Training in progress, step 207, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ba56438d71babce489f788f74e8baac21791812e354d7542958558e28a5b09
+oid sha256:28d58b44db21cf25ba64ac1c27e6f1bb7784ee0a02ac931b01d36f76f3220387
 size 535971781

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578030cef8b7c5c69af6edf07508bd8fbd30dd15bd17675223747e37eae63b73
+oid sha256:c504f83aad7d0a302af9e29bf917ae3d98fef0c854c77f7a243e352e62aa8270
 size 267978033

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87e04e7d234747e7e919c5e789170752456573555547e3deeb923883bc8fb68
+oid sha256:9c0cc7cef5fa73d93c76289cba5b5ec53161a70d5a31f0a11bb51c131c5a0f9a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d1ed32e9c64dc8043e49a394f10417bfc59f6bbabc5ffbdc0900311f4a833f
+oid sha256:0ac9980dd115ceed587e7cac8192a9802f0556a44357dfa4f0585a55038b5273
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10267857142857142,
+  "epoch": 0.9241071428571429,
   "eval_steps": 500,
-  "global_step": 23,
+  "global_step": 207,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -13,13 +13,67 @@
       "learning_rate": 4.5535714285714286e-05,
       "loss": 5.2623,
       "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.107142857142857e-05,
+      "loss": 4.7292,
+      "step": 40
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.6607142857142853e-05,
+      "loss": 4.0834,
+      "step": 60
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.2142857142857144e-05,
+      "loss": 4.3913,
+      "step": 80
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.767857142857143e-05,
+      "loss": 4.0595,
+      "step": 100
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3214285714285715e-05,
+      "loss": 3.9562,
+      "step": 120
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 4.0609,
+      "step": 140
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 4.3562,
+      "step": 160
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.821428571428573e-06,
+      "loss": 4.0136,
+      "step": 180
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 3.8597,
+      "step": 200
     }
   ],
   "logging_steps": 20,
   "max_steps": 224,
   "num_train_epochs": 1,
   "save_steps": 23,
-  "total_flos": 195130021773312.0,
+  "total_flos": 1756170195959808.0,
   "trial_name": null,
   "trial_params": null
 }