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:bc6b42d6dfacd6cda3681b261552a5006481cb514d37ad1a62193fd4469afafd
+oid sha256:42f3d4fcef07f1899878cedd3fdf488f15884813ad8b88f57557330111df8b4c
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:796d9c8fad4458e6cebc7637575eb7e597350df1c3432911b53fe95152107508
+oid sha256:c2b6dc131d98052ac1029370a0c0620861ea858adb1789892dd1f63d0bfd9e18
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f40a4c065023b7c7e84169852874083c9c8aff5ea2268e61269a141fdbb1b4f
+oid sha256:9e331ef2a3c31b8085c139afa029f7a7bec4b0c238a8a66416325de12e6bb446
 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": 0.085199344620426,
+  "epoch": 0.10922992900054615,
   "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": 0.7678,
       "step": 35
+    },
+    {
+      "epoch": 0.08738394320043692,
+      "grad_norm": 14.080451965332031,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8416,
+      "step": 40
+    },
+    {
+      "epoch": 0.08738394320043692,
+      "eval_loss": 0.8112453818321228,
+      "eval_runtime": 15.2147,
+      "eval_samples_per_second": 12.685,
+      "eval_steps_per_second": 6.375,
+      "step": 40
+    },
+    {
+      "epoch": 0.09830693610049153,
+      "grad_norm": 9.87679386138916,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9493,
+      "step": 45
+    },
+    {
+      "epoch": 0.10922992900054615,
+      "grad_norm": 12.29512882232666,
+      "learning_rate": 0.0,
+      "loss": 0.7734,
+      "step": 50
+    },
+    {
+      "epoch": 0.10922992900054615,
+      "eval_loss": 0.8227449059486389,
+      "eval_runtime": 15.1364,
+      "eval_samples_per_second": 12.751,
+      "eval_steps_per_second": 6.408,
+      "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": 7501033808855040.0,
+  "total_flos": 9603234366750720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null