Training in progress, step 121000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b4abcad2bc55f8b93b6bd0b69a3e6b19d6d79eea733df712ccb4e558c7e76f
+oid sha256:b66425b94f2e83e9f2d0ef0a5a9619097cea94f688140b6355837c6862e130d4
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1318700afdd8bc8f372d0aac1019c41e2362c09c3dd521afe41c9c15c2dff706
+oid sha256:2ca4050210e3e0b53086ab39ce001a08cbf8ed7f8ce6ede11116945d8c1f4075
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6f637f68138f2f3e0b10bc8106538e25e3a7bd3c99fc90c278af4e9c1843848
+oid sha256:7b1977d3bd75beb86c861efe86a2ecbbc84d67eabe3c546ad1f9cc4b0c95cfb5
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0d0bc14c7937072008c2425eb1b1c8372d5578f285662a058c839c08d67094
+oid sha256:be817e3410feaa10ca81244df169cdce850a393c8c8d757e09a32a186f0361ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 28.90521498253643,
+  "epoch": 29.14609177405757,
   "eval_steps": 500,
-  "global_step": 120000,
+  "global_step": 121000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -847,6 +847,13 @@
       "learning_rate": 3.6376776680318e-05,
       "loss": 0.7478,
       "step": 120000
+    },
+    {
+      "epoch": 29.14609177405757,
+      "grad_norm": 0.5422804355621338,
+      "learning_rate": 2.834658315265398e-05,
+      "loss": 0.7454,
+      "step": 121000
     }
   ],
   "logging_steps": 1000,
@@ -866,7 +873,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2004367363924296e+18,
+  "total_flos": 1.210439597113213e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null