Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae73e520bc2500ddf5da5f37cb2f38dda3b758de36f0997a1f83cbfa19b9152a
+oid sha256:58321af00ea50434f9ed928638ec24bf53f41fe3ebe7b31471622022c97978e0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c3841ac53915f1f4bb87e806aa949dbb01976f0d807968d05089029bf2add94
+oid sha256:5e374ce492e1948645280441e581102c3ec1143bb1c58145bd2d7b176a73b6d5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
+oid sha256:aae8d4065d911ba11f2f51fe3d3db409db35e37fa178d3f4d6e23c646987dad6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:95758e6aadaa863940ee26d7d4bc2716664c72b77251097ec968b5c9819c88ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09345794392523364,
+  "epoch": 0.11682242990654206,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,28 @@
       "learning_rate": 9.372094804706867e-05,
       "loss": 2.0835,
       "step": 18
+    },
+    {
+      "epoch": 0.09813084112149532,
+      "grad_norm": 0.9645207524299622,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.2096,
+      "step": 21
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 0.9482259154319763,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.1528,
+      "step": 24
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "eval_loss": 2.0866520404815674,
+      "eval_runtime": 11.8434,
+      "eval_samples_per_second": 7.684,
+      "eval_steps_per_second": 3.884,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -92,7 +114,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 9273591044505600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null