Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a32e202d6a9986f8af91d48a45dcc68c8af86d7d0ac1bb171c1f9857f327da
+oid sha256:1cb14b06fe0b0b43fe787f2df506048d116cf834213956a6f61a3b2e231008a0
 size 2964338224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1c3442ba049accf431a05b91c06b929128705beea2e7eb357461e740a7a49fc
+oid sha256:0d973228f44166b8655aadc245180bda11172445940cb89ed837a63f602955c2
 size 1485440604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3af4895ee60a6cf3967bedfe8b1f52d2a28f2e3bbcaf5bdf959ed76cea26519
+oid sha256:a75420d7d2cab5c13c305836e242e00e279b98390d1374452af7a72362900061
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.068222621184919,
+  "epoch": 2.2980251346499103,
   "eval_steps": 500,
-  "global_step": 36,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,34 @@
       "learning_rate": 1.4773284070716503e-05,
       "loss": 2.0598,
       "step": 36
+    },
+    {
+      "epoch": 2.1256732495511668,
+      "grad_norm": 1.2558954954147339,
+      "learning_rate": 1.3057004537193423e-05,
+      "loss": 2.0412,
+      "step": 37
+    },
+    {
+      "epoch": 2.183123877917415,
+      "grad_norm": 1.0945749282836914,
+      "learning_rate": 1.1410811249969475e-05,
+      "loss": 1.959,
+      "step": 38
+    },
+    {
+      "epoch": 2.2405745062836626,
+      "grad_norm": 1.0557724237442017,
+      "learning_rate": 9.844364725834057e-06,
+      "loss": 1.9716,
+      "step": 39
+    },
+    {
+      "epoch": 2.2980251346499103,
+      "grad_norm": 1.1883456707000732,
+      "learning_rate": 8.36685749586087e-06,
+      "loss": 1.9485,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -278,7 +306,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4592295975399424e+16,
+  "total_flos": 2.7513920113127424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null