Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34d6ac8e378f7f7b5b26938959c599e74c7adad514f025c4f120cc1fa70a1690
+oid sha256:a9fcc5c762a175b2ce3eb9d2790e5668ee790dddb0bb7182c862b44c910204b1
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d0cf19fb22932d83fb7308a8e0e9a1c19d2cdbeacd4f013c614b2c92677b22a
+oid sha256:650b1d448b560c9692d030b8e5b608d90b164a397dc1c481a1a71a7adfed84fd
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c2def82317e76f5437c5ec08617a234bd54bf365c5bbe035a79848052de777
+oid sha256:8fd799c8eb49a6d2f2397175ae1f6391518eefd25afbf33d108d0bd67fc448f7
 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": 0.02198111878258419,
+  "epoch": 0.028180921516133578,
   "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": 0.623,
       "step": 35
+    },
+    {
+      "epoch": 0.02254473721290686,
+      "grad_norm": 6.412773609161377,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4103,
+      "step": 40
+    },
+    {
+      "epoch": 0.02254473721290686,
+      "eval_loss": 0.7003613114356995,
+      "eval_runtime": 47.7974,
+      "eval_samples_per_second": 15.628,
+      "eval_steps_per_second": 7.825,
+      "step": 40
+    },
+    {
+      "epoch": 0.02536282936452022,
+      "grad_norm": 4.594435691833496,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3075,
+      "step": 45
+    },
+    {
+      "epoch": 0.028180921516133578,
+      "grad_norm": 5.985153675079346,
+      "learning_rate": 0.0,
+      "loss": 0.2875,
+      "step": 50
+    },
+    {
+      "epoch": 0.028180921516133578,
+      "eval_loss": 0.6660094857215881,
+      "eval_runtime": 47.9977,
+      "eval_samples_per_second": 15.563,
+      "eval_steps_per_second": 7.792,
+      "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": 2888062084841472.0,
+  "total_flos": 3700720247242752.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null