Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9acb7ab00f4d82234b1082eb6729c8d40ba40ea72e0c2c75225b37b3f09b8bff
+oid sha256:a0c04e58296af2a060e96e7af5d33501c7f2576ba0c8112dd196ee9e7ce82725
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fdcbab62b17dc3ca6967bd656ae0a2c88c143024a79d747c4227ddbe4ebbe60
+oid sha256:3922ac8e48f30131f7e4098ab7e87bf40a368bfa72614678efd9fc5f2b9d2471
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6758c94dff08e90104766708e33ff8cbf1018bfc9134136ef3e1f7d88a92f7
+oid sha256:9f823b57963be51e31620f99c418f4a772969cb6e0504382964ebddd1b207eaa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6666666666666666,
+  "epoch": 0.8888888888888888,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 68.595,
       "eval_steps_per_second": 8.947,
       "step": 27
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.14867456257343292,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 2.1073,
+      "step": 30
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.20560601353645325,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 2.1231,
+      "step": 33
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.20878741145133972,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 2.1412,
+      "step": 36
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 2.027235746383667,
+      "eval_runtime": 1.0148,
+      "eval_samples_per_second": 67.995,
+      "eval_steps_per_second": 8.869,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1716310266347520.0,
+  "total_flos": 2288413688463360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null