Training in progress, step 6231, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621b09bb6b65a042a5d1aa984f1ae3eb550edf44591c3ce5197e723ddb0e6861
+oid sha256:e6a61484c58f2aa5fbb2745552311c9a00798baf432791d1aac6c666b0179b94
 size 4286680

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195d742d70a90ac9fb452296d7eed8e0fb39376173bfdf06b4bb9201d7b249d4
+oid sha256:ae7143c1ac9958839859c3afbfc24d10d8f0514fbf676a7e123d6adb0f7dcc43
 size 8583659

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b384bb028283a2e480a81f100ae4848f22377168030cffb15ea66c728719f08
+oid sha256:9c1211409034a159c109d0b39b882945cb5b76df53eb397f96427985907baedf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38f6745e10494f0fc63c59b1b0a804a10928aac9839af7d5ce6caa7feff5dbdd
+oid sha256:28d686c5d1ce4e1ba39c740cc5b18a76a7041ecc94d8a5e148ede93ef04e7c8a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9971516829141092,
+  "epoch": 0.9998796485738356,
   "eval_steps": 500,
-  "global_step": 6214,
+  "global_step": 6231,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43505,6 +43505,125 @@
       "learning_rate": 1.89702134845704e-09,
       "loss": 32.7734,
       "step": 6214
+    },
+    {
+      "epoch": 0.9973121514823284,
+      "grad_norm": 12.067755699157715,
+      "learning_rate": 1.680407667342676e-09,
+      "loss": 32.7109,
+      "step": 6215
+    },
+    {
+      "epoch": 0.9974726200505476,
+      "grad_norm": 12.38700008392334,
+      "learning_rate": 1.4769218031618349e-09,
+      "loss": 32.5391,
+      "step": 6216
+    },
+    {
+      "epoch": 0.9976330886187668,
+      "grad_norm": 12.381599426269531,
+      "learning_rate": 1.2865638093439992e-09,
+      "loss": 32.6172,
+      "step": 6217
+    },
+    {
+      "epoch": 0.997793557186986,
+      "grad_norm": 12.004240989685059,
+      "learning_rate": 1.1093337358658585e-09,
+      "loss": 32.6016,
+      "step": 6218
+    },
+    {
+      "epoch": 0.9979540257552052,
+      "grad_norm": 12.466684341430664,
+      "learning_rate": 9.45231629273513e-10,
+      "loss": 32.625,
+      "step": 6219
+    },
+    {
+      "epoch": 0.9981144943234244,
+      "grad_norm": 12.143556594848633,
+      "learning_rate": 7.942575326380653e-10,
+      "loss": 32.6562,
+      "step": 6220
+    },
+    {
+      "epoch": 0.9982749628916436,
+      "grad_norm": 12.071325302124023,
+      "learning_rate": 6.564114856111304e-10,
+      "loss": 32.7344,
+      "step": 6221
+    },
+    {
+      "epoch": 0.9984354314598628,
+      "grad_norm": 12.138935089111328,
+      "learning_rate": 5.316935243859789e-10,
+      "loss": 32.8047,
+      "step": 6222
+    },
+    {
+      "epoch": 0.998595900028082,
+      "grad_norm": 12.325695991516113,
+      "learning_rate": 4.20103681708639e-10,
+      "loss": 32.5938,
+      "step": 6223
+    },
+    {
+      "epoch": 0.9987563685963012,
+      "grad_norm": 12.195591926574707,
+      "learning_rate": 3.216419868723453e-10,
+      "loss": 32.5938,
+      "step": 6224
+    },
+    {
+      "epoch": 0.9989168371645204,
+      "grad_norm": 12.133679389953613,
+      "learning_rate": 2.3630846573419183e-10,
+      "loss": 32.6016,
+      "step": 6225
+    },
+    {
+      "epoch": 0.9990773057327396,
+      "grad_norm": 12.008955001831055,
+      "learning_rate": 1.6410314070403054e-10,
+      "loss": 32.625,
+      "step": 6226
+    },
+    {
+      "epoch": 0.9992377743009588,
+      "grad_norm": 12.204169273376465,
+      "learning_rate": 1.0502603073336836e-10,
+      "loss": 32.6797,
+      "step": 6227
+    },
+    {
+      "epoch": 0.999398242869178,
+      "grad_norm": 12.070178031921387,
+      "learning_rate": 5.907715133202096e-11,
+      "loss": 32.6016,
+      "step": 6228
+    },
+    {
+      "epoch": 0.9995587114373972,
+      "grad_norm": 12.140969276428223,
+      "learning_rate": 2.6256514579214854e-11,
+      "loss": 32.6406,
+      "step": 6229
+    },
+    {
+      "epoch": 0.9997191800056164,
+      "grad_norm": 12.390560150146484,
+      "learning_rate": 6.564129073627356e-12,
+      "loss": 32.6172,
+      "step": 6230
+    },
+    {
+      "epoch": 0.9998796485738356,
+      "grad_norm": 12.162409782409668,
+      "learning_rate": 0.0,
+      "loss": 32.75,
+      "step": 6231
     }
   ],
   "logging_steps": 1,
@@ -43519,12 +43638,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2607409105207296.0,
+  "total_flos": 2614542345437184.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null