Training in progress, step 255, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1281b650194f1fbbf19c77dce0688ee14dcd633838ccfe32e26ddcbfabc606a
+oid sha256:4abad106b26a177c80a55998c565b87e8d8e322882f0ee0d82dfa1bc33ce78be
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20441cfd1a765ce19bd0c3aa3fa3f6568100e50441051ecd815972d170df6441
+oid sha256:15391496ce979fc31bfa4b89cf7a1b8ef5dc88ae859e2b82b3f5c1003f85f097
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1242a8006a137d7d7fdf5051a8f1d3180b356281e9f9b85b1f07ab3614b81f01
+oid sha256:92f080d6a96737273ff3f2c3aa9a0b978c372496e285abadb5ac87a0c88bd369
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e258cdfd2c36c8c2f0b10b58594d1a291f5e6c49df7a4537b7e3a4fcef2b8c0b
+oid sha256:727d568946636c509efe7945204da61e120d33ba9eb30256473171e8dfb29ed3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3235198964736331,
+  "epoch": 0.3299902944031058,
   "eval_steps": 386,
-  "global_step": 250,
+  "global_step": 255,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1765,6 +1765,41 @@
       "learning_rate": 9.93216320767545e-05,
       "loss": 0.8878,
       "step": 250
+    },
+    {
+      "epoch": 0.32481397605952766,
+      "grad_norm": 0.8709661960601807,
+      "learning_rate": 9.93148470124375e-05,
+      "loss": 0.8786,
+      "step": 251
+    },
+    {
+      "epoch": 0.32610805564542217,
+      "grad_norm": 0.9593453407287598,
+      "learning_rate": 9.930802841859095e-05,
+      "loss": 1.0659,
+      "step": 252
+    },
+    {
+      "epoch": 0.3274021352313167,
+      "grad_norm": 1.0130974054336548,
+      "learning_rate": 9.93011762998509e-05,
+      "loss": 0.9626,
+      "step": 253
+    },
+    {
+      "epoch": 0.3286962148172113,
+      "grad_norm": 0.9949910640716553,
+      "learning_rate": 9.929429066087616e-05,
+      "loss": 1.0499,
+      "step": 254
+    },
+    {
+      "epoch": 0.3299902944031058,
+      "grad_norm": 0.927542507648468,
+      "learning_rate": 9.92873715063483e-05,
+      "loss": 0.9571,
+      "step": 255
     }
   ],
   "logging_steps": 1,
@@ -1784,7 +1819,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.79484292923392e+17,
+  "total_flos": 2.8507397878185984e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null