Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:285336f374782edb4dc7815d1f78bd38c5bee5b9c87c2d9cabc536b21e0685bf
+oid sha256:2c87e033946f515b83572d386a4f7e4fb76ef320be72b7f76289c0a5e86cd7bf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:378990590ff31f29eed477a6bb81dd76516a88e8109466cec6c2e01d796228d3
+oid sha256:b56b8c44d62b6b11f928f3f321e5fabbf6324447bc38d95fd2ddda1fdf817b1f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc49e406d40d15d4c77a549f46af25554828e4ccf4a2549a6e443a9a7b138dc
+oid sha256:ac74a516e27937bba2984006840b562b37397862f98eb3e48e06fc76f189dc23
 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": 0.00338409475465313,
+  "epoch": 0.005076142131979695,
   "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": 1.2201,
       "step": 18
+    },
+    {
+      "epoch": 0.003553299492385787,
+      "grad_norm": 1.1413564682006836,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.147,
+      "step": 21
+    },
+    {
+      "epoch": 0.0040609137055837565,
+      "grad_norm": 0.8211542367935181,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.1632,
+      "step": 24
+    },
+    {
+      "epoch": 0.0040609137055837565,
+      "eval_loss": 1.2106075286865234,
+      "eval_runtime": 210.9168,
+      "eval_samples_per_second": 11.801,
+      "eval_steps_per_second": 5.903,
+      "step": 24
+    },
+    {
+      "epoch": 0.004568527918781726,
+      "grad_norm": 1.643991470336914,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.0987,
+      "step": 27
+    },
+    {
+      "epoch": 0.005076142131979695,
+      "grad_norm": 0.818309485912323,
+      "learning_rate": 0.0,
+      "loss": 1.2318,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null