Training in progress, step 110, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac183d4e3bfb289b72fde08aa4baa18edb218bf3a85ffc21baef8c9e8c0e1162
+oid sha256:261d77ce7ab15ec1632ae754a5bf3877455f864e510ce3b388967e414c46403d
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f925744c6fae1afd5a9a43ee550e41eb8783773a2f9ae74177e5221304945938
+oid sha256:fc4f4b7834272c51f494774a035366f28694ccb4e7c34efb5c050c467ac11a74
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dedf35ba75ba42e0333d411cfe9a97e5addfe3e2f5fe02a25acdf6a6edac029
+oid sha256:59e17e0dfc13384541ffecf7da21d366d7aa79296745bb1827f3c372bace18c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c855c846898181ed358c1ef65b19ad1435172d9025fde7f25f4580bfc48faa
+oid sha256:802e09b6cc63e64e726d0b68ba37b81d6a6fcf54cdf00e4821b3e38426a8a5c4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.051347881899871634,
+  "epoch": 0.05379301913319885,
   "eval_steps": 34,
-  "global_step": 105,
+  "global_step": 110,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -774,6 +774,41 @@
       "learning_rate": 0.00011837495178165706,
       "loss": 0.9059,
       "step": 105
+    },
+    {
+      "epoch": 0.05183690934653708,
+      "grad_norm": 1.8266162872314453,
+      "learning_rate": 0.000116555387618413,
+      "loss": 1.1925,
+      "step": 106
+    },
+    {
+      "epoch": 0.05232593679320252,
+      "grad_norm": 1.780070424079895,
+      "learning_rate": 0.00011473016980546377,
+      "loss": 1.248,
+      "step": 107
+    },
+    {
+      "epoch": 0.052814964239867965,
+      "grad_norm": 2.0775444507598877,
+      "learning_rate": 0.00011289992165302035,
+      "loss": 1.3379,
+      "step": 108
+    },
+    {
+      "epoch": 0.05330399168653341,
+      "grad_norm": 1.8501131534576416,
+      "learning_rate": 0.00011106526818915008,
+      "loss": 1.3934,
+      "step": 109
+    },
+    {
+      "epoch": 0.05379301913319885,
+      "grad_norm": 1.610377311706543,
+      "learning_rate": 0.00010922683594633021,
+      "loss": 1.2629,
+      "step": 110
     }
   ],
   "logging_steps": 1,
@@ -793,7 +828,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.061746989039616e+16,
+  "total_flos": 6.350401607565312e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null