Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab1af3989a3cb0ef17441134c6d9115d239c28d341121ec54ddc157bc80ca31
+oid sha256:7f9ae7e86bbc77dbce22ca2c90f22880719186ccf1df5b938440f4fba479e8f8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee7fd58185a25f322d89f31ab1205c29d56ebbe0608d01fbd4ed1810b096d21d
+oid sha256:68f073df4c55287ce71ca924a294e38b1ab7cc164a34073772713039d245568f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8142adb50de721c312198118970172331afa1dd03733dddae1b8e58019f13418
+oid sha256:343cbf433a49823c26aa4dd9334fa3e204370732996c7bb60db1a7158c5badde
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0999afe033f75d8bd9448190d8bb949c5c3397cd764ae214dd958ddb75be8cfe
+oid sha256:86b8133c0078c9773a22c7a49b5547dc88d96e16d710eff8078381e482ecc029
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.766417290108063,
+  "epoch": 1.8703241895261846,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -134,6 +134,13 @@
       "learning_rate": 8.229426433915213e-06,
       "loss": 0.355,
       "step": 8500
+    },
+    {
+      "epoch": 1.8703241895261846,
+      "grad_norm": 0.8178287148475647,
+      "learning_rate": 7.536713771127737e-06,
+      "loss": 0.3492,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -153,7 +160,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.035167518162944e+16,
+  "total_flos": 1.096063307218944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null