Training in progress, step 390, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacc218551180e6caca9be38e56e1c8a8c92bb7ca702a41f927879e57aea7285
+oid sha256:847b2063d1d2aa49f6188ad12822d4b013f9c41fe29d682240e6c1c32b436eb3
 size 1316913776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e3c344d56e84dfa5f4ffbbc603b4c3d0efce27c670f812e55f42803d067aed
+oid sha256:d95ed848a5ac0b335b1bd8a3cbca22ee0d7326c275d680f9087b6d3454e96c5f
 size 8908124

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08158007728638901,
+  "epoch": 0.0837269214255045,
   "eval_steps": 500,
-  "global_step": 380,
+  "global_step": 390,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,13 @@
       "learning_rate": 0.0004592099613568055,
       "loss": 0.8697,
       "step": 380
+    },
+    {
+      "epoch": 0.0837269214255045,
+      "grad_norm": 1.1009331941604614,
+      "learning_rate": 0.0004581365392872477,
+      "loss": 0.8653,
+      "step": 390
     }
   ],
   "logging_steps": 10,
@@ -280,7 +287,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 2.832153719613005e+16,
+  "total_flos": 2.90439342566208e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null