Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e959f2bedd4d1c06f7560c91048e25cb09d9cd0bf6f1c8ec525e1b2a50b2be5
+oid sha256:8e7a69d1ce9bf6667ee18a34b80700a6f021f75a39b502df24c940c33a248326
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ea726ba9fc9c9eb1066b46bde05b501eb2ebeaedc9625cd740c2148848db790
+oid sha256:7ffb5918dd4da0749e42b25da719356fb52e940925d48e3da3d388b6dd555958
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840146a001ff48fd14f9176d2551e18a68e4936bbf1b797f6c21c89adb36c9a6
+oid sha256:3a31f9a55784a31138651f313f71945c76da95fef110e5c73e597379ef000db0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d82c151815973da3ac2e374434a38a206899c333d88de9e900733b7877b8460
+oid sha256:1a68cf1fb54f09702759cafde2c8a6d257515638ebe6138585b95a632f1a49e6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00010895535165339746,
+  "epoch": 0.0001245204018895971,
   "eval_steps": 500,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -56,6 +56,13 @@
       "learning_rate": 2.3166666666666666e-05,
       "loss": 3.5379,
       "step": 140
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.540940046310425,
+      "learning_rate": 2.6500000000000004e-05,
+      "loss": 3.16,
+      "step": 160
     }
   ],
   "logging_steps": 20,
@@ -63,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 721108975951872.0,
+  "total_flos": 817767151202304.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null