Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35cbdd7d2c2b118733466af6b07c125b07a95ba4283700751f1a849a9528f13f
+oid sha256:3bc5fceae0c2ede03dee2fa3299b0a9fd3d90caf15846705c2756417741d3267
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3a9c6142b2216994f7ca0cf696e7bbc47e0b8d8c0920e46fedcfd16b77b6fd
+oid sha256:be320abd8552937e785067732021e3200d08f672cde43eb356d454da0cee6e48
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb4f84e3df39bc4065fc2ef04f4d348327ebe5cfd5943e53bd9f635d7b1e00ee
+oid sha256:06532dcf57c168372af4ac42ace76421e377a25a4e8206983f54ebe52ac1849c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006900120752113162,
+  "epoch": 0.010350181128169742,
   "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": 0.00013090169943749476,
       "loss": 0.5395,
       "step": 18
+    },
+    {
+      "epoch": 0.00724512678971882,
+      "grad_norm": 1.662941336631775,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.3747,
+      "step": 21
+    },
+    {
+      "epoch": 0.008280144902535794,
+      "grad_norm": 1.672710657119751,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.3137,
+      "step": 24
+    },
+    {
+      "epoch": 0.008280144902535794,
+      "eval_loss": 0.279544860124588,
+      "eval_runtime": 116.0751,
+      "eval_samples_per_second": 10.519,
+      "eval_steps_per_second": 5.264,
+      "step": 24
+    },
+    {
+      "epoch": 0.009315163015352769,
+      "grad_norm": 1.0861223936080933,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.2541,
+      "step": 27
+    },
+    {
+      "epoch": 0.010350181128169742,
+      "grad_norm": 1.507712483406067,
+      "learning_rate": 0.0,
+      "loss": 0.2888,
+      "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": 3443213708820480.0,
+  "total_flos": 5140226179596288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null