Training in progress, step 235, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9dc04d9131f70be891a19381878614c297c393a909fdfe2b429dde61e4fcefa
+oid sha256:d1d444d1bb45f270e0c212f44c95682120889252458945d6a4d19bcbbfffc231
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0cd8f2a46be5f132346e24f7e0d29bb24f82edd72eb9fee14693d4eecfd4237
+oid sha256:63de950bd110c9cc3cfce72263ab1713819eea42a4aca0e3762bb97c75bdd431
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe870df998feb02da0faa0e10164a513510cb4301dca9513fbf4cb6ab260322
+oid sha256:e93008c0a80496fa52f28860e36ff15ef6ec8281cd46549629ed9ab1ae896a41
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:406b12b84118dfa4a046518d4e2a656e48bb88fb0ae0e36c6b540e90cacbc244
+oid sha256:5f21939c458dd70022a2e060c2bded3f42858a595a1129248ef019a10b6eabb0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2976383047557425,
+  "epoch": 0.3041087026852151,
   "eval_steps": 386,
-  "global_step": 230,
+  "global_step": 235,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1625,6 +1625,41 @@
       "learning_rate": 9.945028522440653e-05,
       "loss": 0.8986,
       "step": 230
+    },
+    {
+      "epoch": 0.298932384341637,
+      "grad_norm": 0.9039688110351562,
+      "learning_rate": 9.944417168911275e-05,
+      "loss": 1.0461,
+      "step": 231
+    },
+    {
+      "epoch": 0.30022646392753155,
+      "grad_norm": 0.8048250675201416,
+      "learning_rate": 9.943802453636065e-05,
+      "loss": 0.89,
+      "step": 232
+    },
+    {
+      "epoch": 0.30152054351342605,
+      "grad_norm": 0.8166521787643433,
+      "learning_rate": 9.94318437703297e-05,
+      "loss": 0.9149,
+      "step": 233
+    },
+    {
+      "epoch": 0.3028146230993206,
+      "grad_norm": 0.7571333646774292,
+      "learning_rate": 9.942562939522228e-05,
+      "loss": 0.9655,
+      "step": 234
+    },
+    {
+      "epoch": 0.3041087026852151,
+      "grad_norm": 0.6913223266601562,
+      "learning_rate": 9.941938141526354e-05,
+      "loss": 0.869,
+      "step": 235
     }
   ],
   "logging_steps": 1,
@@ -1644,7 +1679,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5712554948952064e+17,
+  "total_flos": 2.6271523534798848e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null