Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45817f6184797253d20be9a6676d89e8c9e44db9d5cb836318087cd0ca92ce6f
+oid sha256:ab3fac9a1d25f3cd0ba58676456cfbcf74dd4c147de99d98c1a257fd860a9e7a
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c0d4678a1ec8015a23cbf885c3cd7e91dc45bd58c18091de99439658dc680b
+oid sha256:24af03f061e9302f9219859e3ea7d5b5a900f23813bf144778ecd38d67e2d2df
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1048321c1ec07a37ac1cd38aed52e01fe92be66d6f78452e8cb0ec615000044
+oid sha256:f299d812da9c89d60c4a0b21f4bee9b4158ec2e31551f2287216dd140256762c
 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": 0.0148204446133384,
+  "epoch": 0.019000570017100513,
   "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": 72.7073,
       "step": 35
+    },
+    {
+      "epoch": 0.01520045601368041,
+      "grad_norm": 607.7332153320312,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 89.6675,
+      "step": 40
+    },
+    {
+      "epoch": 0.01520045601368041,
+      "eval_loss": 22.692827224731445,
+      "eval_runtime": 8.0814,
+      "eval_samples_per_second": 137.104,
+      "eval_steps_per_second": 68.552,
+      "step": 40
+    },
+    {
+      "epoch": 0.01710051301539046,
+      "grad_norm": 776.9797973632812,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 90.7522,
+      "step": 45
+    },
+    {
+      "epoch": 0.019000570017100513,
+      "grad_norm": 736.1396484375,
+      "learning_rate": 0.0,
+      "loss": 75.1007,
+      "step": 50
+    },
+    {
+      "epoch": 0.019000570017100513,
+      "eval_loss": 22.678951263427734,
+      "eval_runtime": 7.921,
+      "eval_samples_per_second": 139.88,
+      "eval_steps_per_second": 69.94,
+      "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": 43746154512384.0,
+  "total_flos": 55928627920896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null