Training in progress, step 155, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b030ba7fcf62e5c346671de13683242d2201eadf998d69e19d12aa7b9cf8ff5
+oid sha256:e74b2ebc60418255b427b192e0c542ac135a548e2775c41043011d534e43b387
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26632f11da375f18c00e1ae3853a6812467af817f6fda67137389cbfd9f6f6d
+oid sha256:0f19f7031d1e3ed85893ad388f3273e5198d76ada01b533381832088a96be25d
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85dcff485150847800368b832b7fbbde9bcca50c94c2ff19cbbdf38672b04cb0
+oid sha256:4fe14dee36a73635fccad5a14a292e5eba895c9869df06a43c1764c5dffef85e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a946cb282348d3fba8c242cd51f3b90b3dccbd24720ee6b6397a7e493e7b92c
+oid sha256:382ece00c385c691790a218c7659825f5fdd28b4e63aa1032e7b069dd2944457
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07335411699981662,
+  "epoch": 0.07579925423314383,
   "eval_steps": 34,
-  "global_step": 150,
+  "global_step": 155,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1097,6 +1097,41 @@
       "learning_rate": 3.973653636207437e-05,
       "loss": 8.9558,
       "step": 150
+    },
+    {
+      "epoch": 0.07384314444648206,
+      "grad_norm": 9.168760943570584e+18,
+      "learning_rate": 3.8272177871020723e-05,
+      "loss": 9.9009,
+      "step": 151
+    },
+    {
+      "epoch": 0.0743321718931475,
+      "grad_norm": Infinity,
+      "learning_rate": 3.682889937467493e-05,
+      "loss": 9.1193,
+      "step": 152
+    },
+    {
+      "epoch": 0.07482119933981295,
+      "grad_norm": Infinity,
+      "learning_rate": 3.540719375132129e-05,
+      "loss": 9.1242,
+      "step": 153
+    },
+    {
+      "epoch": 0.07531022678647839,
+      "grad_norm": Infinity,
+      "learning_rate": 3.400754651212776e-05,
+      "loss": 9.2777,
+      "step": 154
+    },
+    {
+      "epoch": 0.07579925423314383,
+      "grad_norm": Infinity,
+      "learning_rate": 3.263043563534428e-05,
+      "loss": 10.0257,
+      "step": 155
     }
   ],
   "logging_steps": 1,
@@ -1116,7 +1151,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.306719513935872e+17,
+  "total_flos": 3.4169434977337344e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null