Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8b775564ac16ad0fd65aa4e5c89d581c9bf8162362ee64ad87f26ec08e1755
+oid sha256:ecbcc29274f15acdef920dfb2fe62fd96dc716aa9fba305933719cbd3df980b3
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a97b7f8518895eadcb65a86aabc91df117b779ea03b2c187dfbcbcf9b285fc5
+oid sha256:caca890bb9ff8f44e67c85c7531fff84d9d67ebfed3795868aaf0fff5d1b3af4
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
+oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005186974211012595,
+  "epoch": 0.0006483717763765744,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 25.685,
       "eval_steps_per_second": 12.842,
       "step": 4
+    },
+    {
+      "epoch": 0.0006483717763765744,
+      "grad_norm": 1.231426477432251,
+      "learning_rate": 5e-05,
+      "loss": 1.6159,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4491064828231680.0,
+  "total_flos": 5398833250959360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null