Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497a63d9df7b47b69459aafb78d21a688247f3b7553a7029718a7e7ec01a5ab0
+oid sha256:d7136f996b0f21b932c755adb995522b6911eb02f048367b49cc8c76fdf35501
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5651e26bed9ff6056393ba02a845493639292773b1802668eb98e3c4332ec90f
+oid sha256:2d1c040596727cf0883cc18daf8552a0bb61b5b778051570510785deaee2a35a
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0eae5d7a16af50a465a7bb79ae72882e8fae900ed86f42a6ea24998e162e19
+oid sha256:869d08cbdb3ebaf2562454c023dc210d37d7757b871f2faef0bdbc8f8e514f1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5520287054926856,
+  "epoch": 0.8280430582390285,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,41 @@
       "learning_rate": 9.996717238759354e-05,
       "loss": 0.5078,
       "step": 1000
+    },
+    {
+      "epoch": 0.6072315760419542,
+      "grad_norm": 1.3841311931610107,
+      "learning_rate": 9.986022415440564e-05,
+      "loss": 0.5091,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6624344465912227,
+      "grad_norm": 1.3825188875198364,
+      "learning_rate": 9.967918047007774e-05,
+      "loss": 0.4915,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7176373171404913,
+      "grad_norm": 1.248660683631897,
+      "learning_rate": 9.942431037699172e-05,
+      "loss": 0.5049,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7728401876897598,
+      "grad_norm": 1.2805066108703613,
+      "learning_rate": 9.909599262824883e-05,
+      "loss": 0.4787,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8280430582390285,
+      "grad_norm": 1.5455862283706665,
+      "learning_rate": 9.869471512481871e-05,
+      "loss": 0.4844,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -96,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.303975346705531e+17,
+  "total_flos": 7.944410411838996e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null