Training in progress, epoch 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39522035318c6891143c58cce7395a4b46a8a32d402bd53320b7add7af03c143
+oid sha256:abebf746f56f14ea1c6d8ef79bf7cc69f037792b0bd636287cdb7f2c1a3928fe
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba91e1ab0bec10a4dbc402a346679b92ee39686ac168c1f648076e2d105ab8d9
+oid sha256:39486f905d3e2bd58da856bb1b74556d8f0907974bb974e1b3102d2f1446ad54
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b1acc767a23f92a1cf146ec9baf1cc3b239925a6b047467260fa5c92f3a706
+oid sha256:87d5c9286991fd6abcd75cd4294dab9742776362fd8071b1990965800ca9383a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e70a028bb791111f78798008505c773f2338175afcf5d4ca9cbdb950af0ca1
+oid sha256:3c9c5600295c02beca5e11de59b008919eaaa92fbaffaec029a47792351815c5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 29013,
+  "global_step": 30540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2037,6 +2037,111 @@
       "learning_rate": 1.0252996005326232e-05,
       "loss": 0.1057,
       "step": 29000
+    },
+    {
+      "epoch": 19.05697445972495,
+      "grad_norm": 0.29688164591789246,
+      "learning_rate": 9.587217043941411e-06,
+      "loss": 0.1004,
+      "step": 29100
+    },
+    {
+      "epoch": 19.122462344466275,
+      "grad_norm": 0.23096615076065063,
+      "learning_rate": 8.921438082556593e-06,
+      "loss": 0.1025,
+      "step": 29200
+    },
+    {
+      "epoch": 19.187950229207598,
+      "grad_norm": 0.14553728699684143,
+      "learning_rate": 8.255659121171772e-06,
+      "loss": 0.1039,
+      "step": 29300
+    },
+    {
+      "epoch": 19.25343811394892,
+      "grad_norm": 0.21273891627788544,
+      "learning_rate": 7.589880159786951e-06,
+      "loss": 0.0993,
+      "step": 29400
+    },
+    {
+      "epoch": 19.318925998690244,
+      "grad_norm": 0.26496270298957825,
+      "learning_rate": 6.92410119840213e-06,
+      "loss": 0.1045,
+      "step": 29500
+    },
+    {
+      "epoch": 19.384413883431566,
+      "grad_norm": 0.22591184079647064,
+      "learning_rate": 6.258322237017311e-06,
+      "loss": 0.1021,
+      "step": 29600
+    },
+    {
+      "epoch": 19.44990176817289,
+      "grad_norm": 0.45855116844177246,
+      "learning_rate": 5.59254327563249e-06,
+      "loss": 0.1057,
+      "step": 29700
+    },
+    {
+      "epoch": 19.515389652914212,
+      "grad_norm": 0.2156517505645752,
+      "learning_rate": 4.92676431424767e-06,
+      "loss": 0.0985,
+      "step": 29800
+    },
+    {
+      "epoch": 19.580877537655535,
+      "grad_norm": 0.4062209725379944,
+      "learning_rate": 4.26098535286285e-06,
+      "loss": 0.1022,
+      "step": 29900
+    },
+    {
+      "epoch": 19.64636542239686,
+      "grad_norm": 0.27822694182395935,
+      "learning_rate": 3.5952063914780293e-06,
+      "loss": 0.1059,
+      "step": 30000
+    },
+    {
+      "epoch": 19.711853307138178,
+      "grad_norm": 0.35251957178115845,
+      "learning_rate": 2.9294274300932092e-06,
+      "loss": 0.1044,
+      "step": 30100
+    },
+    {
+      "epoch": 19.7773411918795,
+      "grad_norm": 0.3081159293651581,
+      "learning_rate": 2.2636484687083888e-06,
+      "loss": 0.1057,
+      "step": 30200
+    },
+    {
+      "epoch": 19.842829076620824,
+      "grad_norm": 0.22974246740341187,
+      "learning_rate": 1.5978695073235687e-06,
+      "loss": 0.1019,
+      "step": 30300
+    },
+    {
+      "epoch": 19.908316961362146,
+      "grad_norm": 0.4793023467063904,
+      "learning_rate": 9.320905459387485e-07,
+      "loss": 0.0999,
+      "step": 30400
+    },
+    {
+      "epoch": 19.97380484610347,
+      "grad_norm": 0.38982269167900085,
+      "learning_rate": 2.6631158455392814e-07,
+      "loss": 0.1012,
+      "step": 30500
     }
   ],
   "logging_steps": 100,
@@ -2051,12 +2156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0923286703741338e+17,
+  "total_flos": 1.1498196528791552e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null