Training in progress, epoch 13, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbe4fcf585d74b0e916899724070c59a3cb8d2474f6f410d2870c72650b35c0
+oid sha256:ca3bdfcc66def65d0f604e01092775bb8047ff54f897ac825a782dab0065a2e0
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8adfeb763cfbe1cede3723bc945c0f7c532cd6940bf78aecd344894ff05f91f7
+oid sha256:1df3e4d97e5340b4a3c3b62168ce0a7e7d863568e262a8f917461eafc07a464b
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146c78d801fa79ef2403d0b4210ad68d562ba03db24c25eb1431ebd4394b2a57
+oid sha256:f4d452003ffd26a609202b256e3dbe796c6c31379217f192c3635c6946486885
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40a841847056be2f04abe72731f87a48fd8fa403be07c0dd5087b2da5fb38d8
+oid sha256:f69879333db32fd09e66a8372d09140f268c99379f91f2de1d978c4c8764223c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.0,
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 18324,
+  "global_step": 19851,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1288,6 +1288,111 @@
       "learning_rate": 8.1491344873502e-05,
       "loss": 0.1445,
       "step": 18300
+    },
+    {
+      "epoch": 12.049770792403406,
+      "grad_norm": 0.48655104637145996,
+      "learning_rate": 8.082556591211719e-05,
+      "loss": 0.1228,
+      "step": 18400
+    },
+    {
+      "epoch": 12.115258677144729,
+      "grad_norm": 0.5396549105644226,
+      "learning_rate": 8.015978695073236e-05,
+      "loss": 0.1227,
+      "step": 18500
+    },
+    {
+      "epoch": 12.180746561886052,
+      "grad_norm": 0.20431631803512573,
+      "learning_rate": 7.949400798934754e-05,
+      "loss": 0.1281,
+      "step": 18600
+    },
+    {
+      "epoch": 12.246234446627374,
+      "grad_norm": 0.40931564569473267,
+      "learning_rate": 7.882822902796272e-05,
+      "loss": 0.129,
+      "step": 18700
+    },
+    {
+      "epoch": 12.311722331368697,
+      "grad_norm": 0.3679026961326599,
+      "learning_rate": 7.81624500665779e-05,
+      "loss": 0.1291,
+      "step": 18800
+    },
+    {
+      "epoch": 12.37721021611002,
+      "grad_norm": 0.3819580674171448,
+      "learning_rate": 7.749667110519307e-05,
+      "loss": 0.126,
+      "step": 18900
+    },
+    {
+      "epoch": 12.442698100851343,
+      "grad_norm": 0.4266682267189026,
+      "learning_rate": 7.683089214380826e-05,
+      "loss": 0.1293,
+      "step": 19000
+    },
+    {
+      "epoch": 12.508185985592664,
+      "grad_norm": 0.22216545045375824,
+      "learning_rate": 7.616511318242345e-05,
+      "loss": 0.1338,
+      "step": 19100
+    },
+    {
+      "epoch": 12.573673870333987,
+      "grad_norm": 0.4221850037574768,
+      "learning_rate": 7.549933422103862e-05,
+      "loss": 0.1339,
+      "step": 19200
+    },
+    {
+      "epoch": 12.63916175507531,
+      "grad_norm": 0.5264990925788879,
+      "learning_rate": 7.48335552596538e-05,
+      "loss": 0.1355,
+      "step": 19300
+    },
+    {
+      "epoch": 12.704649639816633,
+      "grad_norm": 0.653891384601593,
+      "learning_rate": 7.416777629826898e-05,
+      "loss": 0.1317,
+      "step": 19400
+    },
+    {
+      "epoch": 12.770137524557956,
+      "grad_norm": 1.4240955114364624,
+      "learning_rate": 7.350199733688415e-05,
+      "loss": 0.1297,
+      "step": 19500
+    },
+    {
+      "epoch": 12.83562540929928,
+      "grad_norm": 0.33510828018188477,
+      "learning_rate": 7.283621837549934e-05,
+      "loss": 0.1378,
+      "step": 19600
+    },
+    {
+      "epoch": 12.901113294040602,
+      "grad_norm": 0.31254374980926514,
+      "learning_rate": 7.217043941411452e-05,
+      "loss": 0.1291,
+      "step": 19700
+    },
+    {
+      "epoch": 12.966601178781925,
+      "grad_norm": 0.5154318809509277,
+      "learning_rate": 7.15046604527297e-05,
+      "loss": 0.1359,
+      "step": 19800
     }
   ],
   "logging_steps": 100,
@@ -1307,7 +1412,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.898917943489331e+16,
+  "total_flos": 7.473827766861824e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null