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:ab1083db1159b2ffa4f39a5d3d6fda141d845635775bb20bb203f2f109220a92
+oid sha256:69a283733ea9210d23caf88cd25ca97107aa7d6714e850af20642a171923f22a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230e8147038da3d05c7c50b6668765f299a87bed70bd7533fbca83eaec6389df
+oid sha256:af667c14720c37b53e2fa10c89d76df6217dc5bd0c8fdee405be26a25896a039
 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": 0.564961521050249,
+  "epoch": 0.724309642372114,
   "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": 11.252,
       "eval_steps_per_second": 2.831,
       "step": 39
+    },
+    {
+      "epoch": 0.5794477138976912,
+      "grad_norm": 100.62445068359375,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 17.5808,
+      "step": 40
+    },
+    {
+      "epoch": 0.5939339067451336,
+      "grad_norm": 108.46626281738281,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 13.7374,
+      "step": 41
+    },
+    {
+      "epoch": 0.6084200995925758,
+      "grad_norm": 85.36103820800781,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 17.013,
+      "step": 42
+    },
+    {
+      "epoch": 0.6229062924400182,
+      "grad_norm": 83.11396789550781,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 13.9914,
+      "step": 43
+    },
+    {
+      "epoch": 0.6373924852874604,
+      "grad_norm": 93.9541015625,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 16.1954,
+      "step": 44
+    },
+    {
+      "epoch": 0.6518786781349026,
+      "grad_norm": 102.81454467773438,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 14.4745,
+      "step": 45
+    },
+    {
+      "epoch": 0.666364870982345,
+      "grad_norm": 111.78718566894531,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 15.9655,
+      "step": 46
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 186.56785583496094,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 14.6932,
+      "step": 47
+    },
+    {
+      "epoch": 0.6953372566772296,
+      "grad_norm": 69.18374633789062,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 13.9869,
+      "step": 48
+    },
+    {
+      "epoch": 0.7098234495246718,
+      "grad_norm": 95.9025650024414,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 16.5867,
+      "step": 49
+    },
+    {
+      "epoch": 0.724309642372114,
+      "grad_norm": 103.1650390625,
+      "learning_rate": 0.0,
+      "loss": 13.8776,
+      "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