Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824ae469c6063a0efa80795f36a5fecfcede9ef9c2aca4c3a0666be19ccecb6a
+oid sha256:4f070452bd24cff69a78f0ac2756480a665c8c2aacdff9b3bcd7c9b1700fdf45
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c763222db616c9f29a484a6203361406ff9384f9cb22f2ac97f7e9bec82ff737
+oid sha256:da9dac7d925bd1fe70721927bb0f6e127ace59e8cd20d3f571d2662255001aea
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec24b3854134798d2456e1dd854b45d6659c142bc296821da1aaf13f07c042eb
+oid sha256:68bd8c8e0925b342f12eb7af7f76dfd02dcd4f16cb8570a361136dfd35216850
 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": 0.005306122448979592,
+  "epoch": 0.010612244897959184,
   "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": 10.247,
       "eval_steps_per_second": 5.123,
       "step": 10
+    },
+    {
+      "epoch": 0.006122448979591836,
+      "grad_norm": 1.417625069618225,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.859,
+      "step": 15
+    },
+    {
+      "epoch": 0.00816326530612245,
+      "grad_norm": 2.1316819190979004,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.3143,
+      "step": 20
+    },
+    {
+      "epoch": 0.00816326530612245,
+      "eval_loss": 0.8414375185966492,
+      "eval_runtime": 100.4603,
+      "eval_samples_per_second": 10.273,
+      "eval_steps_per_second": 5.136,
+      "step": 20
+    },
+    {
+      "epoch": 0.01020408163265306,
+      "grad_norm": 1.9280800819396973,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.1387,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4493168439459840.0,
+  "total_flos": 9057657012879360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null