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:fa17734fa2cf50153c91cc55c7298df617bcb0714366429286a67775620c9553
+oid sha256:b050dc8da75c36f8ee6de02b4f8eed832dd183eb91a3db394872e27c342d364e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee34572ad54f9e3f0d690211a8ccc1a1eccafd2a33c751e3b380dc54cbf1892
+oid sha256:500d8f0ecf3f6b16048b21fa0ab544570a086d53bd03b8a2a0672f94b8ce214b
 size 41119636

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": 0.03349031920460492,
+  "epoch": 0.04186289900575615,
   "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": 22.628,
       "eval_steps_per_second": 11.314,
       "step": 4
+    },
+    {
+      "epoch": 0.04186289900575615,
+      "grad_norm": 12.090420722961426,
+      "learning_rate": 5e-05,
+      "loss": 22.302,
+      "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": 2605998787264512.0,
+  "total_flos": 3257498484080640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null