Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70c1eae3ea32328eac5dc2c15a179baad744d980c715f3e21b00283238d2fd7a
+oid sha256:a5c73fb953f8799a4e938c441e149f2372dc197b97d96ba8d86481f29a9cb5bb
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed9175609e2bf9039578e569744b25f6a7d4258f6725d07c9fe5c525f4c9aa7
+oid sha256:bcb355c4238585274b9f9d89536eb8b84e1beafa02b9e1bd781c54399c31e198
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 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": 0.0557361820715281,
+  "epoch": 0.07431490942870414,
   "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": 46.133,
       "eval_steps_per_second": 23.067,
       "step": 15
+    },
+    {
+      "epoch": 0.05945192754296331,
+      "grad_norm": 0.25280341506004333,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.4441,
+      "step": 16
+    },
+    {
+      "epoch": 0.06316767301439852,
+      "grad_norm": 0.24035438895225525,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.454,
+      "step": 17
+    },
+    {
+      "epoch": 0.06688341848583372,
+      "grad_norm": 0.25593966245651245,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4755,
+      "step": 18
+    },
+    {
+      "epoch": 0.07059916395726892,
+      "grad_norm": 0.23320859670639038,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3743,
+      "step": 19
+    },
+    {
+      "epoch": 0.07431490942870414,
+      "grad_norm": 0.2590647339820862,
+      "learning_rate": 0.0,
+      "loss": 0.559,
+      "step": 20
+    },
+    {
+      "epoch": 0.07431490942870414,
+      "eval_loss": 0.35494011640548706,
+      "eval_runtime": 9.8317,
+      "eval_samples_per_second": 46.177,
+      "eval_steps_per_second": 23.089,
+      "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": 5488568204525568.0,
+  "total_flos": 7276416161808384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null