Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa9ed56e6df15074fe06489feeb334ab6b27661c053ff3070db0d7c755944941
+oid sha256:2ad106a6741fcc7140bf2703855b87ba0005edcda6f3e322645cd84e39d1a599
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3efd8cd15c962e114eb55855131fec5ccd04c0360336e4606c9a4be07708671a
+oid sha256:573bd29d80e268738a043b87faddec9617e4624a19da6c040c2871530c69a301
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f681f1ec457af39e0ce158d1ac181ec2068f20d832e0736dfb63b3d9ef50b7d
+oid sha256:adef96fec1e64951031f99b379c4a942f776e813faab333e4035a6bb2f9ccc95
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d2e8fbf2c6f6693369261f0bc524b3fd101ab44636fee258ab2ed2faf1210d
+oid sha256:ad8befdc63df11e8e98cd226b6de6db77ab7781057363f64d1a63bc437d2cc05
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0425531914893615,
+  "epoch": 2.297872340425532,
   "eval_steps": 3,
-  "global_step": 24,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -135,6 +135,21 @@
       "eval_samples_per_second": 47.757,
       "eval_steps_per_second": 7.164,
       "step": 24
+    },
+    {
+      "epoch": 2.297872340425532,
+      "grad_norm": 2.8489627838134766,
+      "learning_rate": 2.6763841397811573e-05,
+      "loss": 2.2496,
+      "step": 27
+    },
+    {
+      "epoch": 2.297872340425532,
+      "eval_loss": 2.7331249713897705,
+      "eval_runtime": 0.4223,
+      "eval_samples_per_second": 47.356,
+      "eval_steps_per_second": 7.103,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -154,7 +169,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4804634958888960.0,
+  "total_flos": 5405214328750080.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null