Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46952c1c4497aa95e4ad76b794335eb5808f1c058dad43746b9b083bd4559901
+oid sha256:d235b4283b9d15546f0ceefc6e6f57ec9cba7d5353fd4b049b7f021b55ee5d3f
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b547daa019dd4bffd00a62507eb645719b3acbeb1b7d2c709c17e5d617d30a
+oid sha256:1815209d6b84de6bd8dafd44748099c88421e0a9334b6b618f00484f31b8851e
 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 sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01598721023181455,
+  "epoch": 0.023980815347721823,
   "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": 10.3787,
       "step": 18
+    },
+    {
+      "epoch": 0.016786570743405275,
+      "grad_norm": 0.023296209052205086,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 10.3789,
+      "step": 21
+    },
+    {
+      "epoch": 0.019184652278177457,
+      "grad_norm": 0.023096146062016487,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3793,
+      "step": 24
+    },
+    {
+      "epoch": 0.019184652278177457,
+      "eval_loss": 10.377493858337402,
+      "eval_runtime": 3.8926,
+      "eval_samples_per_second": 135.384,
+      "eval_steps_per_second": 67.821,
+      "step": 24
+    },
+    {
+      "epoch": 0.02158273381294964,
+      "grad_norm": 0.023451387882232666,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 10.3782,
+      "step": 27
+    },
+    {
+      "epoch": 0.023980815347721823,
+      "grad_norm": 0.025783749297261238,
+      "learning_rate": 0.0,
+      "loss": 10.3769,
+      "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": 732234252288.0,
+  "total_flos": 1170267242496.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null