Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847b2063d1d2aa49f6188ad12822d4b013f9c41fe29d682240e6c1c32b436eb3
+oid sha256:19ed79b11216a51a61c91ceb6718a283c1617543152b0ba5f4b575170cbc1765
 size 1316913776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d95ed848a5ac0b335b1bd8a3cbca22ee0d7326c275d680f9087b6d3454e96c5f
+oid sha256:79e122fe10c25f35bb9aa91f429c7959bcc622d43d2158400d186b24f4a4c6df
 size 8908124

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0837269214255045,
+  "epoch": 0.08587376556462001,
   "eval_steps": 500,
-  "global_step": 390,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -280,6 +280,13 @@
       "learning_rate": 0.0004581365392872477,
       "loss": 0.8653,
       "step": 390
+    },
+    {
+      "epoch": 0.08587376556462001,
+      "grad_norm": 1.3970990180969238,
+      "learning_rate": 0.00045706311721769,
+      "loss": 0.8542,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -287,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 2.90439342566208e+16,
+  "total_flos": 2.976872891771059e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null