Training in progress, step 3276, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e963705c16b053b94ecc7fb1e65350d738a1a1ccc4d852b3b13c8e1132ed1152
+oid sha256:5c86dadc500b7188faf7a8bb7a954d0971ad492e6fc6ecdc105bab21d7d9e30b
 size 44871152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b804648b78f6aba4b3c759b83d3b63afbcc2e9b23d01cff14205168d48d6da
+oid sha256:6e04f7cbd508a4aca9633d4642c5f36e93f991547db82777edb22c8552dedecc
 size 23160933

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e837c3df27ba5c150fca3ab0ea53bed8b6518dd15754087371a66bda5b1bffd
+oid sha256:75a44b3635613af98dbe31c7f353f92c33d397458c8f6c5354223aad999f0546
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6637ca6b270447484bcdcef0a0495294e6184477f8a9ca4b540be4b8a24d109b
+oid sha256:25eb07200b873fcd613c4be0014b422c43d68a4f83d8b03bae4b1fa479396410
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.307156752329272,
+  "epoch": 1.3415583085901506,
   "eval_steps": 500,
-  "global_step": 3192,
+  "global_step": 3276,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2241,6 +2241,62 @@
       "learning_rate": 5.6803786218553225e-05,
       "loss": 0.39436218738555906,
       "step": 3190
+    },
+    {
+      "epoch": 1.3104330910207842,
+      "grad_norm": 0.21847650408744812,
+      "learning_rate": 5.620660325105085e-05,
+      "loss": 0.3792898178100586,
+      "step": 3200
+    },
+    {
+      "epoch": 1.3145285143851746,
+      "grad_norm": 0.18161235749721527,
+      "learning_rate": 5.561134647750453e-05,
+      "loss": 0.3819849967956543,
+      "step": 3210
+    },
+    {
+      "epoch": 1.3186239377495648,
+      "grad_norm": 0.19815488159656525,
+      "learning_rate": 5.501804207948686e-05,
+      "loss": 0.3910470724105835,
+      "step": 3220
+    },
+    {
+      "epoch": 1.3227193611139552,
+      "grad_norm": 0.20001402497291565,
+      "learning_rate": 5.4426716152697966e-05,
+      "loss": 0.40929183959960935,
+      "step": 3230
+    },
+    {
+      "epoch": 1.3268147844783456,
+      "grad_norm": 0.1942245364189148,
+      "learning_rate": 5.383739470581739e-05,
+      "loss": 0.3569636344909668,
+      "step": 3240
+    },
+    {
+      "epoch": 1.3309102078427357,
+      "grad_norm": 0.19983036816120148,
+      "learning_rate": 5.3250103659360474e-05,
+      "loss": 0.45906848907470704,
+      "step": 3250
+    },
+    {
+      "epoch": 1.335005631207126,
+      "grad_norm": 0.16998930275440216,
+      "learning_rate": 5.2664868844538e-05,
+      "loss": 0.37126028537750244,
+      "step": 3260
+    },
+    {
+      "epoch": 1.3391010545715163,
+      "grad_norm": 0.21435993909835815,
+      "learning_rate": 5.2081716002120195e-05,
+      "loss": 0.4437861919403076,
+      "step": 3270
     }
   ],
   "logging_steps": 10,
@@ -2260,7 +2316,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.538904590800609e+17,
+  "total_flos": 5.68472722169684e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null