Training in progress, step 51, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa72c69e81bba821cc4c73a7f7844bf111cb1b22c425a42f8940d2a620786f87
+oid sha256:6c40abc5ddbc8cce4c38252033f65546ef0ed695d12c0979ab0e6e53b8ddff3d
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc66b34c385cd244db2547d4c348b3df1eb8dc43f9577663661efef47fbad88
+oid sha256:6131a0b83a062e037bac2e68d74d4a9c1690df55d265b19520f04c71f8c51943
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8401f39bd167cf8ab44ce58e7de9c3739721eec7ba9360b71bc778d12332a672
+oid sha256:f7bd16cd408bd3dd2676b8823dfc63738eec458eb445f09c19422fb33f5a1acb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af27ed5b5e5c3013f1da7a97e494138e751399ceff1f8e7486b6e269bc7092f
+oid sha256:a9fa892ecd236e652150058649b13d9161331d85e374c4bec1d60ad6a556c3a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02568945976577257,
+  "epoch": 0.03853418964865886,
   "eval_steps": 17,
-  "global_step": 34,
+  "global_step": 51,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -108,6 +108,56 @@
       "eval_samples_per_second": 36.079,
       "eval_steps_per_second": 4.514,
       "step": 34
+    },
+    {
+      "epoch": 0.02720060445787684,
+      "grad_norm": 0.013970930129289627,
+      "learning_rate": 9.545032675245813e-05,
+      "loss": 12.4541,
+      "step": 36
+    },
+    {
+      "epoch": 0.029467321496033247,
+      "grad_norm": 0.014797762967646122,
+      "learning_rate": 9.43611409721806e-05,
+      "loss": 12.4476,
+      "step": 39
+    },
+    {
+      "epoch": 0.03173403853418965,
+      "grad_norm": 0.01638209819793701,
+      "learning_rate": 9.316282404787871e-05,
+      "loss": 12.4498,
+      "step": 42
+    },
+    {
+      "epoch": 0.03400075557234605,
+      "grad_norm": 0.017414981499314308,
+      "learning_rate": 9.185832391312644e-05,
+      "loss": 12.4489,
+      "step": 45
+    },
+    {
+      "epoch": 0.036267472610502456,
+      "grad_norm": 0.01976948417723179,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 12.4498,
+      "step": 48
+    },
+    {
+      "epoch": 0.03853418964865886,
+      "grad_norm": 0.017705973237752914,
+      "learning_rate": 8.894386393810563e-05,
+      "loss": 12.4478,
+      "step": 51
+    },
+    {
+      "epoch": 0.03853418964865886,
+      "eval_loss": 12.449511528015137,
+      "eval_runtime": 61.8317,
+      "eval_samples_per_second": 36.066,
+      "eval_steps_per_second": 4.512,
+      "step": 51
     }
   ],
   "logging_steps": 3,
@@ -127,7 +177,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 73987522560.0,
+  "total_flos": 111289565184.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null