Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b636730c560778e7305ad7be53017f729fb72353c9cbca3f821c51578fdecd
+oid sha256:5e4ac5ce372c6d76fefb432a9f34b1015e160cfbabf8028e778af0ff0e1f8b9a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9659a60cd3476c71cddfb124b57e609e5b6ca6c9642736235b28838ce927c7e3
+oid sha256:1bac2277ba6440576f9709acb98e17f2cf16dde69bad7c2cbf1ec833c966ec34
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03822592501837785,
+  "epoch": 0.0490075961774075,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.9605,
       "step": 35
+    },
+    {
+      "epoch": 0.039206076941926,
+      "grad_norm": 10.360566139221191,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7756,
+      "step": 40
+    },
+    {
+      "epoch": 0.039206076941926,
+      "eval_loss": 0.23207147419452667,
+      "eval_runtime": 27.4395,
+      "eval_samples_per_second": 15.671,
+      "eval_steps_per_second": 7.835,
+      "step": 40
+    },
+    {
+      "epoch": 0.04410683655966675,
+      "grad_norm": 6.0309343338012695,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7961,
+      "step": 45
+    },
+    {
+      "epoch": 0.0490075961774075,
+      "grad_norm": 5.921755313873291,
+      "learning_rate": 0.0,
+      "loss": 0.835,
+      "step": 50
+    },
+    {
+      "epoch": 0.0490075961774075,
+      "eval_loss": 0.2300577163696289,
+      "eval_runtime": 27.2186,
+      "eval_samples_per_second": 15.798,
+      "eval_steps_per_second": 7.899,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6838427232239616.0,
+  "total_flos": 8767214400307200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null