Training in progress, step 5760, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85dd23053478779ccf46e0ca2c0ab595376b10a00281986da38738dcf4c5a6f2
+oid sha256:106e0a8e71cc55180d6c0190fdb06747b7348afc51dc8c66dd21361bdf370b7c
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68508aeacddbbed435dffee6ab56d14ad8cc7af1af1a4a1cbd0e8c21cccf52c
+oid sha256:9c4d8d6970ba09dd48969d99468a522c66cd6d17c14302ed117d1905247ae7ab
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3568a47a934d5a4cfad1f4c6204e4bef8d710f3fea7631bb7a3e787aba3f0c2
+oid sha256:328225a5ada1e91a7a041c82bd448f246b9de4bba61f01f80576b43e250cc0a2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db005cc740de60b97936932099d8a692b0015d48f80c2b3cda30ecdcf7f9644e
+oid sha256:90472b611ffb952578703b9c8bc11e7e2553f2156ebce3593e42f79723ecc9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4592,
+  "epoch": 0.4608,
   "eval_steps": 500,
-  "global_step": 5740,
+  "global_step": 5760,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2016,6 +2016,13 @@
       "learning_rate": 2.509698418337534e-05,
       "loss": 3.4938,
       "step": 5740
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 32.694766998291016,
+      "learning_rate": 2.5061004322976953e-05,
+      "loss": 3.4351,
+      "step": 5760
     }
   ],
   "logging_steps": 20,
@@ -2023,7 +2030,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3598247598227456e+16,
+  "total_flos": 1.364496321773568e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null