Training in progress, step 12500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16bef696d643f07b3b74c8e05298a90d16f8d6377bcfc3c92d7ed58d57dc478
+oid sha256:c5e9efffe9b7c56a24141331717c7106d1e6b75b664c6b6e41c838b1c2ae800f
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64178181dbf154aa8840338b3a9cd793eb6f36c2a3240a459f9e58d74069bf32
+oid sha256:271ded05124935b87806da10eeb3248f1f5e3b9d1821371983eb0947ab652255
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d08ed8d6cfd3ff9d1a96759159e76e5a09c5fb769c0396ef4ede20b9b1cacd
+oid sha256:8a9d3e1e0e2094934ac230fdd75ebe4375103c7d57b000d50375350f3dfdec58
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c42a478dc2abce506266bee23681e656243611e73c868841a8a274a8f9cc7e
+oid sha256:7c24dc2fc932ae6f658653cc45eeb992571bdff268fdfc9138ada0f732a92dc5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 24.79612560537416,
+  "epoch": 24.99609436025621,
   "eval_steps": 500,
-  "global_step": 12400,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1067,6 +1067,21 @@
       "learning_rate": 1.7333333333333336e-05,
       "loss": 1.2215,
       "step": 12400
+    },
+    {
+      "epoch": 24.99609436025621,
+      "grad_norm": 0.24221302568912506,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2257,
+      "step": 12500
+    },
+    {
+      "epoch": 24.99609436025621,
+      "eval_loss": 1.1003334522247314,
+      "eval_runtime": 782.6561,
+      "eval_samples_per_second": 19.832,
+      "eval_steps_per_second": 2.48,
+      "step": 12500
     }
   ],
   "logging_steps": 100,
@@ -1086,7 +1101,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9353076662446064e+19,
+  "total_flos": 1.950915163363423e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null