Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e74b2ebc60418255b427b192e0c542ac135a548e2775c41043011d534e43b387
+oid sha256:53bad8d26f88728dcad49d9d67620340a524e6147bc3971fc55bb8b1402df5b4
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f19f7031d1e3ed85893ad388f3273e5198d76ada01b533381832088a96be25d
+oid sha256:ecd579c529539ff37f6b6ff96f02721f0d3685a0b8a5cfa862e349f56ed45cd0
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe14dee36a73635fccad5a14a292e5eba895c9869df06a43c1764c5dffef85e
+oid sha256:1a492bc11190965aaac7d5575038263ec57f90649266f6d672b0255bafe0953f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382ece00c385c691790a218c7659825f5fdd28b4e63aa1032e7b069dd2944457
+oid sha256:fda70a7e2255bb2a6bed4064da315669732f8ee1496404c42573741f484eb69b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07579925423314383,
+  "epoch": 0.07824439146647105,
   "eval_steps": 34,
-  "global_step": 155,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1132,6 +1132,41 @@
       "learning_rate": 3.263043563534428e-05,
       "loss": 10.0257,
       "step": 155
+    },
+    {
+      "epoch": 0.07628828167980928,
+      "grad_norm": Infinity,
+      "learning_rate": 3.1276331403073735e-05,
+      "loss": 9.0075,
+      "step": 156
+    },
+    {
+      "epoch": 0.07677730912647472,
+      "grad_norm": Infinity,
+      "learning_rate": 2.9945696240670906e-05,
+      "loss": 9.2834,
+      "step": 157
+    },
+    {
+      "epoch": 0.07726633657314017,
+      "grad_norm": Infinity,
+      "learning_rate": 2.8638984558824777e-05,
+      "loss": 9.9998,
+      "step": 158
+    },
+    {
+      "epoch": 0.07775536401980561,
+      "grad_norm": 6.262369407729664e+16,
+      "learning_rate": 2.7356642598377603e-05,
+      "loss": 9.3281,
+      "step": 159
+    },
+    {
+      "epoch": 0.07824439146647105,
+      "grad_norm": Infinity,
+      "learning_rate": 2.6099108277934103e-05,
+      "loss": 10.5182,
+      "step": 160
     }
   ],
   "logging_steps": 1,
@@ -1151,7 +1186,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4169434977337344e+17,
+  "total_flos": 3.527167481531597e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null