Training in progress, step 195, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a5c97dbf76ff33b307a5750999b650fdca855b6fccfb24cfb317d17b551db2
+oid sha256:4b6961ec56fb4a44ef494b0d658571c48ac344664dc6fe4a951f2610f0f03b8f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e14756a84c0c36abc832c0c104bd27a99e8fd2062b9726fdee254c458fe1f7b4
+oid sha256:345c3d0745bb4c43f0fbe85fc7c3ff9f29987a091928463d46244addf1e119f1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf11cdd535ea662ff270636f900a467408683d2b7101cb9dbc848f0681f26dea
+oid sha256:523bfe0a33577b4182bf5e3b1a37489a75b989d79cb5926278ae5a0647ffb1d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b289b438571df9d34409287e67864402aaad98d9ecdf87ccd44b9abb7f5b6982
+oid sha256:a35430a05f2b9748f37dd11667a782564c85a35d840d60cbaddfa2c905ab7c0a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09291521486643438,
+  "epoch": 0.0953603520997616,
   "eval_steps": 34,
-  "global_step": 190,
+  "global_step": 195,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1385,6 +1385,41 @@
       "learning_rate": 1.7026900316098215e-06,
       "loss": 1.1048,
       "step": 190
+    },
+    {
+      "epoch": 0.09340424231309982,
+      "grad_norm": 0.3293691873550415,
+      "learning_rate": 1.3799252646597426e-06,
+      "loss": 1.1607,
+      "step": 191
+    },
+    {
+      "epoch": 0.09389326975976527,
+      "grad_norm": 0.28064343333244324,
+      "learning_rate": 1.0908391628854041e-06,
+      "loss": 0.9642,
+      "step": 192
+    },
+    {
+      "epoch": 0.09438229720643071,
+      "grad_norm": 0.4100506603717804,
+      "learning_rate": 8.355304489257254e-07,
+      "loss": 0.931,
+      "step": 193
+    },
+    {
+      "epoch": 0.09487132465309615,
+      "grad_norm": 0.298096626996994,
+      "learning_rate": 6.140863104726391e-07,
+      "loss": 0.9616,
+      "step": 194
+    },
+    {
+      "epoch": 0.0953603520997616,
+      "grad_norm": 0.26067015528678894,
+      "learning_rate": 4.2658237049655323e-07,
+      "loss": 1.0008,
+      "step": 195
     }
   ],
   "logging_steps": 1,
@@ -1404,7 +1439,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.434012971545395e+17,
+  "total_flos": 8.655960681322906e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null