Training in progress, step 59, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e1fa113e6149ce9c6ce95ed8a7aeeab5f87e234d1b33709c3dbb7f598be74c
+oid sha256:b3aff3636ab3523c875e895edf1c22ffba31c1bd38d1a6e2f1984f4373d0f60d
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01036a507461b9269482d82d9e8e9d29fc4ea4955d2c69274168112f597313e8
+oid sha256:0796cbd549515f8a66cd097c13d51c18287da5b3a0bfc23819777bcfeb7ae594
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060fb8d01e61c5a9e60483fa6352a837a9ab184977ffc490aaafd24dbde173a4
+oid sha256:ea916cbeea5eaa52a1f1be13dd70aec5eda379a7398c920ae7786ff902929743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15089163237311384,
+  "epoch": 0.16186556927297668,
   "eval_steps": 500,
-  "global_step": 55,
+  "global_step": 59,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -392,6 +392,34 @@
       "learning_rate": 0.00011000000000000002,
       "loss": 1.3694,
       "step": 55
+    },
+    {
+      "epoch": 0.15363511659807957,
+      "grad_norm": 0.15829141438007355,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.3351,
+      "step": 56
+    },
+    {
+      "epoch": 0.15637860082304528,
+      "grad_norm": 0.16939309239387512,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.3487,
+      "step": 57
+    },
+    {
+      "epoch": 0.15912208504801098,
+      "grad_norm": 0.19683969020843506,
+      "learning_rate": 0.000116,
+      "loss": 1.2837,
+      "step": 58
+    },
+    {
+      "epoch": 0.16186556927297668,
+      "grad_norm": 0.17148783802986145,
+      "learning_rate": 0.000118,
+      "loss": 1.3372,
+      "step": 59
     }
   ],
   "logging_steps": 1,
@@ -411,7 +439,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.802733722810368e+16,
+  "total_flos": 7.302877225272115e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null