Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4410422f6ed56264c7b58a32a13df93b360aca3a5dd60a4019df0badc2359c7d
+oid sha256:57d231be0f26d449a05d403120d382651408877abb6a5f2c8da3b245da64d1bf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63a2098a5419ffd329632db84a8c3fdfd2c4e66a35fa65c2dd8225b561f98c5
+oid sha256:4835c8fdf5e1244d06b538bb0411f5663ba61a4b642b239ac84bacfdf7a67ce7
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07eb6b63cad9993dec6e656fd4c71d3947ff753d1d69f6cb4af816e99133c6a5
+oid sha256:b11bbf0be8e9c6bef86629b19875ef5a58334c29406c7ba5e19a74162e79e6cd
 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": 0.030547305897327112,
+  "epoch": 0.04582095884599067,
   "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": 13.674,
       "eval_steps_per_second": 1.721,
       "step": 18
+    },
+    {
+      "epoch": 0.03563852354688163,
+      "grad_norm": 0.5423109531402588,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.4864,
+      "step": 21
+    },
+    {
+      "epoch": 0.040729741196436145,
+      "grad_norm": 0.5172947645187378,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.4619,
+      "step": 24
+    },
+    {
+      "epoch": 0.04582095884599067,
+      "grad_norm": 0.48413389921188354,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.4352,
+      "step": 27
+    },
+    {
+      "epoch": 0.04582095884599067,
+      "eval_loss": 0.4471208155155182,
+      "eval_runtime": 72.6272,
+      "eval_samples_per_second": 13.673,
+      "eval_steps_per_second": 1.721,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.707888584995635e+16,
+  "total_flos": 4.043285695404442e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null