Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a97630e1368a66820f45555880867683aaedd1b9edef7426dd01954f07c44c7
+oid sha256:08937cd1e8bfffe175abb463e0bd6963aa388dd72a8c09ab9eaf7e6bfe3213d4
 size 2964338224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54ea64d2f29eb6ff7803f2260dc4e913ae868b444699033e9ccf9ce687e519c
+oid sha256:366717366a781f891e5238670ada9d71d90db2961275233e493342f4828f2954
 size 1485440604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d5d8adae9a211748d1ef52614f55a092508613a69bda9bec818167bfeb4e47e
+oid sha256:f2d462d07679545eba1e8a66c26224b42aa8eadb6caa3ceb233445f0ef2c747c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.608617594254937,
+  "epoch": 1.8384201077199283,
   "eval_steps": 500,
-  "global_step": 28,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,34 @@
       "learning_rate": 2.975977772911671e-05,
       "loss": 2.1047,
       "step": 28
+    },
+    {
+      "epoch": 1.666068222621185,
+      "grad_norm": 1.3046050071716309,
+      "learning_rate": 2.7867085634960016e-05,
+      "loss": 2.0175,
+      "step": 29
+    },
+    {
+      "epoch": 1.7235188509874326,
+      "grad_norm": 1.3713139295578003,
+      "learning_rate": 2.595756834225089e-05,
+      "loss": 2.0437,
+      "step": 30
+    },
+    {
+      "epoch": 1.7809694793536806,
+      "grad_norm": 1.2804160118103027,
+      "learning_rate": 2.4042431657749117e-05,
+      "loss": 2.0573,
+      "step": 31
+    },
+    {
+      "epoch": 1.8384201077199283,
+      "grad_norm": 1.257683277130127,
+      "learning_rate": 2.2132914365039993e-05,
+      "loss": 2.0105,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -222,7 +250,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.919402630957875e+16,
+  "total_flos": 2.1877250611040256e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null