Training in progress, step 6520, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e08bf1a33a98f5ad95a313e7a7f611270dd303d602c0511a878d938534fca8
+oid sha256:ab44c0650fc35117528c103709aeefeda1ba5a0c1b201a042c443fced883ac06
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4631ab9889a8ec8ca19b9d63d135f464285d7b10f4a57df37d5602c15eb4157e
+oid sha256:b8f8827e725054a7d3aa47b66a00e417f27bf58195e5d53d80134e98a97b930d
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327156111fc189e7e1e06944c3644c0b0e602db7096e3ae9ec3b005b4a71556b
+oid sha256:966b1d0c91c0efe2171d6c761e8fb3dd8dd23b43cb7c345758210f8c5726e8a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:559bbd1bba34568007cb524880da5ab92a31da308e4db32d6963a8a220ceec7d
+oid sha256:9b9c2686d4c99776f5194741a1ee501ae1a6b12f42eb0cf041ec1c8a8c483c5a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.52,
+  "epoch": 0.5216,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 6520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2282,6 +2282,13 @@
       "learning_rate": 2.3658830835585294e-05,
       "loss": 3.5093,
       "step": 6500
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 37.4576530456543,
+      "learning_rate": 2.361911574288736e-05,
+      "loss": 3.5952,
+      "step": 6520
     }
   ],
   "logging_steps": 20,
@@ -2289,7 +2296,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5342734805368832e+16,
+  "total_flos": 1.539204209197056e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null