Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6192a9c2546cd366def15b8e3ffdb7b09e06f7134e055f1fed6e4d1a85f16f
+oid sha256:260a7f3a222986a8a1c4b4b4af984295c40dfdc8229c1dd37b8459df7420961c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562358bc10f69c18c0962b7ef9313b9a4d93e89c8585e149a15b75ea36c88556
+oid sha256:36bd524b5f423471f1256f9d5a97610eccfe8b45ce85481fda9c1e46a6cd322b
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed78873d9b5732a5ff32f9ceeec3e0fdc3bc384e03b093710d735de66f42854
+oid sha256:8223884a837947fbfec558cb58e812c4074552a4c58d626bdabb079dd579f77a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008918249380677127,
+  "epoch": 0.00990916597853014,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 12.913,
       "eval_steps_per_second": 1.615,
       "step": 81
+    },
+    {
+      "epoch": 0.009248554913294798,
+      "grad_norm": 0.036499105393886566,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.002,
+      "step": 84
+    },
+    {
+      "epoch": 0.009578860445912468,
+      "grad_norm": 0.19988898932933807,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.0006,
+      "step": 87
+    },
+    {
+      "epoch": 0.00990916597853014,
+      "grad_norm": 0.11661279201507568,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.0005,
+      "step": 90
+    },
+    {
+      "epoch": 0.00990916597853014,
+      "eval_loss": 0.004694274626672268,
+      "eval_runtime": 1184.8106,
+      "eval_samples_per_second": 12.911,
+      "eval_steps_per_second": 1.615,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2234467289386189e+17,
+  "total_flos": 1.350010183656407e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null