Training in progress, step 195, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b6eb8ff80256a2af4655621c3b1cca2bb38c588a0d97d526605f4e6ecb9c5d
+oid sha256:0ac17f6c81e08b1a89e83f8b4b3ac513bfcde0ca7120d41b6dd8dfadc577d5ed
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254008b4f692574facaadf44e32daa062d61e774cf4f9c4d0948054fd3989bf8
+oid sha256:7913d11ecc23045b0ab002924b05f4a9d60d3343204f419264cc03cbb357383e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdb857673169b4cc95f1ddb6b2070ee6ac8e493f9b660c237eec416fb84fea6
+oid sha256:ec19b72888d01e31467c857df8c64f2dfef7d68663f73e44a2d8d2f166d6c909
 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": 1.2827004219409281,
+  "epoch": 1.3164556962025316,
   "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": 0.6815,
       "step": 190
+    },
+    {
+      "epoch": 1.289451476793249,
+      "grad_norm": 0.5844349265098572,
+      "learning_rate": 1.3799252646597426e-06,
+      "loss": 0.7115,
+      "step": 191
+    },
+    {
+      "epoch": 1.2962025316455696,
+      "grad_norm": 0.6024525165557861,
+      "learning_rate": 1.0908391628854041e-06,
+      "loss": 0.7172,
+      "step": 192
+    },
+    {
+      "epoch": 1.3029535864978903,
+      "grad_norm": 0.5579437017440796,
+      "learning_rate": 8.355304489257254e-07,
+      "loss": 0.6542,
+      "step": 193
+    },
+    {
+      "epoch": 1.309704641350211,
+      "grad_norm": 0.5968881249427795,
+      "learning_rate": 6.140863104726391e-07,
+      "loss": 0.7236,
+      "step": 194
+    },
+    {
+      "epoch": 1.3164556962025316,
+      "grad_norm": 0.6294706463813782,
+      "learning_rate": 4.2658237049655323e-07,
+      "loss": 0.6669,
+      "step": 195
     }
   ],
   "logging_steps": 1,
@@ -1404,7 +1439,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.430313843049103e+17,
+  "total_flos": 8.652261552826614e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null