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:f5c13f3f9e55eea6488b664ecb9a4ca0d06a6c77161160739d8381363125bb67
+oid sha256:0bb3ce749651ce9b473ee8dbeb6173458b01ad9e2393fcb4979f2ae1467c624e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f29991818cbeb6493c278179b12e4a510cde0cb7370d208e213a7a53e0b771
+oid sha256:6c1c13331295c58b9183af5c6a5971781210cff2212ccfb66bf6d52cfc1cd7ee
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
+oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
 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": 0.06074766355140187,
+  "epoch": 0.12149532710280374,
   "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": 11.618,
       "eval_steps_per_second": 5.873,
       "step": 10
+    },
+    {
+      "epoch": 0.07009345794392523,
+      "grad_norm": 2.114860773086548,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.5615,
+      "step": 15
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 1.852180004119873,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.4648,
+      "step": 20
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "eval_loss": 1.411849021911621,
+      "eval_runtime": 7.9752,
+      "eval_samples_per_second": 11.41,
+      "eval_steps_per_second": 5.768,
+      "step": 20
+    },
+    {
+      "epoch": 0.11682242990654206,
+      "grad_norm": 1.8431528806686401,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.3921,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null