Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebef43c353778570accaa7da465e23a8db90980be773c5e80faf4d55113f91b6
+oid sha256:b0ca951c98b3ac2ac34ca7506396b40d3e2fa72e71a87a9cf4c585d9191a2aa6
 size 1316913776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8620b538119ae7ba6b2309d187eccdd71127ec1cc43770dc44e2b2597c8a8335
+oid sha256:5b465d3e8d581244d9d30c6aa34bb357bb4a426ff425c3afe4820d8b9e28c1a4
 size 8908124

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1481322455989695,
+  "epoch": 0.15027908973808501,
   "eval_steps": 500,
-  "global_step": 690,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -490,6 +490,13 @@
       "learning_rate": 0.0004259338772005152,
       "loss": 0.8116,
       "step": 690
+    },
+    {
+      "epoch": 0.15027908973808501,
+      "grad_norm": 1.0387822389602661,
+      "learning_rate": 0.0004248604551309575,
+      "loss": 0.8233,
+      "step": 700
     }
   ],
   "logging_steps": 10,
@@ -497,7 +504,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 5.171204912024448e+16,
+  "total_flos": 5.24682523491817e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null