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:edbbdcc2c6ee84ce47d03fe97f6f91395a4a830bc85e197a21726d36312cb8da
+oid sha256:2622cd5b3e051882429e16c98b2b8e13f5a6a0035c4a4c1e8d0cda6cdb040982
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1b12b75be11b6f2a453dca326f0e24e7177db26fe4a37771c80bf37c98f8b1
+oid sha256:714ae6d432cd099f10212d5befe5891fe11f9e854427f12590c31449614cd8d3
 size 41459700

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": 0.044137931034482755,
+  "epoch": 0.05517241379310345,
   "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": 35.963,
       "eval_steps_per_second": 18.099,
       "step": 4
+    },
+    {
+      "epoch": 0.05517241379310345,
+      "grad_norm": 3.2730822563171387,
+      "learning_rate": 5e-05,
+      "loss": 14.2351,
+      "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": 3528837993332736.0,
+  "total_flos": 4443721917530112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null