Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fc5979dfeb987c8e72c1c7295e81e58d9deed9a5bc40278759afcdbfc53c07
+oid sha256:cbab10f78c989674a6b9a1f2781df64c2947f0a91f41fa7d8436683577b79b39
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10944f0f17a89063a18ab4f684c248de4d74c4ad3a51c3f399a683764b5a8ad9
+oid sha256:e96fa03385ecdd36d739a3c7d56a9091e30842df4c72903b17b097e04b1f4880
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f16f3b8874379bf8e1e039ef0bfa9f44be83be43b977ccd15b78395a275f501
+oid sha256:afbf885258eba70f5506df642b9914670073e12a659d870c912f419df3669557
 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": 0.002982848620432513,
+  "epoch": 0.0037285607755406414,
   "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": 6.671,
       "eval_steps_per_second": 3.337,
       "step": 4
+    },
+    {
+      "epoch": 0.0037285607755406414,
+      "grad_norm": 21.318023681640625,
+      "learning_rate": 5e-05,
+      "loss": 28.5183,
+      "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": 5065926676316160.0,
+  "total_flos": 6332408345395200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null