Training in progress, step 3520, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d574a9cfe44b6a9f1d49919f1d1075af72d4ebae831ed5168457960a110cf96
+oid sha256:86d755fdbe6f94a9a2692d37f476a7f3f294adf90ab7d7dfd64705c07fa4d33a
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43bdae8cb558222fb1e4b8ab4a8921afca3a24f6302f6ab4eb57e840888a343d
+oid sha256:9c6b821c1771e6fd3ffaa6fc89b2818ba9fe473e836a944a154ed7ef1fb7364a
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd37529ec6267cade7e3edbd0752da2dc70537a327ba7205cdcfdf07532b1f14
+oid sha256:aa8265710fb321d1c26a08015211fa45d8789b6c86382ab93455535b66e21e3b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9cf56fcd440484564e22fe18b4a309200b45f2e6cb790d1d19c81f6ae46057
+oid sha256:d4c2f733828b47d09685b4b92680b3f65e8207ee9b83d81c0150205a4a65cf60
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28,
+  "epoch": 0.2816,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 3520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1232,6 +1232,13 @@
       "learning_rate": 2.8376108064873216e-05,
       "loss": 3.5228,
       "step": 3500
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 32.50440216064453,
+      "learning_rate": 2.835405261236676e-05,
+      "loss": 3.479,
+      "step": 3520
     }
   ],
   "logging_steps": 20,
@@ -1239,7 +1246,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8289562019266560.0,
+  "total_flos": 8338245993529344.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null