee2e4f36118921f7fbfc672d8200c6cde5159731c7
+oid sha256:dd7e558efc05c7857c55680cae30ef0a4d65e8d9cbb5e001241cc014941d7312
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.256356754149584,
-  "global_step": 582000,
+  "epoch": 15.334997011670215,
+  "global_step": 585000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6990,11 +6990,47 @@
       "learning_rate": 6.640749410559011e-07,
       "loss": 1.0248,
       "step": 582000
+    },
+    {
+      "epoch": 15.27,
+      "learning_rate": 6.605922514508042e-07,
+      "loss": 1.0305,
+      "step": 582500
+    },
+    {
+      "epoch": 15.28,
+      "learning_rate": 6.571103714792401e-07,
+      "loss": 1.0334,
+      "step": 583000
+    },
+    {
+      "epoch": 15.3,
+      "learning_rate": 6.536363030247672e-07,
+      "loss": 1.0313,
+      "step": 583500
+    },
+    {
+      "epoch": 15.31,
+      "learning_rate": 6.501700608130337e-07,
+      "loss": 1.0269,
+      "step": 584000
+    },
+    {
+      "epoch": 15.32,
+      "learning_rate": 6.467116595365149e-07,
+      "loss": 1.0397,
+      "step": 584500
+    },
+    {
+      "epoch": 15.33,
+      "learning_rate": 6.432680070962052e-07,
+      "loss": 1.0271,
+      "step": 585000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 6.971082996612465e+17,
+  "total_flos": 7.004102496447283e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ddb0d445df94c4cc297a21738ebeae7340f5cb1491611529b9010ef16e2285e
+oid sha256:ade14b8fcd7033799d31d7c0b3638db665d1101ba6c901b224e22e4630967f0f
 size 1944201353

runs/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae362c64a1320faae29882bc06c0bf84eeb1edd292e0baf069f637fc22f4975
-size 9261
+oid sha256:289f05ba23629ccf8a109c80a0479b07884acff653ab97fe91883a05fb591060
+size 10221