Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cfec892e6af9c878db781c830af2c35029d6d16a91b807ea6733eb4283945b9
+oid sha256:c5d9a32f114f08eb934f4ec9fba53ffec5a94fbc412a3997f0b91cb3c8af52b6
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a870598cc3cf8d2eb0822c7f577a2e023bd8a63ce71bca3fbc2c7bef28e16e0
+oid sha256:f1d0c9b59f4f76d4e7cd830cf36f88fe5960114634e97b9a42452f0166aff020
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f8ec2561f103f3c818121a29d5f8b31a50fd3236b2e0a463a1a051665c6d22
+oid sha256:9619c9fda1c83ec1361351e8390c6c7568496d397fba61ffb6f069dd04cf8908
 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": 0.049072035231204784,
+  "epoch": 0.06291286568103177,
   "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": 1.461,
       "step": 35
+    },
+    {
+      "epoch": 0.05033029254482542,
+      "grad_norm": 0.7941172122955322,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2533,
+      "step": 40
+    },
+    {
+      "epoch": 0.05033029254482542,
+      "eval_loss": 1.3716589212417603,
+      "eval_runtime": 22.0355,
+      "eval_samples_per_second": 15.203,
+      "eval_steps_per_second": 7.624,
+      "step": 40
+    },
+    {
+      "epoch": 0.056621579112928595,
+      "grad_norm": 0.5609609484672546,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2299,
+      "step": 45
+    },
+    {
+      "epoch": 0.06291286568103177,
+      "grad_norm": 0.6352398991584778,
+      "learning_rate": 0.0,
+      "loss": 1.3598,
+      "step": 50
+    },
+    {
+      "epoch": 0.06291286568103177,
+      "eval_loss": 1.3645598888397217,
+      "eval_runtime": 21.8758,
+      "eval_samples_per_second": 15.314,
+      "eval_steps_per_second": 7.68,
+      "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": 6314374720389120.0,
+  "total_flos": 8077479350108160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null