Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff6889f682a1bef7c0846cee3dd6e0e0356cf96daecea7047315f2298426331
+oid sha256:9552cb2d1c18caec54d8d99c1b129665a4681c147ff4aa16bd94bedaffdf4536
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ead8859c7ea9f3a268fbe46221a7181cfd65564e431fda1875416e8edfb78df
+oid sha256:7adca16c067fb98ad03e03ced90170c10d37bdadf7dc17a94e5c6ead1ee4aca0
 size 60753722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c7b6cb315312c6c82b23cb21e455823073a3e69e8631d21018c71ee2b3e5c9
+oid sha256:bc8736936d98cb02a1755b50506203ba1f9474aaf0b35e17745418df904e23bb
 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": 0.012202562538133009,
+  "epoch": 0.018303843807199512,
   "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": 5.3219,
       "step": 18
+    },
+    {
+      "epoch": 0.012812690665039659,
+      "grad_norm": 1.6282868385314941,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 5.0499,
+      "step": 21
+    },
+    {
+      "epoch": 0.01464307504575961,
+      "grad_norm": 1.859714388847351,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 5.0796,
+      "step": 24
+    },
+    {
+      "epoch": 0.01464307504575961,
+      "eval_loss": 5.20974063873291,
+      "eval_runtime": 12.3822,
+      "eval_samples_per_second": 55.806,
+      "eval_steps_per_second": 27.943,
+      "step": 24
+    },
+    {
+      "epoch": 0.01647345942647956,
+      "grad_norm": 1.4957493543624878,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 4.874,
+      "step": 27
+    },
+    {
+      "epoch": 0.018303843807199512,
+      "grad_norm": 1.566078543663025,
+      "learning_rate": 0.0,
+      "loss": 4.8825,
+      "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": 310615725834240.0,
+  "total_flos": 465923588751360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null