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:c7d8a0aa3e6d9371732513ecc6106999a92c28a5dd10b3ae7c0ac689cc7bdf18
+oid sha256:9fea248011550d271dba19c4e82e77715372a7fd0592e2f5ca5a8b55f753bf29
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a642b4a05bd74aa128f92eb2c316e7c01f7deb790610779b835b61f197c3e44f
+oid sha256:df65b129a1ddac94e109d67405c60fadea05436e366211fd2190fbc545402b5e
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f7de842be5b823c5352a6f4d4c24b0c158a91304726e478c62968d6920c3c78
+oid sha256:107a2111e838867c3feac9e98b4e198826002bd6fc18625eae8ef120b76d9b4b
 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": 0.010643605521370364,
+  "epoch": 0.013304506901712955,
   "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": 52.134,
       "eval_steps_per_second": 26.108,
       "step": 4
+    },
+    {
+      "epoch": 0.013304506901712955,
+      "grad_norm": 28.087499618530273,
+      "learning_rate": 5e-05,
+      "loss": 58.7344,
+      "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": 2611964849160192.0,
+  "total_flos": 3264956061450240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null