Training in progress, epoch 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1ce623a9290244838506727dabcd032cd98161a4bc9a4d333e928e900106b8
+oid sha256:82f7731b75422377a28eb0fbed27842ed5385f04e8571f8d31a9f329c1bf5063
 size 2526824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72c7b53fcd949fae1a20cef1038864720e95adb6f0ba2ee1613eb97830791f8
+oid sha256:54b1ff93ac859f0c1756b6dc4cd8eccd491deb9d6d7ee6535ef016cf0648fa2b
 size 1628986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41043d7401f5848237af4c4b1c2c2082e5048849c31547448e6f7368c669002c
+oid sha256:ca209c2564619e3369f7269d5d082523329af98f0199cd771fd3b9abd44b2930
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30241b4c1125cc90d62919e91ddb85f7c49ce98d2e890950e4784d91b698c05e
+oid sha256:ec3c5bcba33cc40c0c0a56d57f81d4e0801ed7a2347a76d3ba244fe8f8b71213
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 5.91970802919708,
   "eval_steps": 500,
-  "global_step": 345,
+  "global_step": 408,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,13 @@
       "learning_rate": 5.772683701771136e-05,
       "loss": 1.5781,
       "step": 328
+    },
+    {
+      "epoch": 5.350364963503649,
+      "grad_norm": 0.5262916684150696,
+      "learning_rate": 1.4512769140498178e-05,
+      "loss": 1.6,
+      "step": 369
     }
   ],
   "logging_steps": 41,
@@ -78,12 +85,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.976304525737984e+16,
+  "total_flos": 3.5237707596693504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null