Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9889b903d1a84241f6de9a4633a5a74580871e06fcf56c7242ee68563b54e1f0
+oid sha256:78dd4f12f6998113698840d8eaf04bac190de6b55536950086553d622c583a81
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e97f68af56ded89a7904b7fde8cb57af9f3ba0b07a55980472ce040e65407
+oid sha256:48ddd0b07e329d5e2b72b151a14804fc919f97b0490e6d34168d1c9fd12d6ac6
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323eed6e808e7833f72c9c158993f7f51694aa2d568e26d624f9902a8b7f9ab0
+oid sha256:9ea003e731d402dcd02d2b25f1d347e30dc40ca30e38ec4f49bf97814daa069e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03761755485893417,
+  "epoch": 0.050156739811912224,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 13.488,
       "eval_steps_per_second": 1.686,
       "step": 15
+    },
+    {
+      "epoch": 0.045141065830721,
+      "grad_norm": 0.4628920555114746,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.663,
+      "step": 18
+    },
+    {
+      "epoch": 0.050156739811912224,
+      "eval_loss": 1.6090316772460938,
+      "eval_runtime": 49.8182,
+      "eval_samples_per_second": 13.489,
+      "eval_steps_per_second": 1.686,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0522955964416e+16,
+  "total_flos": 2.7251793985536e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null