Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e2d1945f33a0479a7e90481176bdbd7100340e3993a91028772031f347ab3d
+oid sha256:5d396a718ea92c0c502a738a7cd20f3105f64ecde1cc6c8b159914db1aeeb87f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7271aa2941a2548577239c4c50d7bd0a2bd373245eb14dbd11930ffad541f2e
+oid sha256:19ebaebc2cb3cf1d83faf247ed509e3cef3d15dc4d748a02086960e095ae8f04
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1396f6ab0efb68e81bf65c8ab316623ba95c6a4e339af173bc25084fafa81f7f
+oid sha256:8e57417c00e90b24532d321646726159016c0cee76eaa6fb5b5ff3dcb743203d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005236698785085882,
+  "epoch": 0.0010473397570171764,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 0.8328,
       "step": 9
+    },
+    {
+      "epoch": 0.0006284038542103058,
+      "grad_norm": 0.3369526267051697,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.9986,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007855048177628823,
+      "grad_norm": 0.3511159121990204,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.9991,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008378718056137411,
+      "eval_loss": 0.8831256031990051,
+      "eval_runtime": 1327.855,
+      "eval_samples_per_second": 6.056,
+      "eval_steps_per_second": 3.028,
+      "step": 16
+    },
+    {
+      "epoch": 0.0009426057813154587,
+      "grad_norm": 0.3320366442203522,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9714,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7140665104269312.0,
+  "total_flos": 1.437406611898368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null