Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5b8c055fbc4cfee0c011f0503f5164aac7bfe4be51050205a71f8a1505a5250
+oid sha256:8c85407f600156ac5243f7ac7bdb2f99fd52e0d2b9dd155377e6984b280b8cdb
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f5cc698c5358d0614a1568b7e2f017041423bbdbf8e1a896971b9b69f074d5
+oid sha256:3b37174927714cec2e61c454712290368ccd8a8714b0ebd27ab7511b87c550a1
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e1387e214d70dfb802b640ec231549370dc3f65b42b72d8d5868f97ba68c32
+oid sha256:a07938138ec004ff3d5081b07253c4357b50bd72ea7c1cfabba2e25e891013e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b665a2618254d0693455029a117143eb612684fd8f287fa7207d501afc785521
+oid sha256:6f68b4a4ba4603d307a8be653dd70e693a9f3506ea1af5f24d2d241dc54cfcb1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3813559322033898,
+  "epoch": 0.4576271186440678,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -118,6 +118,21 @@
       "eval_samples_per_second": 18.885,
       "eval_steps_per_second": 2.383,
       "step": 45
+    },
+    {
+      "epoch": 0.423728813559322,
+      "grad_norm": 0.5933341979980469,
+      "learning_rate": 0.00010370125742738173,
+      "loss": 0.792,
+      "step": 50
+    },
+    {
+      "epoch": 0.4576271186440678,
+      "eval_loss": 0.81903076171875,
+      "eval_runtime": 22.2328,
+      "eval_samples_per_second": 18.891,
+      "eval_steps_per_second": 2.384,
+      "step": 54
     }
   ],
   "logging_steps": 5,
@@ -137,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.939162462230938e+16,
+  "total_flos": 8.409963201508147e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null