Training in progress, step 187, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d64bb4252a56462612ce8ea325bbb4f7eb1e476a12210a5f3bc4adabecffe5
+oid sha256:f7cf0bd9a85d6e3b1dfba727a272bb5ec1b34ad233dbee1759f9c3dc7db4c616
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4beda4b81812c494724c944ce42a1384386d898438a92682ca41d1363ea7cd53
+oid sha256:130097d8b9a1531563be49666bf68e868a3488e44a4aa76718c4310d857b5354
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2cc8b4da1c1e828f3ecd6fdcd0ddcc7555dae3d2812a0ace74e33cfe7a8a86
+oid sha256:cfcd98a6fb5e6805c0c88270935cb6243951ff273b1a434ad4ff4ae8b2aadba3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a138d58efee4722b14f409e14731dcd0935c0eaa8a6078a4918744b9529bab
+oid sha256:9f9ab26294f369ba5d99cf6e2514a5d05f3df1a90b36a045191f6b23077ba365
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7878349022447502,
+  "epoch": 0.8666183924692252,
   "eval_steps": 50,
-  "global_step": 170,
+  "global_step": 187,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1229,6 +1229,125 @@
       "learning_rate": 1.0048094716167095e-05,
       "loss": 0.1441,
       "step": 170
+    },
+    {
+      "epoch": 0.7924692251991311,
+      "grad_norm": 1.155311942100525,
+      "learning_rate": 9.40352196454532e-06,
+      "loss": 0.1666,
+      "step": 171
+    },
+    {
+      "epoch": 0.7971035481535119,
+      "grad_norm": 1.0911647081375122,
+      "learning_rate": 8.778930535580474e-06,
+      "loss": 0.185,
+      "step": 172
+    },
+    {
+      "epoch": 0.8017378711078929,
+      "grad_norm": 0.9174829721450806,
+      "learning_rate": 8.174510685872415e-06,
+      "loss": 0.1147,
+      "step": 173
+    },
+    {
+      "epoch": 0.8063721940622737,
+      "grad_norm": 1.362585425376892,
+      "learning_rate": 7.5904465275624884e-06,
+      "loss": 0.2452,
+      "step": 174
+    },
+    {
+      "epoch": 0.8110065170166546,
+      "grad_norm": 1.197021722793579,
+      "learning_rate": 7.026915972251254e-06,
+      "loss": 0.2385,
+      "step": 175
+    },
+    {
+      "epoch": 0.8156408399710355,
+      "grad_norm": 1.0614386796951294,
+      "learning_rate": 6.484090676804926e-06,
+      "loss": 0.1824,
+      "step": 176
+    },
+    {
+      "epoch": 0.8202751629254164,
+      "grad_norm": 1.1456388235092163,
+      "learning_rate": 5.962135991066971e-06,
+      "loss": 0.1921,
+      "step": 177
+    },
+    {
+      "epoch": 0.8249094858797973,
+      "grad_norm": 1.2095783948898315,
+      "learning_rate": 5.461210907490951e-06,
+      "loss": 0.1803,
+      "step": 178
+    },
+    {
+      "epoch": 0.8295438088341781,
+      "grad_norm": 1.2167255878448486,
+      "learning_rate": 4.981468012709877e-06,
+      "loss": 0.1777,
+      "step": 179
+    },
+    {
+      "epoch": 0.834178131788559,
+      "grad_norm": 1.2779210805892944,
+      "learning_rate": 4.523053441056876e-06,
+      "loss": 0.2648,
+      "step": 180
+    },
+    {
+      "epoch": 0.8388124547429399,
+      "grad_norm": 1.1896816492080688,
+      "learning_rate": 4.086106830051236e-06,
+      "loss": 0.1531,
+      "step": 181
+    },
+    {
+      "epoch": 0.8434467776973208,
+      "grad_norm": 1.0845763683319092,
+      "learning_rate": 3.670761277863485e-06,
+      "loss": 0.1953,
+      "step": 182
+    },
+    {
+      "epoch": 0.8480811006517016,
+      "grad_norm": 1.338794231414795,
+      "learning_rate": 3.277143302772342e-06,
+      "loss": 0.1878,
+      "step": 183
+    },
+    {
+      "epoch": 0.8527154236060825,
+      "grad_norm": 1.036252737045288,
+      "learning_rate": 2.9053728046260825e-06,
+      "loss": 0.1352,
+      "step": 184
+    },
+    {
+      "epoch": 0.8573497465604635,
+      "grad_norm": 1.3027642965316772,
+      "learning_rate": 2.555563028319885e-06,
+      "loss": 0.2213,
+      "step": 185
+    },
+    {
+      "epoch": 0.8619840695148443,
+      "grad_norm": 1.0671361684799194,
+      "learning_rate": 2.227820529300264e-06,
+      "loss": 0.2172,
+      "step": 186
+    },
+    {
+      "epoch": 0.8666183924692252,
+      "grad_norm": 1.0457696914672852,
+      "learning_rate": 1.9222451411073645e-06,
+      "loss": 0.1704,
+      "step": 187
     }
   ],
   "logging_steps": 1,
@@ -1248,7 +1367,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0145742149438669e+18,
+  "total_flos": 1.1160316364382536e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null