Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038ff60f7ce575aef87ad3c4893b783b82185d2482a8fae2b7715b75303456ed
+oid sha256:611eb546c4213a33a191de2af6f0e9be0eb59bbc9b57f2d2a3596c176b932d95
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c152cd374b66112691af4095b77b1614ac3b3275e7feb9208f29401f5fad969
+oid sha256:7a19512af0d064526955708988a05200050292d802901635ddabf7d444826a1e
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7f0fe58f20a3ab677d7ee18585b766c1ac2de0b05dc8f10b3f865fe4417547
+oid sha256:1daf813549d6191a658ca47468b077c3487cd48e02216803f471e9a5adc4df2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12560386473429952,
+  "epoch": 0.25120772946859904,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 240.952,
       "eval_steps_per_second": 30.378,
       "step": 10
+    },
+    {
+      "epoch": 0.1932367149758454,
+      "grad_norm": 11.83459186553955,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 8.7933,
+      "step": 20
+    },
+    {
+      "epoch": 0.1932367149758454,
+      "eval_loss": 8.16073226928711,
+      "eval_runtime": 2.9153,
+      "eval_samples_per_second": 239.423,
+      "eval_steps_per_second": 30.185,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 23404400345088.0,
+  "total_flos": 47464386134016.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null