Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bc4b70375818e13a47b5d252d83790a99899fc88a0a233bebfd5d142b144859
+oid sha256:288e5a9083227779b1f42e3df04dad2f21fc8134ca952bfb66a039629372c4a8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df0236884de9659121070648736b29073c2cfbe562f6108207d4278fc3631588
+oid sha256:cabd7335c33ebb3c2f04ee0e5004f71c68f36faf1cd514b31c8e6e08e2fb0f7f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f22e103718bcf7c795caf2c97489e0eb8ab6b39b1de599faab5377a481bd5ff
+oid sha256:5804fd7ef539ba12202b1d9b94718f746df6071cbe56216b183c48cd4bb72ad4
 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": 0.0042866711319490955,
+  "epoch": 0.0053583389149363695,
   "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": 20.016,
       "eval_steps_per_second": 10.008,
       "step": 4
+    },
+    {
+      "epoch": 0.0053583389149363695,
+      "grad_norm": 7.703738212585449,
+      "learning_rate": 5e-05,
+      "loss": 5.7005,
+      "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": 4600758188113920.0,
+  "total_flos": 5783810293628928.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null