Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419459e5c5b30ebe4d60a6ba04f2f56b78a2a41d7de6a5b4df32a4eec4439d39
+oid sha256:5873d1383584948a3d38fae98287e1b387aad0d1ee8973b96120ec22a1cb4114
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71ba0298941760f1ee90ad0eb464f48dd8377069a494c105c18413039e68551
+oid sha256:8d04b9fb2eaa2d3722eb6c6b0b3735ed394aa7e72e0c71edc4b6e8ee3a768e6c
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e354f6de81f1a3a7506e26691225735f2d2057733b9018b9d2d7d93dda6a36
+oid sha256:c31810ad875dd7e946b118571d514f7b65886850eb7e803620def1b522979375
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
+oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20454545454545456,
+  "epoch": 0.3068181818181818,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 8.676,
       "eval_steps_per_second": 1.114,
       "step": 18
+    },
+    {
+      "epoch": 0.23863636363636365,
+      "grad_norm": 1.6107302904129028,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 2.6472,
+      "step": 21
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 1.6939775943756104,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 2.6063,
+      "step": 24
+    },
+    {
+      "epoch": 0.3068181818181818,
+      "grad_norm": 1.569953203201294,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 2.5102,
+      "step": 27
+    },
+    {
+      "epoch": 0.3068181818181818,
+      "eval_loss": 2.223207473754883,
+      "eval_runtime": 17.0516,
+      "eval_samples_per_second": 8.68,
+      "eval_steps_per_second": 1.114,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.124328290628403e+16,
+  "total_flos": 6.221444370608947e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null