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:fb4ded60a90c72c0e6b07fcd89a16e60d01593440040c9c6a2f05e8821ca0d12
+oid sha256:651b8a59a1c811edc52f3342adf914e7a586adcbd5f0016e27ad91725449b67e
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9251aabb8d24da614d1959e780bcdab6362f9999ff3652228f3a64d0ad91b3e4
+oid sha256:ebc67965dbedf537595fe61aa0521ce53b58f6e74d524aa51c3428d5ec333605
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c9505ea107c50a3d49a2c1d2ec340dba41b0aaaed777de49785c68de5108ca
+oid sha256:1cfcd7c29d7918a765c61e4c786e26410f90d1371e3ec74f445ed22134f97b7f
 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": 0.022168537729145944,
+  "epoch": 0.028421202216853774,
   "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": 10.1476,
       "step": 35
+    },
+    {
+      "epoch": 0.022736961773483017,
+      "grad_norm": 27.225990295410156,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 9.8778,
+      "step": 40
+    },
+    {
+      "epoch": 0.022736961773483017,
+      "eval_loss": 2.679257869720459,
+      "eval_runtime": 15.4476,
+      "eval_samples_per_second": 47.969,
+      "eval_steps_per_second": 24.017,
+      "step": 40
+    },
+    {
+      "epoch": 0.025579081995168396,
+      "grad_norm": 66.36029815673828,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.9107,
+      "step": 45
+    },
+    {
+      "epoch": 0.028421202216853774,
+      "grad_norm": 37.51848220825195,
+      "learning_rate": 0.0,
+      "loss": 11.0199,
+      "step": 50
+    },
+    {
+      "epoch": 0.028421202216853774,
+      "eval_loss": 2.678460121154785,
+      "eval_runtime": 15.2491,
+      "eval_samples_per_second": 48.593,
+      "eval_steps_per_second": 24.329,
+      "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": 392585331867648.0,
+  "total_flos": 495666396659712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null