Training in progress, step 256, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2499cb84d044f14380d1436e809204017b642ef077cd6d85e04a0612d04f139c
+oid sha256:89202c3a83c656009c49405e34a199746a7402ebd46b8daddcaa8ca18ca6d51e
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8127b2d19d877bc8b6390abef2ec730fbe95a18ba0f539c7b6cea04272a25b9a
-size 75455362
+oid sha256:41d7a8511652baf58cf06d37d605965dd1bc2aee8d912767371f5f07328245b8
+size 75455810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd63113a0a7922f08bc7bf5a3f424120a413b69e0c07f67a117e000ca3f41b8
+oid sha256:377c19831806be3b2af38951dd08dcc47e0fc843a7df6b6c5b4d819485499ed8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cae400ce236e72d865001da29ea9701cbf6e3c969ad1bd3d2f923aecee97db42
+oid sha256:a3d84d4585b602d0abc8b4dfccabde21254d9ba4ef932cab6e61e0e9e3b40642
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09764352062770834,
+  "epoch": 0.09919341778052912,
   "eval_steps": 500,
-  "global_step": 252,
+  "global_step": 256,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1771,6 +1771,34 @@
       "learning_rate": 9.846358414859598e-06,
       "loss": 1.5649,
       "step": 252
+    },
+    {
+      "epoch": 0.09803099491591354,
+      "grad_norm": 0.08257234841585159,
+      "learning_rate": 9.844826174531863e-06,
+      "loss": 1.5609,
+      "step": 253
+    },
+    {
+      "epoch": 0.09841846920411873,
+      "grad_norm": 0.16954340040683746,
+      "learning_rate": 9.843286452099964e-06,
+      "loss": 1.5876,
+      "step": 254
+    },
+    {
+      "epoch": 0.09880594349232392,
+      "grad_norm": 0.08577932417392731,
+      "learning_rate": 9.841739249941772e-06,
+      "loss": 1.5812,
+      "step": 255
+    },
+    {
+      "epoch": 0.09919341778052912,
+      "grad_norm": 0.13520435988903046,
+      "learning_rate": 9.840184570446702e-06,
+      "loss": 1.5758,
+      "step": 256
     }
   ],
   "logging_steps": 1.0,
@@ -1790,7 +1818,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4955793132720947e+17,
+  "total_flos": 2.5351262457715814e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null