Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29958b50b7f6d6e302c6caffa0a81330c869c07bbc5ea975cea05fbd4bc39436
+oid sha256:c267856d48781420842fbc77bcb77e3e5fe614dad166484ef9c360494b04b074
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98876f4ea44785ccb94a4f28375838455d061228e67289fc0f4d8d159118a54b
+oid sha256:122fe4f28e7c568ebd3b15c330efdcf721827963326fbce4c7b2c934621eaebf
 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": 0.10897659797415299,
+  "epoch": 0.13971358714635,
   "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": 11.163,
       "eval_steps_per_second": 2.792,
       "step": 39
+    },
+    {
+      "epoch": 0.11177086971707999,
+      "grad_norm": 20.202943801879883,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 32.6489,
+      "step": 40
+    },
+    {
+      "epoch": 0.11456514146000699,
+      "grad_norm": 19.53352928161621,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 33.9152,
+      "step": 41
+    },
+    {
+      "epoch": 0.11735941320293398,
+      "grad_norm": 18.473039627075195,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 32.9272,
+      "step": 42
+    },
+    {
+      "epoch": 0.12015368494586098,
+      "grad_norm": 21.347410202026367,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 32.0126,
+      "step": 43
+    },
+    {
+      "epoch": 0.12294795668878798,
+      "grad_norm": 18.974212646484375,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 32.8613,
+      "step": 44
+    },
+    {
+      "epoch": 0.12574222843171498,
+      "grad_norm": 20.034618377685547,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 33.6573,
+      "step": 45
+    },
+    {
+      "epoch": 0.128536500174642,
+      "grad_norm": 19.2609920501709,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 33.1644,
+      "step": 46
+    },
+    {
+      "epoch": 0.13133077191756898,
+      "grad_norm": 18.932796478271484,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 33.0339,
+      "step": 47
+    },
+    {
+      "epoch": 0.134125043660496,
+      "grad_norm": 18.432373046875,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 32.077,
+      "step": 48
+    },
+    {
+      "epoch": 0.13691931540342298,
+      "grad_norm": 19.448955535888672,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 35.2186,
+      "step": 49
+    },
+    {
+      "epoch": 0.13971358714635,
+      "grad_norm": 22.028099060058594,
+      "learning_rate": 0.0,
+      "loss": 31.1742,
+      "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": 8.775216947118735e+17,
+  "total_flos": 1.1250278137331712e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null