Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185c3f2d97734325851ebca16a89e4129bd9ec7f8da233875f91261adf4bf855
+oid sha256:7b6c1e4879e0c9dd37b9cec066a764f102a3b4b403481e06624a5a5ca9ced14c
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70bdca56d2ef364a208309c6440e0c3a1cc7339f9d0af0f36108e888f1c86aaa
+oid sha256:01b67f105ff11f908ba778e32f07290beaa91773a232f6c3d0471e1c5171d0dc
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0473a82658c627429c106558fb3bb262aa9211c031722dafa14ae2d5bab0f9e
+oid sha256:3b397ac926f0b3026b0cd0d9b3b6e1a67602cebbd3b8482e388a419e4c49512e
 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": 0.002871341800110436,
+  "epoch": 0.003681207436039021,
   "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": 3.0609,
       "step": 35
+    },
+    {
+      "epoch": 0.0029449659488312166,
+      "grad_norm": 3.932966470718384,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6458,
+      "step": 40
+    },
+    {
+      "epoch": 0.0029449659488312166,
+      "eval_loss": 3.0266425609588623,
+      "eval_runtime": 236.2487,
+      "eval_samples_per_second": 24.208,
+      "eval_steps_per_second": 12.106,
+      "step": 40
+    },
+    {
+      "epoch": 0.0033130866924351186,
+      "grad_norm": 4.188052654266357,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.2045,
+      "step": 45
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "grad_norm": 5.825687408447266,
+      "learning_rate": 0.0,
+      "loss": 3.243,
+      "step": 50
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "eval_loss": 3.0219552516937256,
+      "eval_runtime": 238.5537,
+      "eval_samples_per_second": 23.974,
+      "eval_steps_per_second": 11.989,
+      "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": 1950379589763072.0,
+  "total_flos": 2512989086810112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null