Training in progress, step 308000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51adf105e6f6a7ed906d29c700a302ed25a5f3762591fb828115de3db85e6428
+oid sha256:ddf091d92150b410454884a8c91e3dc226a132fe10d71fb8400cd7ece97a3584
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e99f73129aa9790926d7e259881eb34dc636e42b1b114ed72b764955661475
+oid sha256:8be19f438c7d67d61cf13256a49ed3ad7b46df9e3dda94737360d2c52009aefe
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8a5728e1af3d048775ed91e97081b2078f2ef02825d44e2a1d3ed6f1e431ea
+oid sha256:f304ed8d96fda4e4ad2231633dc62d1a96263c09cf492c47dd305b371e921107
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5ef81669a76b9bc8adaca72bc010d0d224d425bd06e93da371512f70d617c1a
+oid sha256:409cb0b4e16b85c147bedb9d008c639c7e921681e7144237e971640eac06da7e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9616,
+  "epoch": 1.9712,
   "eval_steps": 500,
-  "global_step": 306500,
+  "global_step": 308000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4298,6 +4298,27 @@
       "learning_rate": 9.780799999999999e-07,
       "loss": 0.2434,
       "step": 306500
+    },
+    {
+      "epoch": 1.9647999999999999,
+      "grad_norm": 0.5600497722625732,
+      "learning_rate": 8.980800000000001e-07,
+      "loss": 0.2456,
+      "step": 307000
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 0.46547964215278625,
+      "learning_rate": 8.1808e-07,
+      "loss": 0.2467,
+      "step": 307500
+    },
+    {
+      "epoch": 1.9712,
+      "grad_norm": 0.5435817241668701,
+      "learning_rate": 7.380800000000001e-07,
+      "loss": 0.25,
+      "step": 308000
     }
   ],
   "logging_steps": 500,
@@ -4317,7 +4338,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.49316474765312e+18,
+  "total_flos": 1.50047224233984e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null