Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d11f4b4d122c247ca30e8a484e4d5da7a0f312335b9ffafa8311b3d0c49342
+oid sha256:c6146b7096e08b8d94b0f3aa62d87fffb39b8a01040d054b0a2e5f39ab2b3767
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4161a268c431a2784049914d6488e4219157df4c0836f8f03cd16f49b9b58d46
+oid sha256:f747933f6ffab92306b233396322f42866efcd347cd8da431ed5bd3e0fc5492e
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bfd8deca4669c4d862688088e265172b55c9ed56fc54666385adead3bdb6c5
+oid sha256:711a839c37c850d2a73618168c26c7d42fa2942868385ff598beced73bdc06cf
 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": 0.006428801028608165,
+  "epoch": 0.009643201542912247,
   "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": 9.4144,
       "step": 18
+    },
+    {
+      "epoch": 0.006750241080038573,
+      "grad_norm": 3.005903482437134,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 8.6917,
+      "step": 21
+    },
+    {
+      "epoch": 0.007714561234329798,
+      "grad_norm": 3.32614803314209,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 8.2647,
+      "step": 24
+    },
+    {
+      "epoch": 0.007714561234329798,
+      "eval_loss": 2.131072998046875,
+      "eval_runtime": 200.0895,
+      "eval_samples_per_second": 6.547,
+      "eval_steps_per_second": 3.274,
+      "step": 24
+    },
+    {
+      "epoch": 0.008678881388621022,
+      "grad_norm": 2.954596996307373,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 8.3838,
+      "step": 27
+    },
+    {
+      "epoch": 0.009643201542912247,
+      "grad_norm": 2.7677104473114014,
+      "learning_rate": 0.0,
+      "loss": 8.3747,
+      "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": 6716688532992000.0,
+  "total_flos": 1.0183366485504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null