Training in progress, epoch 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693b8b9493a1341e036fe175f3c242fb0e70d29b2806414ec7f6d0e7af219541
+oid sha256:b274423009b5c07f11f58b77746b02b17f24e009f61c8110575044d63aa61d1a
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e052ac635caaca4a903cc21b648c6ca206f956c8750d678b1b4d52b5329dc6
+oid sha256:f893ec55f4313073798186de3601fec1586b266210af973437333cc0ed945ca6
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e87811f0f1effcce9b8f93da83987850561a5f540a92a1eae3e98079fa8bf27
+oid sha256:51eb010538f9bfc20098825581f682636ad0996150942740598bcbc86d52aa9d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681b81b0832ded00f66f265bc2327f35108bc92cae631f3148849c5007cbbcc8
+oid sha256:2539799723e10e9a07aa6c43c82d98ebd09ebb7f8d014c7067a0d2ccd17dc28b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.0,
+  "epoch": 16.0,
   "eval_steps": 500,
-  "global_step": 22905,
+  "global_step": 24432,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1610,6 +1610,111 @@
       "learning_rate": 5.086551264980027e-05,
       "loss": 0.1237,
       "step": 22900
+    },
+    {
+      "epoch": 15.062213490504258,
+      "grad_norm": 0.3952956795692444,
+      "learning_rate": 5.0199733688415454e-05,
+      "loss": 0.1104,
+      "step": 23000
+    },
+    {
+      "epoch": 15.127701375245579,
+      "grad_norm": 0.151408389210701,
+      "learning_rate": 4.953395472703063e-05,
+      "loss": 0.1075,
+      "step": 23100
+    },
+    {
+      "epoch": 15.193189259986902,
+      "grad_norm": 0.24425071477890015,
+      "learning_rate": 4.8868175765645806e-05,
+      "loss": 0.108,
+      "step": 23200
+    },
+    {
+      "epoch": 15.258677144728225,
+      "grad_norm": 0.2905368208885193,
+      "learning_rate": 4.820239680426098e-05,
+      "loss": 0.1132,
+      "step": 23300
+    },
+    {
+      "epoch": 15.324165029469548,
+      "grad_norm": 0.3744182586669922,
+      "learning_rate": 4.753661784287617e-05,
+      "loss": 0.1144,
+      "step": 23400
+    },
+    {
+      "epoch": 15.38965291421087,
+      "grad_norm": 0.15581925213336945,
+      "learning_rate": 4.687083888149135e-05,
+      "loss": 0.1156,
+      "step": 23500
+    },
+    {
+      "epoch": 15.455140798952193,
+      "grad_norm": 0.48975881934165955,
+      "learning_rate": 4.6205059920106524e-05,
+      "loss": 0.1179,
+      "step": 23600
+    },
+    {
+      "epoch": 15.520628683693516,
+      "grad_norm": 0.37415140867233276,
+      "learning_rate": 4.553928095872171e-05,
+      "loss": 0.12,
+      "step": 23700
+    },
+    {
+      "epoch": 15.58611656843484,
+      "grad_norm": 0.4051840305328369,
+      "learning_rate": 4.487350199733688e-05,
+      "loss": 0.1147,
+      "step": 23800
+    },
+    {
+      "epoch": 15.651604453176162,
+      "grad_norm": 0.22354257106781006,
+      "learning_rate": 4.4207723035952066e-05,
+      "loss": 0.1198,
+      "step": 23900
+    },
+    {
+      "epoch": 15.717092337917485,
+      "grad_norm": 0.43471258878707886,
+      "learning_rate": 4.354194407456725e-05,
+      "loss": 0.119,
+      "step": 24000
+    },
+    {
+      "epoch": 15.782580222658808,
+      "grad_norm": 0.6896039247512817,
+      "learning_rate": 4.2876165113182425e-05,
+      "loss": 0.1203,
+      "step": 24100
+    },
+    {
+      "epoch": 15.848068107400131,
+      "grad_norm": 0.2914521098136902,
+      "learning_rate": 4.22103861517976e-05,
+      "loss": 0.1182,
+      "step": 24200
+    },
+    {
+      "epoch": 15.913555992141454,
+      "grad_norm": 0.36893925070762634,
+      "learning_rate": 4.154460719041279e-05,
+      "loss": 0.1132,
+      "step": 24300
+    },
+    {
+      "epoch": 15.979043876882777,
+      "grad_norm": 0.30738958716392517,
+      "learning_rate": 4.087882822902797e-05,
+      "loss": 0.1186,
+      "step": 24400
     }
   ],
   "logging_steps": 100,
@@ -1629,7 +1734,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.62364741318738e+16,
+  "total_flos": 9.198557238237594e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null