Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1efbf219a00b65bce48a32d63b2f2e6fca7f7347bcf30d96d1ca9c580c566c8
+oid sha256:115244ecedfda202764066a9283b044d4f6f8ecd10b0e2174f26837ebec18113
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:033706564b49c45fa23eac93cc22d3a7b4f32180f1ef1d4f4bb64d049f4f1cfd
+oid sha256:8268a66f741d5224e040055843b8fae8b2b858b7540189b4dfe9005024bc65fe
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95769943b503fd37e5ac516a17484f5788998a9cd717e8fc51b80176db1e71d3
+oid sha256:d8a3f819f57d0d751243ebc959c033ebee4a23f980b357dd2c10d415f1bec5c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01274197500612595,
+  "epoch": 0.0254839500122519,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 16.62,
       "eval_steps_per_second": 8.31,
       "step": 10
+    },
+    {
+      "epoch": 0.014702278853222249,
+      "grad_norm": 0.8822070956230164,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.5342,
+      "step": 15
+    },
+    {
+      "epoch": 0.019603038470963,
+      "grad_norm": 1.0811736583709717,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.196,
+      "step": 20
+    },
+    {
+      "epoch": 0.019603038470963,
+      "eval_loss": 1.078147530555725,
+      "eval_runtime": 26.0768,
+      "eval_samples_per_second": 16.49,
+      "eval_steps_per_second": 8.245,
+      "step": 20
+    },
+    {
+      "epoch": 0.02450379808870375,
+      "grad_norm": 0.7334229946136475,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.9801,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2177192599486464.0,
+  "total_flos": 4313306093322240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null