Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61996341056c0dabfab719a24657f6be2c1701f6ab89a6b0227572c4e5cbfd87
+oid sha256:1aee6814908f60d28f3e5fcc332554daab1d81bbd0d9381a2818cf428f91a055
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ff81c602eef2b9aea49d39e2dc2325b032b26045cd7cdfca451de5e4ca8984
+oid sha256:c23cd49c0107bd85eef33672afcfbfae97e1304bb32ad1839126632c6ab5c754
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b632b832bdc839a1f87f2b54a86c7465bc00e10f4d1d0eef845b6f6921a2856e
+oid sha256:d5fa5a15dacc246c77ef90ba7e7896379953025d6077daf340f31bc19decacb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002153576956726563,
+  "epoch": 0.0032303654350898446,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 8.368,
       "eval_steps_per_second": 4.187,
       "step": 8
+    },
+    {
+      "epoch": 0.0024227740763173833,
+      "grad_norm": 6.028713226318359,
+      "learning_rate": 0.00018,
+      "loss": 4.9807,
+      "step": 9
+    },
+    {
+      "epoch": 0.0026919711959082038,
+      "grad_norm": 3.5283517837524414,
+      "learning_rate": 0.0002,
+      "loss": 4.4461,
+      "step": 10
+    },
+    {
+      "epoch": 0.002961168315499024,
+      "grad_norm": 3.948577880859375,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 4.0834,
+      "step": 11
+    },
+    {
+      "epoch": 0.0032303654350898446,
+      "grad_norm": 3.531851053237915,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 4.6573,
+      "step": 12
+    },
+    {
+      "epoch": 0.0032303654350898446,
+      "eval_loss": 4.350089073181152,
+      "eval_runtime": 186.8405,
+      "eval_samples_per_second": 8.376,
+      "eval_steps_per_second": 4.191,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6135154892341248.0,
+  "total_flos": 9202732338511872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null