Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f880a4e1745d49b7c45949a05153ccf8f4b045a811d84958cd4abc00fac67dbd
+oid sha256:aa9ed56e6df15074fe06489feeb334ab6b27661c053ff3070db0d7c755944941
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65e185024af1ce05fbcb06b6e277c2b33368b7855ab77859f026375accaec2a
+oid sha256:3efd8cd15c962e114eb55855131fec5ccd04c0360336e4606c9a4be07708671a
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99829502e75e5e0810e799113406f096b1811b4de5e7bf230e8c2ba6819dcef
+oid sha256:6f681f1ec457af39e0ce158d1ac181ec2068f20d832e0736dfb63b3d9ef50b7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83450c18b224a87d74f8c8e7d50fafb72f4e677fe1089fb566389ff9d23f9b65
+oid sha256:b8d2e8fbf2c6f6693369261f0bc524b3fd101ab44636fee258ab2ed2faf1210d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7872340425531914,
+  "epoch": 2.0425531914893615,
   "eval_steps": 3,
-  "global_step": 21,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,21 @@
       "eval_samples_per_second": 48.098,
       "eval_steps_per_second": 7.215,
       "step": 21
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 3.6542279720306396,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 2.8825,
+      "step": 24
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "eval_loss": 2.7445950508117676,
+      "eval_runtime": 0.4188,
+      "eval_samples_per_second": 47.757,
+      "eval_steps_per_second": 7.164,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -139,7 +154,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4204055589027840.0,
+  "total_flos": 4804634958888960.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null