Training in progress, epoch 19, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295e227f4e998576f2a46404ae9d148fa1bb1493bdc88784d107d552dda3652e
+oid sha256:39522035318c6891143c58cce7395a4b46a8a32d402bd53320b7add7af03c143
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455000c25f92a494a25f90dc3bd7687b765861d9cec6e730d66f542d1c742e67
+oid sha256:ba91e1ab0bec10a4dbc402a346679b92ee39686ac168c1f648076e2d105ab8d9
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eda51522553149ac7f04823b2f24de1e4a29a13d19516c47586480c30dd68505
+oid sha256:30b1acc767a23f92a1cf146ec9baf1cc3b239925a6b047467260fa5c92f3a706
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:030c8ec491c7b3efa0e75662d44f44352cd1301e27125b1e92d52f65f4a03185
+oid sha256:90e70a028bb791111f78798008505c773f2338175afcf5d4ca9cbdb950af0ca1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.0,
+  "epoch": 19.0,
   "eval_steps": 500,
-  "global_step": 27486,
+  "global_step": 29013,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1925,6 +1925,118 @@
       "learning_rate": 2.0905459387483356e-05,
       "loss": 0.109,
       "step": 27400
+    },
+    {
+      "epoch": 18.009168303863785,
+      "grad_norm": 0.23712952435016632,
+      "learning_rate": 2.0239680426098536e-05,
+      "loss": 0.1122,
+      "step": 27500
+    },
+    {
+      "epoch": 18.074656188605108,
+      "grad_norm": 0.295411080121994,
+      "learning_rate": 1.9573901464713715e-05,
+      "loss": 0.1043,
+      "step": 27600
+    },
+    {
+      "epoch": 18.14014407334643,
+      "grad_norm": 0.4246551990509033,
+      "learning_rate": 1.8908122503328895e-05,
+      "loss": 0.1063,
+      "step": 27700
+    },
+    {
+      "epoch": 18.205631958087753,
+      "grad_norm": 0.36956048011779785,
+      "learning_rate": 1.8242343541944078e-05,
+      "loss": 0.1062,
+      "step": 27800
+    },
+    {
+      "epoch": 18.271119842829076,
+      "grad_norm": 0.4467618763446808,
+      "learning_rate": 1.7576564580559254e-05,
+      "loss": 0.1034,
+      "step": 27900
+    },
+    {
+      "epoch": 18.3366077275704,
+      "grad_norm": 0.375034898519516,
+      "learning_rate": 1.6910785619174437e-05,
+      "loss": 0.1044,
+      "step": 28000
+    },
+    {
+      "epoch": 18.402095612311722,
+      "grad_norm": 0.37095317244529724,
+      "learning_rate": 1.6245006657789616e-05,
+      "loss": 0.1036,
+      "step": 28100
+    },
+    {
+      "epoch": 18.467583497053045,
+      "grad_norm": 0.2957724630832672,
+      "learning_rate": 1.5579227696404792e-05,
+      "loss": 0.1075,
+      "step": 28200
+    },
+    {
+      "epoch": 18.533071381794368,
+      "grad_norm": 0.2983064353466034,
+      "learning_rate": 1.4913448735019975e-05,
+      "loss": 0.1056,
+      "step": 28300
+    },
+    {
+      "epoch": 18.59855926653569,
+      "grad_norm": 0.30214086174964905,
+      "learning_rate": 1.4247669773635153e-05,
+      "loss": 0.1038,
+      "step": 28400
+    },
+    {
+      "epoch": 18.664047151277014,
+      "grad_norm": 0.2917056083679199,
+      "learning_rate": 1.3581890812250334e-05,
+      "loss": 0.1042,
+      "step": 28500
+    },
+    {
+      "epoch": 18.729535036018337,
+      "grad_norm": 0.40877100825309753,
+      "learning_rate": 1.2916111850865514e-05,
+      "loss": 0.1039,
+      "step": 28600
+    },
+    {
+      "epoch": 18.79502292075966,
+      "grad_norm": 0.15422676503658295,
+      "learning_rate": 1.2250332889480692e-05,
+      "loss": 0.1065,
+      "step": 28700
+    },
+    {
+      "epoch": 18.860510805500983,
+      "grad_norm": 0.3668764531612396,
+      "learning_rate": 1.1584553928095873e-05,
+      "loss": 0.1097,
+      "step": 28800
+    },
+    {
+      "epoch": 18.925998690242306,
+      "grad_norm": 0.2623516321182251,
+      "learning_rate": 1.0918774966711052e-05,
+      "loss": 0.1132,
+      "step": 28900
+    },
+    {
+      "epoch": 18.99148657498363,
+      "grad_norm": 0.22360046207904816,
+      "learning_rate": 1.0252996005326232e-05,
+      "loss": 0.1057,
+      "step": 29000
     }
   ],
   "logging_steps": 100,
@@ -1944,7 +2056,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0348376881627136e+17,
+  "total_flos": 1.0923286703741338e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null