Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1dc30bd262bcdcc9b11ac6858c3fdc0bf50b77419a1ab6ded40fc5b8448cbc
+oid sha256:5cf05509147ae289a6401c175787541a86e7b27b9e02822d13d3c68a9b551ee8
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1cac41c925e8ebeb2ac3e01fe2cfcfab106ea8e627aa3b3d65d32b44f8b7412
+oid sha256:bda070ce8697c300bbcd60d0635b8325887f21fdcc6715ad16e17bcfe2c59e4a
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d40f761f58490413a6bc1eba33545e30eb8837c7707dca5575393f3f81beb33
+oid sha256:0104cd3a39a39e7efe96d4368d017e590c56f84656f77b6c2e0cc8bfebf6aafb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb97b24f34ff3e53eec5be9cf35c1a7161c58dbc2fed7dda160fb3eb64e5f353
+oid sha256:dd09e47b42474af18ba1772930aac1db12bb0a5a5868e68e151935c59da27a51
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.037578288100208766,
+  "epoch": 0.04133611691022965,
   "eval_steps": 17,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -685,6 +685,69 @@
       "learning_rate": 6.030737921409169e-06,
       "loss": 2.6747,
       "step": 90
+    },
+    {
+      "epoch": 0.037995824634655534,
+      "grad_norm": Infinity,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 2.9142,
+      "step": 91
+    },
+    {
+      "epoch": 0.038413361169102295,
+      "grad_norm": Infinity,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 2.9999,
+      "step": 92
+    },
+    {
+      "epoch": 0.03883089770354906,
+      "grad_norm": Infinity,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 2.9339,
+      "step": 93
+    },
+    {
+      "epoch": 0.03924843423799582,
+      "grad_norm": Infinity,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.0186,
+      "step": 94
+    },
+    {
+      "epoch": 0.03966597077244259,
+      "grad_norm": Infinity,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 2.7521,
+      "step": 95
+    },
+    {
+      "epoch": 0.04008350730688935,
+      "grad_norm": Infinity,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 2.8372,
+      "step": 96
+    },
+    {
+      "epoch": 0.04050104384133612,
+      "grad_norm": Infinity,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 2.8114,
+      "step": 97
+    },
+    {
+      "epoch": 0.04091858037578288,
+      "grad_norm": Infinity,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 2.7142,
+      "step": 98
+    },
+    {
+      "epoch": 0.04133611691022965,
+      "grad_norm": Infinity,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 3.1884,
+      "step": 99
     }
   ],
   "logging_steps": 1,
@@ -704,7 +767,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.705727579324416e+16,
+  "total_flos": 4.076300337256858e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null