Training in progress, step 89, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f243f6b3616c8433386fc88ddf6327a577ba6287c4ed295e830c228fda35beb6
+oid sha256:4214ef0ee7f7d582fe2add79fbe93b96823ee44d17df992afcac821c8420d811
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f72706d984d21bee0f467c65e8399002645accd78908dfaafc210e8643a0d2
+oid sha256:26d1dcdcb23846ee16e878f1b8dc7af0f4f4ec206a90a4b73dde0ee17fe5e626
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d1c8adee9796452e76469ace59653b3f2ebccea698756c2275e8b6cf74ba43
+oid sha256:cf4df7a6f01855e97e0632ba1247237d498e93e227d9db04c0584a2eb317fae9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23045267489711935,
+  "epoch": 0.24417009602194786,
   "eval_steps": 500,
-  "global_step": 84,
+  "global_step": 89,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -595,6 +595,41 @@
       "learning_rate": 0.000168,
       "loss": 1.1982,
       "step": 84
+    },
+    {
+      "epoch": 0.23319615912208505,
+      "grad_norm": 0.10137173533439636,
+      "learning_rate": 0.00017,
+      "loss": 1.2697,
+      "step": 85
+    },
+    {
+      "epoch": 0.23593964334705075,
+      "grad_norm": 0.09000196307897568,
+      "learning_rate": 0.000172,
+      "loss": 1.3122,
+      "step": 86
+    },
+    {
+      "epoch": 0.23868312757201646,
+      "grad_norm": 0.12272510677576065,
+      "learning_rate": 0.000174,
+      "loss": 1.3238,
+      "step": 87
+    },
+    {
+      "epoch": 0.24142661179698216,
+      "grad_norm": 0.10101604461669922,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.3637,
+      "step": 88
+    },
+    {
+      "epoch": 0.24417009602194786,
+      "grad_norm": 0.10622192174196243,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.2577,
+      "step": 89
     }
   ],
   "logging_steps": 1,
@@ -614,7 +649,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0405766029849805e+17,
+  "total_flos": 1.1049531277218202e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null