Training in progress, step 69, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16d6eb07033b72a3b2968dc0dc635125ffab4a31846978220b6caf42e45fad7
+oid sha256:9852065cb43524c383f57bd5def4c2c9f0923b073f71220cb9803b7f1394c549
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e1a5df9978303ccfad162c5fd2bedf1e222d91ffaa01e9f8d185b50633a3219
+oid sha256:dd09bb2b31d26d272eeb8a175856fb3c22a527c5eb60f853a0f298886e745ffc
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14bf2f4838ff5eca2b84152c5f01ed2f55b189468509c0c79a96ec148e07b9cb
+oid sha256:e16ecba4f383b032800f6f4b292a87e2dba91471d1e9ce1303a2b98db5647af3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1755829903978052,
+  "epoch": 0.18930041152263374,
   "eval_steps": 500,
-  "global_step": 64,
+  "global_step": 69,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,6 +455,41 @@
       "learning_rate": 0.00012800000000000002,
       "loss": 1.3083,
       "step": 64
+    },
+    {
+      "epoch": 0.17832647462277093,
+      "grad_norm": 0.0989551916718483,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.3216,
+      "step": 65
+    },
+    {
+      "epoch": 0.18106995884773663,
+      "grad_norm": 0.09368593990802765,
+      "learning_rate": 0.000132,
+      "loss": 1.3409,
+      "step": 66
+    },
+    {
+      "epoch": 0.18381344307270234,
+      "grad_norm": 0.09617207944393158,
+      "learning_rate": 0.000134,
+      "loss": 1.3192,
+      "step": 67
+    },
+    {
+      "epoch": 0.18655692729766804,
+      "grad_norm": 0.08890332281589508,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.354,
+      "step": 68
+    },
+    {
+      "epoch": 0.18930041152263374,
+      "grad_norm": 0.11371646821498871,
+      "learning_rate": 0.000138,
+      "loss": 1.3201,
+      "step": 69
     }
   ],
   "logging_steps": 1,
@@ -474,7 +509,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.909975005462528e+16,
+  "total_flos": 8.552053099433165e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null