Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93272d9cd36da9660f618f0d4170893e231b805f453f258319f489193a929e61
+oid sha256:c2da72b5735912a7146f1b0098c38e81ef60fcd9b354c2ac262e40773ed831ad
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834b3e2741cdc3ed93fbe48c07e9651dc3691bdd8c3f26a8de51dbcc2d77f03f
+oid sha256:f3279afc25f29ca05c76777102f8b8a4be8b1d7e804df145702e72730578574e
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
+oid sha256:f0cab76d95a75c34838cec8f4adace53a2d256142482eba847df4bb06de7690f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08241758241758242,
+  "epoch": 0.10989010989010989,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 33.325,
       "eval_steps_per_second": 16.663,
       "step": 15
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 0.028067054226994514,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9316,
+      "step": 16
+    },
+    {
+      "epoch": 0.09340659340659341,
+      "grad_norm": 0.029327698051929474,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9319,
+      "step": 17
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.02734130434691906,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9326,
+      "step": 18
+    },
+    {
+      "epoch": 0.1043956043956044,
+      "grad_norm": 0.030583491548895836,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.933,
+      "step": 19
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 0.023537058383226395,
+      "learning_rate": 0.0,
+      "loss": 11.9314,
+      "step": 20
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "eval_loss": 11.931438446044922,
+      "eval_runtime": 18.4207,
+      "eval_samples_per_second": 33.332,
+      "eval_steps_per_second": 16.666,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 179872727040.0,
+  "total_flos": 239830302720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null