Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fb75a4a36553b73994dbd2353c33c1160b78c14db20d5475338392d9c4157d
+oid sha256:0120a8149bd4c9c80c434ee1d50d17d11b5ff6a9a540930d8477b8330665d7c6
 size 75579856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f97ab80c0e9ed284bc1431c9250044bcd13f5ab7aee843eb60252e95c35c049
+oid sha256:3cf508cce684f141d23779498e2107e05fe761d23d480c911d36daef0444c4a1
 size 39015574

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b432237b00d1d90d6724248db250f29e52844d78501ed7ee56e7727e8a88c36f
+oid sha256:923d278f6956e6477248046106bcc976164d13b97aca384b8661e5bb580c9f50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a625473bb0a513e1727ebc85c0930216deed7d5ec1e4fd299b7895bbd369bcc
+oid sha256:b8ccbb7e9b2bee49a3a83a2cbe68b9ea55fce3c23d9b7073b07177a5b6c6d109
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01383365035448729,
+  "epoch": 0.020750475531730934,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,76 @@
       "learning_rate": 2.6027397260273973e-05,
       "loss": 2.5836,
       "step": 20
+    },
+    {
+      "epoch": 0.014525332872211656,
+      "grad_norm": 0.2680312991142273,
+      "learning_rate": 2.7397260273972603e-05,
+      "loss": 2.748,
+      "step": 21
+    },
+    {
+      "epoch": 0.01521701538993602,
+      "grad_norm": 0.2818455398082733,
+      "learning_rate": 2.8767123287671234e-05,
+      "loss": 2.5701,
+      "step": 22
+    },
+    {
+      "epoch": 0.015908697907660384,
+      "grad_norm": 0.2324114739894867,
+      "learning_rate": 3.0136986301369862e-05,
+      "loss": 1.8337,
+      "step": 23
+    },
+    {
+      "epoch": 0.01660038042538475,
+      "grad_norm": 0.2770012617111206,
+      "learning_rate": 3.1506849315068496e-05,
+      "loss": 2.7497,
+      "step": 24
+    },
+    {
+      "epoch": 0.017292062943109112,
+      "grad_norm": 0.27101394534111023,
+      "learning_rate": 3.287671232876712e-05,
+      "loss": 2.8125,
+      "step": 25
+    },
+    {
+      "epoch": 0.017983745460833478,
+      "grad_norm": 0.27373552322387695,
+      "learning_rate": 3.424657534246575e-05,
+      "loss": 2.7676,
+      "step": 26
+    },
+    {
+      "epoch": 0.01867542797855784,
+      "grad_norm": 0.2803725302219391,
+      "learning_rate": 3.561643835616438e-05,
+      "loss": 2.2638,
+      "step": 27
+    },
+    {
+      "epoch": 0.019367110496282206,
+      "grad_norm": 0.25683945417404175,
+      "learning_rate": 3.698630136986301e-05,
+      "loss": 2.8515,
+      "step": 28
+    },
+    {
+      "epoch": 0.020058793014006572,
+      "grad_norm": 0.32016420364379883,
+      "learning_rate": 3.8356164383561644e-05,
+      "loss": 2.8561,
+      "step": 29
+    },
+    {
+      "epoch": 0.020750475531730934,
+      "grad_norm": 0.4947223663330078,
+      "learning_rate": 3.9726027397260274e-05,
+      "loss": 2.9034,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -167,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 673991251476480.0,
+  "total_flos": 1008346610073600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null