Training in progress, step 119000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfed27d6337a699642afb264f3167a26d2ca21ac0273cb5e18c125ded3a387ba
+oid sha256:412193e885b1f8267ec01dd41cf7748d4021c58a085cdccf3df96d4c39a4f744
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7801aee86c0670959119d2467b5f94581b85321743ff0b2c1de9d55040ef0a1
+oid sha256:4c065961e7db169a4d7ddfe994e9a841e734d8eba81e357e012ac63914181fd7
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d12692e3ded8e4b48e14a240df346a1d6bfd5fe5c760f7febc8f9669a6659e15
+oid sha256:df07f83f2f362fd986b1bf45b68e7a3dcf6fa383add3ed8d2f752492eebc54e4
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b9b8c3bd8dd54ca219bcc622f7453fe04bec46ffa58e0fd1624344a5a69ef4
+oid sha256:4ba15a0768ff2fa4f2e6148e363a3a482950f51aed5d4a6c6dacbbecf282200a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 28.42346139949416,
+  "epoch": 28.664338191015297,
   "eval_steps": 500,
-  "global_step": 118000,
+  "global_step": 119000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -833,6 +833,13 @@
       "learning_rate": 5.243716373564603e-05,
       "loss": 0.7453,
       "step": 118000
+    },
+    {
+      "epoch": 28.664338191015297,
+      "grad_norm": 0.5951708555221558,
+      "learning_rate": 4.440697020798201e-05,
+      "loss": 0.7462,
+      "step": 119000
     }
   ],
   "logging_steps": 1000,
@@ -852,7 +859,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1804289834313318e+18,
+  "total_flos": 1.1904328599118807e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null