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:e84944919d86221cd4fd6600f5d8e5ae84770ab5e3234b79dd67b929a6a10d47
+oid sha256:f6385f63d52f2a2d5c9a8cb3801bdbb1d909cb14e84da813c335f30ac71c54a9
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e980fe4bf18fde0942f42e4cd17ac5d5471b4f75829cfef3707c93aaf34ca06f
+oid sha256:42b437e7e11af87788a9087c69e0fcce6474735bec785598af22deec5b1a9b9d
 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:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003283654378958343,
+  "epoch": 0.0004925481568437514,
   "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": 10.3782,
       "step": 18
+    },
+    {
+      "epoch": 0.000344783709790626,
+      "grad_norm": 0.09610570222139359,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3811,
+      "step": 21
+    },
+    {
+      "epoch": 0.0003940385254750011,
+      "grad_norm": 0.0615416057407856,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3827,
+      "step": 24
+    },
+    {
+      "epoch": 0.0003940385254750011,
+      "eval_loss": 10.373649597167969,
+      "eval_runtime": 76.3786,
+      "eval_samples_per_second": 335.774,
+      "eval_steps_per_second": 167.887,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004432933411593763,
+      "grad_norm": 0.05280403047800064,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3698,
+      "step": 27
+    },
+    {
+      "epoch": 0.0004925481568437514,
+      "grad_norm": 0.05877093970775604,
+      "learning_rate": 0.0,
+      "loss": 10.3763,
+      "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": 523024465920.0,
+  "total_flos": 784536698880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null