Training in progress, step 6500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a30a008dae072195fc28eccb26ab5bd9eb4cd09d5723d01bd5eef06c2f548cc
+oid sha256:98e08bf1a33a98f5ad95a313e7a7f611270dd303d602c0511a878d938534fca8
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c548ed51d455157bc66ff27bbdf7cc0ece0b25d6b6583885fd9166381cfa1f
+oid sha256:4631ab9889a8ec8ca19b9d63d135f464285d7b10f4a57df37d5602c15eb4157e
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab96dece0057048172e676099e7a2287bdd92408cbb9619002ab46488332801f
+oid sha256:327156111fc189e7e1e06944c3644c0b0e602db7096e3ae9ec3b005b4a71556b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f067d06bd847c479f71bde77c89318403c2c2dbcdb7f1dd86724b30b9fac060c
+oid sha256:559bbd1bba34568007cb524880da5ab92a31da308e4db32d6963a8a220ceec7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5184,
+  "epoch": 0.52,
   "eval_steps": 500,
-  "global_step": 6480,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2275,6 +2275,13 @@
       "learning_rate": 2.3698455101245052e-05,
       "loss": 3.5403,
       "step": 6480
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 28.261327743530273,
+      "learning_rate": 2.3658830835585294e-05,
+      "loss": 3.5093,
+      "step": 6500
     }
   ],
   "logging_steps": 20,
@@ -2282,7 +2289,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5298774882516992e+16,
+  "total_flos": 1.5342734805368832e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null