Training in progress, step 187, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e1f5c84173ea5e9b2e4fb08e10124d39b1a491b402f0de28caf8de4b760db49
+oid sha256:b4ecdf1d1971ac27d2273232d5e499a28ce82ab31d2afdfc65766d2e6c71c53f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:515b3e1ecb36e1cb5fbebf47abf80241dff7b621accc66dc2a10405eb064652a
+oid sha256:c5840807e8f3e3570da83c6ea2ea59e6407056ebf36fb978fe99851d8888a288
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f247327caf964bf7fa15c173ae9e435da78e83dfcb744db194cf8eca0374dd
+oid sha256:1d4af8b337fcb06c5a1eb4c33326a529881fb5d751ecc21aa6194c4594aa1b4b
 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": 0.2502875546353807,
+  "epoch": 0.27531631009891877,
   "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": 0.0101,
       "step": 170
+    },
+    {
+      "epoch": 0.25175983436853,
+      "grad_norm": 0.11024050414562225,
+      "learning_rate": 9.40352196454532e-06,
+      "loss": 0.0496,
+      "step": 171
+    },
+    {
+      "epoch": 0.25323211410167934,
+      "grad_norm": 0.09290501475334167,
+      "learning_rate": 8.778930535580474e-06,
+      "loss": 0.042,
+      "step": 172
+    },
+    {
+      "epoch": 0.2547043938348286,
+      "grad_norm": 0.10324755311012268,
+      "learning_rate": 8.174510685872415e-06,
+      "loss": 0.0466,
+      "step": 173
+    },
+    {
+      "epoch": 0.2561766735679779,
+      "grad_norm": 0.1255979835987091,
+      "learning_rate": 7.5904465275624884e-06,
+      "loss": 0.0731,
+      "step": 174
+    },
+    {
+      "epoch": 0.2576489533011272,
+      "grad_norm": 0.14712050557136536,
+      "learning_rate": 7.026915972251254e-06,
+      "loss": 0.0501,
+      "step": 175
+    },
+    {
+      "epoch": 0.25912123303427653,
+      "grad_norm": 0.10622108727693558,
+      "learning_rate": 6.484090676804926e-06,
+      "loss": 0.0465,
+      "step": 176
+    },
+    {
+      "epoch": 0.2605935127674258,
+      "grad_norm": 0.08225951343774796,
+      "learning_rate": 5.962135991066971e-06,
+      "loss": 0.0322,
+      "step": 177
+    },
+    {
+      "epoch": 0.2620657925005751,
+      "grad_norm": 0.06552782654762268,
+      "learning_rate": 5.461210907490951e-06,
+      "loss": 0.0156,
+      "step": 178
+    },
+    {
+      "epoch": 0.2635380722337244,
+      "grad_norm": 0.09848985821008682,
+      "learning_rate": 4.981468012709877e-06,
+      "loss": 0.0319,
+      "step": 179
+    },
+    {
+      "epoch": 0.2650103519668737,
+      "grad_norm": 0.11006014794111252,
+      "learning_rate": 4.523053441056876e-06,
+      "loss": 0.0384,
+      "step": 180
+    },
+    {
+      "epoch": 0.266482631700023,
+      "grad_norm": 0.07918134331703186,
+      "learning_rate": 4.086106830051236e-06,
+      "loss": 0.0424,
+      "step": 181
+    },
+    {
+      "epoch": 0.2679549114331723,
+      "grad_norm": 0.043903008103370667,
+      "learning_rate": 3.670761277863485e-06,
+      "loss": 0.0097,
+      "step": 182
+    },
+    {
+      "epoch": 0.2694271911663216,
+      "grad_norm": 0.08103958517313004,
+      "learning_rate": 3.277143302772342e-06,
+      "loss": 0.049,
+      "step": 183
+    },
+    {
+      "epoch": 0.2708994708994709,
+      "grad_norm": 0.12223482131958008,
+      "learning_rate": 2.9053728046260825e-06,
+      "loss": 0.0317,
+      "step": 184
+    },
+    {
+      "epoch": 0.2723717506326202,
+      "grad_norm": 0.04852719232439995,
+      "learning_rate": 2.555563028319885e-06,
+      "loss": 0.0094,
+      "step": 185
+    },
+    {
+      "epoch": 0.2738440303657695,
+      "grad_norm": 0.0753386989235878,
+      "learning_rate": 2.227820529300264e-06,
+      "loss": 0.0332,
+      "step": 186
+    },
+    {
+      "epoch": 0.27531631009891877,
+      "grad_norm": 0.11057372391223907,
+      "learning_rate": 1.9222451411073645e-06,
+      "loss": 0.0736,
+      "step": 187
     }
   ],
   "logging_steps": 1,
@@ -1248,7 +1367,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.796206666199335e+18,
+  "total_flos": 1.9745031642666762e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null