Training in progress, step 120000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:412193e885b1f8267ec01dd41cf7748d4021c58a085cdccf3df96d4c39a4f744
+oid sha256:64b4abcad2bc55f8b93b6bd0b69a3e6b19d6d79eea733df712ccb4e558c7e76f
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c065961e7db169a4d7ddfe994e9a841e734d8eba81e357e012ac63914181fd7
+oid sha256:1318700afdd8bc8f372d0aac1019c41e2362c09c3dd521afe41c9c15c2dff706
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df07f83f2f362fd986b1bf45b68e7a3dcf6fa383add3ed8d2f752492eebc54e4
+oid sha256:e6f637f68138f2f3e0b10bc8106538e25e3a7bd3c99fc90c278af4e9c1843848
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba15a0768ff2fa4f2e6148e363a3a482950f51aed5d4a6c6dacbbecf282200a
+oid sha256:eb0d0bc14c7937072008c2425eb1b1c8372d5578f285662a058c839c08d67094
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 28.664338191015297,
+  "epoch": 28.90521498253643,
   "eval_steps": 500,
-  "global_step": 119000,
+  "global_step": 120000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -840,6 +840,13 @@
       "learning_rate": 4.440697020798201e-05,
       "loss": 0.7462,
       "step": 119000
+    },
+    {
+      "epoch": 28.90521498253643,
+      "grad_norm": 0.5529988408088684,
+      "learning_rate": 3.6376776680318e-05,
+      "loss": 0.7478,
+      "step": 120000
     }
   ],
   "logging_steps": 1000,
@@ -859,7 +866,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1904328599118807e+18,
+  "total_flos": 1.2004367363924296e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null