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:ef9f4b836c02afd7ed1c180ab6cce99bb10b41d1924ff812d5a431150f649e0f
+oid sha256:5562758958d9c933df9464f619411fbe8ae1fa318035e8e7b577ad7320578083
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df86b5cb7ff5258ef8eebaa3e2bd8cf5c49f0c219eef989ba0db413622b6b185
+oid sha256:52122d9880c312c52c04a4ed74ac97875df71512027cc21be7a99f17f5964c1e
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6191367ab70dbb5534bf3c80f01e5a4ca78e25ec0c46e08a50a21a04fffcc593
+oid sha256:f57a98a96269463c4f3b5283c3eb0ad90dcda650b9e164cba692d068abf2b1bc
 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": 0.013169125716376053,
+  "epoch": 0.017558834288501402,
   "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": 12.154,
       "eval_steps_per_second": 1.521,
       "step": 27
+    },
+    {
+      "epoch": 0.014632361907084501,
+      "grad_norm": 0.6314910054206848,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.7935,
+      "step": 30
+    },
+    {
+      "epoch": 0.016095598097792953,
+      "grad_norm": 0.3279048800468445,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.823,
+      "step": 33
+    },
+    {
+      "epoch": 0.017558834288501402,
+      "grad_norm": 0.4065856635570526,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.8136,
+      "step": 36
+    },
+    {
+      "epoch": 0.017558834288501402,
+      "eval_loss": 0.7961127161979675,
+      "eval_runtime": 284.0262,
+      "eval_samples_per_second": 12.157,
+      "eval_steps_per_second": 1.521,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.299087963960115e+16,
+  "total_flos": 5.802021154612838e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null