Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f32f45832644c2ca40db2b1938eaebaffd570646e1a97e9bdb9457bc025a883
+oid sha256:02f52663c8bd9ee11fa6e54bf903dcb9e5a62163b5322459e1d15b5a87b30000
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aae61cc9117b96137586458f29b7a8e163dd0dec129de7be64f4538f1024511
+oid sha256:7fbbf711be0bb17e4414778a1380402faf662ccfe6cf3167e68b7fcd0fda1502
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c992bec7bad02bc7fd2d5a6b879f5f88896e3c2afafaa49127ee15fcf63f3ab
+oid sha256:463d4c32c3b16e0d2da78be9efac9c053a1d39e289c95070a3d7b6d26777c1a4
 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": 0.07485380116959064,
+  "epoch": 0.0935672514619883,
   "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": 4.204,
       "eval_steps_per_second": 2.102,
       "step": 4
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "grad_norm": 88.95408630371094,
+      "learning_rate": 5e-05,
+      "loss": 185.9496,
+      "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": 4967685188222976.0,
+  "total_flos": 6148528388702208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null