Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff47faa45db36675ef26ef4651c6dea0e71b458bbceec27c80d905a4cc3960e
+oid sha256:0e56abb6b96f3b4078ee0add0e947c0c888773453f17f32863d5de7a4711a076
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d525f68ac9af49f79941f941dd21068fe2976ecf4a03f912a8d2de64c9d6aeb
+oid sha256:a3622b160a47500f6dfa14bf7d25b442be75d263a85b6aaa34488389dd363dbe
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b835124e9438a67b4922362546d9917dd2ad1ecf9964a45797b5ccba615a520
+oid sha256:4f29e05bcbde75ce27a9713f89d1d62332544e44f262dd85c2f7f43afaa9c494
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07073386383731212,
+  "epoch": 0.10610079575596817,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 3.3868,
       "step": 18
+    },
+    {
+      "epoch": 0.07427055702917772,
+      "grad_norm": 2.5410356521606445,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 3.2253,
+      "step": 21
+    },
+    {
+      "epoch": 0.08488063660477453,
+      "grad_norm": 2.174226760864258,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.8453,
+      "step": 24
+    },
+    {
+      "epoch": 0.08488063660477453,
+      "eval_loss": 2.9847254753112793,
+      "eval_runtime": 8.576,
+      "eval_samples_per_second": 13.876,
+      "eval_steps_per_second": 6.996,
+      "step": 24
+    },
+    {
+      "epoch": 0.09549071618037135,
+      "grad_norm": 2.7939352989196777,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.0492,
+      "step": 27
+    },
+    {
+      "epoch": 0.10610079575596817,
+      "grad_norm": 2.3326683044433594,
+      "learning_rate": 0.0,
+      "loss": 2.8804,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2757139491717120.0,
+  "total_flos": 4135709237575680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null