Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:454a1484bf9ae663900bccbb23ef99732643ab20d1062dc2bbca3bc84c4bb7ed
+oid sha256:3db0ae42d37be1aaf2a7664cb20d94d2813102781c27627d9b2a9c4510e1cfb0
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368ca92e536d23cad970f7f3c189628cdf03fe35a6517b072ab84fc1d84dc4e8
+oid sha256:016d5e03f16c1fb2de4cb9742df06f5fffd73b2f5407331435f8de5298e646c9
 size 436083346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877632ef3bd249f1e644a973de52fe2c669b9ad6827c9500f5f8d598a7bb9bcd
+oid sha256:2feff802a75ff8cb940559719b71ab6aa644cb8b64b64058cef0d935e2c185cf
 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": 0.02307470435535045,
+  "epoch": 0.03461205653302567,
   "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": 0.3792,
       "step": 18
+    },
+    {
+      "epoch": 0.02422843957311797,
+      "grad_norm": 0.25382229685783386,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.315,
+      "step": 21
+    },
+    {
+      "epoch": 0.027689645226420537,
+      "grad_norm": 0.22817522287368774,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.3164,
+      "step": 24
+    },
+    {
+      "epoch": 0.027689645226420537,
+      "eval_loss": 0.3118995130062103,
+      "eval_runtime": 114.1724,
+      "eval_samples_per_second": 3.197,
+      "eval_steps_per_second": 1.603,
+      "step": 24
+    },
+    {
+      "epoch": 0.031150850879723104,
+      "grad_norm": 0.21940067410469055,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.3085,
+      "step": 27
+    },
+    {
+      "epoch": 0.03461205653302567,
+      "grad_norm": 0.2270139902830124,
+      "learning_rate": 0.0,
+      "loss": 0.3242,
+      "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": 1.695099842985984e+16,
+  "total_flos": 2.542649764478976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null