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:d11a75249137a1c22436c20bc053fe0a84d1475a9234d4c77bc013e4c9da3ea7
+oid sha256:0ed2dc453838011a3ad88cc1cf98eda576c5b58b08fdb52747363459586e7f50
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806b575990e107a54c7adc5096ba8a892fa7b517e81f1785705cb8bc3449ffae
+oid sha256:380fa9f7aaf32c320af5bc14b4b06f8c42ffd5783662615ecbf1f25fec3ff108
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
+oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0022655829628161197,
+  "epoch": 0.0033983744442241796,
   "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": 9.372094804706867e-05,
       "loss": 10.3714,
       "step": 18
+    },
+    {
+      "epoch": 0.0023788621109569258,
+      "grad_norm": 0.07062539458274841,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.3731,
+      "step": 21
+    },
+    {
+      "epoch": 0.0027186995553793434,
+      "grad_norm": 0.07306697219610214,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.3711,
+      "step": 24
+    },
+    {
+      "epoch": 0.0027186995553793434,
+      "eval_loss": 10.371893882751465,
+      "eval_runtime": 22.0107,
+      "eval_samples_per_second": 168.872,
+      "eval_steps_per_second": 84.459,
+      "step": 24
+    },
+    {
+      "epoch": 0.0030585369998017615,
+      "grad_norm": 0.06676942855119705,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.3717,
+      "step": 27
+    },
+    {
+      "epoch": 0.0033983744442241796,
+      "grad_norm": 0.07616107165813446,
+      "learning_rate": 0.0,
+      "loss": 10.3713,
+      "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": 568789106688.0,
+  "total_flos": 849914757120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null