Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20a66d2bc703e7fdee0633df45d06c93e8c5234b919e56c6d07ae35a46f089ef
+oid sha256:099a3b6d4ae1acae35f884ebc4555e982a44acad96cc9b748df02f9efcf9e951
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1ed642000d4e3c8f486d555b53aed773e0b0d98945aecd9cabe41f4d8f7675
+oid sha256:34c6285f9556c3d6d3358732c13e9aeff46acd2410c53359005ce61f43896292
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18797824dc0375cb657b51b8e87aff809ea47d39704d989e1b1c3a76a7a70a6b
+oid sha256:11e71cead5a7fcc376909c83446602574c8bdf1bd2d38d471d24ab6cfd202c92
 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": 0.0023829913988904195,
+  "epoch": 0.0029787392486130245,
   "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": 363.823,
       "eval_steps_per_second": 181.911,
       "step": 4
+    },
+    {
+      "epoch": 0.0029787392486130245,
+      "grad_norm": 1.994558572769165,
+      "learning_rate": 5e-05,
+      "loss": 177.3125,
+      "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": 23533977600.0,
+  "total_flos": 29324083200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null