Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1589e42cbae5378987344eae93a5cbeb6aaea407f7da88b4a6f4a9d93d04e89
+oid sha256:c1281b650194f1fbbf19c77dce0688ee14dcd633838ccfe32e26ddcbfabc606a
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6cf8294ac17ea5a1d733fcc4cfdc564357fe4b651af698fb1c9e155e20e5cd8
+oid sha256:20441cfd1a765ce19bd0c3aa3fa3f6568100e50441051ecd815972d170df6441
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386ad13fe5d816f22a0cb03c574c387eb21070a41c3bcfa2c61c742027c54d4e
+oid sha256:1242a8006a137d7d7fdf5051a8f1d3180b356281e9f9b85b1f07ab3614b81f01
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb0b702704ac2295f35bde3f325d34f67803c665d4df40762f063d3651311c1
+oid sha256:e258cdfd2c36c8c2f0b10b58594d1a291f5e6c49df7a4537b7e3a4fcef2b8c0b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3170494985441605,
+  "epoch": 0.3235198964736331,
   "eval_steps": 386,
-  "global_step": 245,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1730,6 +1730,41 @@
       "learning_rate": 9.93550542947322e-05,
       "loss": 1.0134,
       "step": 245
+    },
+    {
+      "epoch": 0.318343578130055,
+      "grad_norm": 1.009790062904358,
+      "learning_rate": 9.9348436946805e-05,
+      "loss": 1.0264,
+      "step": 246
+    },
+    {
+      "epoch": 0.31963765771594954,
+      "grad_norm": 0.8702448606491089,
+      "learning_rate": 9.934178604651023e-05,
+      "loss": 1.0067,
+      "step": 247
+    },
+    {
+      "epoch": 0.32093173730184404,
+      "grad_norm": 0.8105303049087524,
+      "learning_rate": 9.933510159836989e-05,
+      "loss": 0.8121,
+      "step": 248
+    },
+    {
+      "epoch": 0.3222258168877386,
+      "grad_norm": 0.7680085897445679,
+      "learning_rate": 9.932838360692878e-05,
+      "loss": 0.8951,
+      "step": 249
+    },
+    {
+      "epoch": 0.3235198964736331,
+      "grad_norm": 0.8338052034378052,
+      "learning_rate": 9.93216320767545e-05,
+      "loss": 0.8878,
+      "step": 250
     }
   ],
   "logging_steps": 1,
@@ -1749,7 +1784,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7389460706492416e+17,
+  "total_flos": 2.79484292923392e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null