Training in progress, step 28, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11067a4e0db7180e978b4680751a828e92fddd604955a774a9541dda8c89fec6
+oid sha256:2a97630e1368a66820f45555880867683aaedd1b9edef7426dd01954f07c44c7
 size 2964338224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c14bc07640d4fa6ba0101c179b86e554410d022d886f62d6db2e15e49478a47
+oid sha256:b54ea64d2f29eb6ff7803f2260dc4e913ae868b444699033e9ccf9ce687e519c
 size 1485440604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b568ba95f7567b0629ca524a99586d93f3235f65e98122124dda6ec920acd2
+oid sha256:9d5d8adae9a211748d1ef52614f55a092508613a69bda9bec818167bfeb4e47e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3788150807899462,
+  "epoch": 1.608617594254937,
   "eval_steps": 500,
-  "global_step": 24,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,34 @@
       "learning_rate": 3.694299546280657e-05,
       "loss": 2.0503,
       "step": 24
+    },
+    {
+      "epoch": 1.436265709156194,
+      "grad_norm": 1.3157715797424316,
+      "learning_rate": 3.5226715929283506e-05,
+      "loss": 2.0297,
+      "step": 25
+    },
+    {
+      "epoch": 1.4937163375224416,
+      "grad_norm": 1.367810606956482,
+      "learning_rate": 3.3450421960212566e-05,
+      "loss": 2.03,
+      "step": 26
+    },
+    {
+      "epoch": 1.5511669658886893,
+      "grad_norm": 1.4925018548965454,
+      "learning_rate": 3.162453755491655e-05,
+      "loss": 2.0478,
+      "step": 27
+    },
+    {
+      "epoch": 1.608617594254937,
+      "grad_norm": 1.350865125656128,
+      "learning_rate": 2.975977772911671e-05,
+      "loss": 2.1047,
+      "step": 28
     }
   ],
   "logging_steps": 1,
@@ -194,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6461756269580288e+16,
+  "total_flos": 1.919402630957875e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null