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:b4f530370d0026afc9e09154946f051f8b4d247e5dbf813d6ef58bb9620c02e7
+oid sha256:03e3149bb9acf82f72aa927cb95ea673ddd83ed1877abab73db7b1b4efa7f949
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a27ed1a125cfdcabc4dd1994ef85990f76e7f83fcfffe2e0ebb21322b911553
+oid sha256:713bc6e2d555570892f7003e09cc4f95024099854437d8c2e1d645e4eb7e9b81
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a72025a75dfde9f6316cf7e78853946a2bfc45ed559fba6d15f16c4440f7ee5
+oid sha256:3ac9e56eb478bb7f690364dd51912aceda670c4f7d68fb18770d429dcec15f3a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ef6f22d42e935fbf13f0628837cd5d2513a098109335b9474dbc5e57db0c7d
+oid sha256:b99c176154c32f3c6148d434b4181fc39da3594f48ce393bb9e59b1fd24bca4d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4568081991215227,
+  "epoch": 0.5856515373352855,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 10.993,
       "eval_steps_per_second": 2.748,
       "step": 39
+    },
+    {
+      "epoch": 0.4685212298682284,
+      "grad_norm": 0.854839026927948,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8056,
+      "step": 40
+    },
+    {
+      "epoch": 0.4802342606149341,
+      "grad_norm": 0.286152720451355,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8081,
+      "step": 41
+    },
+    {
+      "epoch": 0.49194729136163984,
+      "grad_norm": 0.1939641833305359,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8028,
+      "step": 42
+    },
+    {
+      "epoch": 0.5036603221083455,
+      "grad_norm": 0.404239296913147,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8112,
+      "step": 43
+    },
+    {
+      "epoch": 0.5153733528550513,
+      "grad_norm": 0.49070852994918823,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8032,
+      "step": 44
+    },
+    {
+      "epoch": 0.527086383601757,
+      "grad_norm": 0.4219135344028473,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8068,
+      "step": 45
+    },
+    {
+      "epoch": 0.5387994143484627,
+      "grad_norm": 0.6313130855560303,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8108,
+      "step": 46
+    },
+    {
+      "epoch": 0.5505124450951684,
+      "grad_norm": 0.17373493313789368,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8009,
+      "step": 47
+    },
+    {
+      "epoch": 0.5622254758418741,
+      "grad_norm": 1.009384274482727,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8138,
+      "step": 48
+    },
+    {
+      "epoch": 0.5739385065885798,
+      "grad_norm": 0.4097265899181366,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8044,
+      "step": 49
+    },
+    {
+      "epoch": 0.5856515373352855,
+      "grad_norm": 0.5237875580787659,
+      "learning_rate": 0.0,
+      "loss": 0.8044,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.258753298834391e+17,
+  "total_flos": 1.1870196536967168e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null