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:c71d237e710a962dcb9e6ba5ccc36a842b75de6c36ff2691b85a6e48f49d4991
+oid sha256:5150c2196969043314f566861c4849a7f9365e1cc6a686a4cdb2edb6fa4eddb5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0df129bdd4dadcc2e2c280e7cf459a2eb420cd37dd7d896ef8cfbf82a4c45fd
+oid sha256:df1a35499a98ce19e19615db2fbac7d72d4a494f93b1298df13d80ee2cf6aec3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1849ad9db14ff92103b9d227ede45e09b064472ac17db6af688392748c6c18b
+oid sha256:3d72c4d52a605fc99c729c21c0deb735993f9bc8ecba075dedb1f93e3a6ad9c7
 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": 1.0331,
       "step": 155
+    },
+    {
+      "epoch": 0.07628828167980928,
+      "grad_norm": 0.40078866481781006,
+      "learning_rate": 3.1276331403073735e-05,
+      "loss": 0.9615,
+      "step": 156
+    },
+    {
+      "epoch": 0.07677730912647472,
+      "grad_norm": 0.6274716258049011,
+      "learning_rate": 2.9945696240670906e-05,
+      "loss": 1.0867,
+      "step": 157
+    },
+    {
+      "epoch": 0.07726633657314017,
+      "grad_norm": 0.3220311403274536,
+      "learning_rate": 2.8638984558824777e-05,
+      "loss": 0.9813,
+      "step": 158
+    },
+    {
+      "epoch": 0.07775536401980561,
+      "grad_norm": 0.3146653473377228,
+      "learning_rate": 2.7356642598377603e-05,
+      "loss": 0.9991,
+      "step": 159
+    },
+    {
+      "epoch": 0.07824439146647105,
+      "grad_norm": 0.22245855629444122,
+      "learning_rate": 2.6099108277934103e-05,
+      "loss": 0.9811,
+      "step": 160
     }
   ],
   "logging_steps": 1,
@@ -1151,7 +1186,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.880379003102822e+17,
+  "total_flos": 7.102326712880333e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null