Training in progress, epoch 14, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3bdfcc66def65d0f604e01092775bb8047ff54f897ac825a782dab0065a2e0
+oid sha256:6dc59b48fb66813ca78955fa135a5b9c5eeb223b35e78585ef359fa563ac2307
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df3e4d97e5340b4a3c3b62168ce0a7e7d863568e262a8f917461eafc07a464b
+oid sha256:dbfbdfc4b321b15c27cff0da422d2a53f2a28df1c3baf392c51ed726dc694b44
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d452003ffd26a609202b256e3dbe796c6c31379217f192c3635c6946486885
+oid sha256:83dc8405814a784ea21d72ace0f4b91d221f004666d3673770e299e5a05e8fe9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69879333db32fd09e66a8372d09140f268c99379f91f2de1d978c4c8764223c
+oid sha256:30442933123d7669c460d45164eac302a9648bbc2949627d23d3db5a60c61873
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.0,
+  "epoch": 14.0,
   "eval_steps": 500,
-  "global_step": 19851,
+  "global_step": 21378,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1393,6 +1393,111 @@
       "learning_rate": 7.15046604527297e-05,
       "loss": 0.1359,
       "step": 19800
+    },
+    {
+      "epoch": 13.032089063523248,
+      "grad_norm": 0.3909270167350769,
+      "learning_rate": 7.083888149134487e-05,
+      "loss": 0.123,
+      "step": 19900
+    },
+    {
+      "epoch": 13.097576948264571,
+      "grad_norm": 0.3292842209339142,
+      "learning_rate": 7.017310252996006e-05,
+      "loss": 0.1235,
+      "step": 20000
+    },
+    {
+      "epoch": 13.163064833005894,
+      "grad_norm": 1.1147010326385498,
+      "learning_rate": 6.950732356857524e-05,
+      "loss": 0.1157,
+      "step": 20100
+    },
+    {
+      "epoch": 13.228552717747217,
+      "grad_norm": 0.22612357139587402,
+      "learning_rate": 6.884154460719041e-05,
+      "loss": 0.1228,
+      "step": 20200
+    },
+    {
+      "epoch": 13.29404060248854,
+      "grad_norm": 0.2340671569108963,
+      "learning_rate": 6.81757656458056e-05,
+      "loss": 0.1262,
+      "step": 20300
+    },
+    {
+      "epoch": 13.359528487229863,
+      "grad_norm": 0.470034658908844,
+      "learning_rate": 6.750998668442078e-05,
+      "loss": 0.1223,
+      "step": 20400
+    },
+    {
+      "epoch": 13.425016371971186,
+      "grad_norm": 1.8971284627914429,
+      "learning_rate": 6.684420772303596e-05,
+      "loss": 0.1256,
+      "step": 20500
+    },
+    {
+      "epoch": 13.490504256712509,
+      "grad_norm": 0.32659152150154114,
+      "learning_rate": 6.617842876165113e-05,
+      "loss": 0.128,
+      "step": 20600
+    },
+    {
+      "epoch": 13.555992141453832,
+      "grad_norm": 0.4042024314403534,
+      "learning_rate": 6.551264980026631e-05,
+      "loss": 0.1236,
+      "step": 20700
+    },
+    {
+      "epoch": 13.621480026195155,
+      "grad_norm": 0.37899136543273926,
+      "learning_rate": 6.484687083888148e-05,
+      "loss": 0.1229,
+      "step": 20800
+    },
+    {
+      "epoch": 13.686967910936477,
+      "grad_norm": 0.23778092861175537,
+      "learning_rate": 6.418109187749667e-05,
+      "loss": 0.1255,
+      "step": 20900
+    },
+    {
+      "epoch": 13.7524557956778,
+      "grad_norm": 0.637147843837738,
+      "learning_rate": 6.351531291611186e-05,
+      "loss": 0.127,
+      "step": 21000
+    },
+    {
+      "epoch": 13.817943680419123,
+      "grad_norm": 0.5459991693496704,
+      "learning_rate": 6.284953395472704e-05,
+      "loss": 0.1203,
+      "step": 21100
+    },
+    {
+      "epoch": 13.883431565160445,
+      "grad_norm": 0.516917884349823,
+      "learning_rate": 6.218375499334222e-05,
+      "loss": 0.1248,
+      "step": 21200
+    },
+    {
+      "epoch": 13.948919449901767,
+      "grad_norm": 0.34805047512054443,
+      "learning_rate": 6.151797603195739e-05,
+      "loss": 0.1316,
+      "step": 21300
     }
   ],
   "logging_steps": 100,
@@ -1412,7 +1517,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.473827766861824e+16,
+  "total_flos": 8.048737596945203e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null