Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f13988b844ed8c69a71d954cca56c06260c9c862e37c2b37d479d3aa847423
+oid sha256:bc4146169c596c8a46b6a1c46d56fdd08f1dada7f00ec225e8ea9e4d71472f70
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7537b80366f1058d42502431de3c635a4774b2db45ac3cd9565cc2f7c197bc84
+oid sha256:181ff8f655987df2051473c2aa6d62574ed5c4c93c498f6bacbda1bb9807c208
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616c142757d7ec77ca22084861554955efb9fa5f5da5efb368b0b3385f62bf1c
+oid sha256:193cf8763e811dd3e32b43e244a311e62a543ef8398d3b107ff52fb9af797950
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff581a4a3c68f40d8f4f714dabed1501f0a612483eace7a936c21011b06e648
+oid sha256:a09ad69a3f61f9d3d9f02f2a0456c9d35adee50f06a3734fa06d48a8a6546239
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5586034912718203,
+  "epoch": 1.6625103906899419,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,13 @@
       "learning_rate": 9.614851759490165e-06,
       "loss": 0.3564,
       "step": 7500
+    },
+    {
+      "epoch": 1.6625103906899419,
+      "grad_norm": 0.7738548517227173,
+      "learning_rate": 8.92213909670269e-06,
+      "loss": 0.3639,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -139,7 +146,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9133759400509440.0,
+  "total_flos": 9742717291069440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null