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:e24c094821b4b781a25c4918c019c06d7b85985ca491fddb7c42e5b8cd9ca228
+oid sha256:01355cb048b4fa39cd058f6ff6984cd21d24d421416c9995a3d17c10815e6e4d
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2801685f83de6e9f5978e4267f98a825f5888ad1f52ee7535d35af18f34f846f
+oid sha256:5d20f99d915b7db1864af352076fdee8ea4ad2b7404aef9b2bd1754fe63ec53d
 size 11710970

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": 0.009570809032451024,
+  "epoch": 0.011963511290563781,
   "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": 99.072,
       "eval_steps_per_second": 49.536,
       "step": 4
+    },
+    {
+      "epoch": 0.011963511290563781,
+      "grad_norm": 1.2530596256256104,
+      "learning_rate": 5e-05,
+      "loss": 1.4694,
+      "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": 396900100472832.0,
+  "total_flos": 505145582419968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null