Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0e05487678c69fcdcd1b1f79f30b71d52a9b691f8fcc08e6efa982576b0d35
+oid sha256:72809e984d2ef072d1487eed2b8d256d3d981b0e397bb8cadf76ba3a8eab1c11
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1acfae321c96c3e033090f8e4d186ca33e7880d05776b868ba05deb467ff18af
+oid sha256:af08a2e6050272239228b4e480c5c2982f3ed3f4d1886987e3768df08765e611
 size 191012170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51519413bc18290872e1b2878980768c779eb83b65450a149f03ba88575e859b
+oid sha256:63ecd6bcb366a97ada5c6cb1bb57791cba376adf55db6452d04810dc1531ef0a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015463120457708365,
+  "epoch": 0.002319468068656255,
   "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": 0.00013090169943749476,
       "loss": 6.4336,
       "step": 18
+    },
+    {
+      "epoch": 0.0016236276480593784,
+      "grad_norm": 4.184946537017822,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.8627,
+      "step": 21
+    },
+    {
+      "epoch": 0.001855574454925004,
+      "grad_norm": 5.131363391876221,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.2544,
+      "step": 24
+    },
+    {
+      "epoch": 0.001855574454925004,
+      "eval_loss": 0.645858108997345,
+      "eval_runtime": 498.1385,
+      "eval_samples_per_second": 10.933,
+      "eval_steps_per_second": 5.466,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020875212617906293,
+      "grad_norm": 4.872713565826416,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.5263,
+      "step": 27
+    },
+    {
+      "epoch": 0.002319468068656255,
+      "grad_norm": 3.9103922843933105,
+      "learning_rate": 0.0,
+      "loss": 4.5022,
+      "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": 3995567206170624.0,
+  "total_flos": 5957676102057984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null