Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00fdf1a9bc19adeef3a531f1938b41ea11f0ef23a420636f6babbe8ac6c9e452
+oid sha256:160c25f893f8fd05b1ad2f1f6470eedf27ec66c07e68b91e3b5066edc0748506
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2196663033c59cb8699afac1a4e72c4f88180988a9860fd6c9f60a35ae2c765c
+oid sha256:8ad33e27d2097535fc4bda98c933872a56c338d58c4933222a1645bcf3b806c0
 size 13005114

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": 0.04815650865312265,
+  "epoch": 0.06019563581640331,
   "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": 69.655,
       "eval_steps_per_second": 34.827,
       "step": 4
+    },
+    {
+      "epoch": 0.06019563581640331,
+      "grad_norm": 3.912907838821411,
+      "learning_rate": 5e-05,
+      "loss": 23.9453,
+      "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": 955431581122560.0,
+  "total_flos": 1194289476403200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null