Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c02b9f37302900e66e1552c2677161fa62a8a14a5382f52a383b70887e0c30b
+oid sha256:8ac3585621da688b6d9054d65bc76249a32d5e5e23d84714c2686b3ebb4687e0
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf276fdacd0db3e8907c333704f8d26a21f43a0c86a763be6b03f849cd304a0
+oid sha256:8c4fd9696d05a64665dbba07a205d0a7bc3822cf643100ab5896199256910c67
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ae54b5e63e82884cc8216afa89f8f2561c547f1fa2982921ac363ebc4b962f
+oid sha256:ff5a612de2dbbf08e0c47ca2afc15247bcb10f51087c8dcd75c58b354ad42b7b
 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": 0.0002451149359254238,
+  "epoch": 0.0003063936699067797,
   "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": 17.512,
       "eval_steps_per_second": 8.756,
       "step": 4
+    },
+    {
+      "epoch": 0.0003063936699067797,
+      "grad_norm": 10.690298080444336,
+      "learning_rate": 5e-05,
+      "loss": 33.5688,
+      "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": 5699167510855680.0,
+  "total_flos": 7203114492887040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null