Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554ea26ca08449d35f8b0476fae37313909d9e4d128ae492139e63d6eb13785a
+oid sha256:384c9f7b14c24377dbdd5657cb4fac5c28ac39bce9f2acd02283a8f4f8885abb
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c10cfb9a07985bba82f063344246ca5030d04243ee6b91a544afbff8c7a57bc
+oid sha256:2fd2e1d02c220948331114e46510331e23f9c43e82e2b616f98428b11919d5e0
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0473a82658c627429c106558fb3bb262aa9211c031722dafa14ae2d5bab0f9e
+oid sha256:fc8b30dc45df2e7849e049e2f88f3af04b8eb2fec3f79a4131192a96147a0392
 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": 0.14233576642335766,
+  "epoch": 0.18248175182481752,
   "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": 0.1334,
       "step": 35
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 1.123745322227478,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.064,
+      "step": 40
+    },
+    {
+      "epoch": 0.145985401459854,
+      "eval_loss": 0.043108660727739334,
+      "eval_runtime": 6.4968,
+      "eval_samples_per_second": 17.855,
+      "eval_steps_per_second": 8.927,
+      "step": 40
+    },
+    {
+      "epoch": 0.16423357664233576,
+      "grad_norm": 1.209367036819458,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0385,
+      "step": 45
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "grad_norm": 0.65992271900177,
+      "learning_rate": 0.0,
+      "loss": 0.0407,
+      "step": 50
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "eval_loss": 0.03230349346995354,
+      "eval_runtime": 6.4146,
+      "eval_samples_per_second": 18.084,
+      "eval_steps_per_second": 9.042,
+      "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": 2500486653542400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null