Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b52bc73563ede699f4fb8025791d2954dc0576e8d1faeda6a4771a6f71f1f719
+oid sha256:4df0e2e2a1be68dab56094f7dbaea28ebdbdb5a797b4fbed0380957f39629f10
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eee95005a179bcd57d4897077e70944a808a7939d7b8a4fa53f0d11758ba4c3
+oid sha256:dbc277b01570ee96490e2d2749c2dc13bd0a7b15b94745a9b92f42235985a0a4
 size 323292202

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94cefb37789cdeb2602e19409b46d65eb248b69cff5a5a0795671a90fb540af
+oid sha256:b151d05ef25a3355874f53cc7e873a3f7c8f2f7d3efc50f990a795357c4893b5
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06622516556291391,
+  "epoch": 0.08278145695364239,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,20 @@
       "learning_rate": 2.2019867549668874e-05,
       "loss": 0.8786,
       "step": 400
+    },
+    {
+      "epoch": 0.07450331125827815,
+      "grad_norm": 2.6672778129577637,
+      "learning_rate": 2.477924944812362e-05,
+      "loss": 0.8348,
+      "step": 450
+    },
+    {
+      "epoch": 0.08278145695364239,
+      "grad_norm": 2.8199753761291504,
+      "learning_rate": 2.753863134657837e-05,
+      "loss": 0.8417,
+      "step": 500
     }
   ],
   "logging_steps": 50,
@@ -99,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3100779560828928.0,
+  "total_flos": 3898177609531392.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null