Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4e0ebf76da4865efdca1d9c017eb12953429c6450d8ac7b6d1413f7893ddfd
+oid sha256:42c419fc88b90857dd2e619356fef903c6214d5b290045a8f44dcae6558bcc0e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98269e6cfde63cb38f575aa650ba0cffaf95774142b0cf43b9d50b5c3ffa4e05
+oid sha256:a9a2183f7acb1c95f28072e3c9c72ab685f82f9bcf44b217ab3ca9215d92d87c
 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": 0.06792576062700702,
+  "epoch": 0.08708430849616285,
   "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": 10.98,
       "eval_steps_per_second": 2.745,
       "step": 39
+    },
+    {
+      "epoch": 0.06966744679693028,
+      "grad_norm": 0.39408788084983826,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1016,
+      "step": 40
+    },
+    {
+      "epoch": 0.07140913296685354,
+      "grad_norm": 0.3007913827896118,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0745,
+      "step": 41
+    },
+    {
+      "epoch": 0.07315081913677679,
+      "grad_norm": 0.33744704723358154,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.086,
+      "step": 42
+    },
+    {
+      "epoch": 0.07489250530670005,
+      "grad_norm": 0.37013643980026245,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0786,
+      "step": 43
+    },
+    {
+      "epoch": 0.0766341914766233,
+      "grad_norm": 0.3822749853134155,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0882,
+      "step": 44
+    },
+    {
+      "epoch": 0.07837587764654656,
+      "grad_norm": 0.27670085430145264,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0661,
+      "step": 45
+    },
+    {
+      "epoch": 0.08011756381646983,
+      "grad_norm": 0.33175578713417053,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0792,
+      "step": 46
+    },
+    {
+      "epoch": 0.08185924998639307,
+      "grad_norm": 0.2966095209121704,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0705,
+      "step": 47
+    },
+    {
+      "epoch": 0.08360093615631634,
+      "grad_norm": 0.3922402262687683,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0891,
+      "step": 48
+    },
+    {
+      "epoch": 0.08534262232623958,
+      "grad_norm": 0.40399035811424255,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0725,
+      "step": 49
+    },
+    {
+      "epoch": 0.08708430849616285,
+      "grad_norm": 0.34264397621154785,
+      "learning_rate": 0.0,
+      "loss": 0.0832,
+      "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