Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4aefb26bd3197fa8a1f24085c1a32f98df41e5904e44081aab060847a5672a
+oid sha256:94e6a3b73cb956a7db5ce63e3bfe48d3171d32dc6cc6b7543b3a5d81aa845bc3
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488d85bc60101bc276735d86e3e063ea0b21fa18ad7d4bd09206e203054ba5fa
+oid sha256:c8b6177cbdd8a6fc64bb45c8b168aff804c62abd82a2114553cb0b80d6f246ce
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8532b81b442a52e7641152d52819f99f24bb427b98bc8d1a82e25a081ba985ff
+oid sha256:295f0a621346f38e97a347d06bb9927816fe04926f6efca6f6b2fe56f30407d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14311270125223613,
+  "epoch": 0.17889087656529518,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 11.055,
       "eval_steps_per_second": 1.405,
       "step": 20
+    },
+    {
+      "epoch": 0.15026833631484796,
+      "grad_norm": 21.97161293029785,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.3563,
+      "step": 21
+    },
+    {
+      "epoch": 0.17173524150268335,
+      "grad_norm": 2.182478666305542,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.2626,
+      "step": 24
+    },
+    {
+      "epoch": 0.17889087656529518,
+      "eval_loss": 0.041570138186216354,
+      "eval_runtime": 21.352,
+      "eval_samples_per_second": 11.053,
+      "eval_steps_per_second": 1.405,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.661017318326272e+16,
+  "total_flos": 3.32627164790784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null