Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21bb5787ad12db0ae79cd5dda71719177f2d5b43a98d5d6de1efaa680c2747f9
+oid sha256:8f983cb2a5f612e326031e443873d48711cb94e10592cf1d65c72712da0ea605
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95af512bdd81b6ef46441e0fa0b4e9a12072266814772e12cdd9f061e9284d34
+oid sha256:a37ae8e651a837336ce84cccd145fd48dba2dfc770f3ec3406d986b2022d5b56
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148f1afbe85e53f6df3756a21f8a0ab665094392e08503828b5e3a1004bdf711
+oid sha256:f33fbf0dd2fa93f33d420c86701ae4a65abf42d9f472aa29c65ae1f2d0d73758
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03005780346820809,
+  "epoch": 0.04508670520231214,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 36.196,
       "eval_steps_per_second": 18.148,
       "step": 26
+    },
+    {
+      "epoch": 0.03468208092485549,
+      "grad_norm": 31.6507511138916,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 9.2891,
+      "step": 30
+    },
+    {
+      "epoch": 0.04508670520231214,
+      "eval_loss": 2.3214426040649414,
+      "eval_runtime": 10.0582,
+      "eval_samples_per_second": 36.289,
+      "eval_steps_per_second": 18.194,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4366878732189696.0,
+  "total_flos": 6611536024436736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null