Training in progress, step 5780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106e0a8e71cc55180d6c0190fdb06747b7348afc51dc8c66dd21361bdf370b7c
+oid sha256:283dd7cd18659a3c9d3097777e6a3109d1270cd6b8e6372800d079fa0c6abec5
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c4d8d6970ba09dd48969d99468a522c66cd6d17c14302ed117d1905247ae7ab
+oid sha256:d6b30e324e0c0ca3d4e69841f3e1c91025824da6588bf53e3d9fec35c7904fe9
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328225a5ada1e91a7a041c82bd448f246b9de4bba61f01f80576b43e250cc0a2
+oid sha256:1680fcc8fd6c2f3a95198a6b5dcd06c9a4a57f3225e8f95006ad95075adefeb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90472b611ffb952578703b9c8bc11e7e2553f2156ebce3593e42f79723ecc9cf
+oid sha256:447f6f7a97384eaf154d22cf9cf079d353a317926c5cc0034d003c8c0323b94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4608,
+  "epoch": 0.4624,
   "eval_steps": 500,
-  "global_step": 5760,
+  "global_step": 5780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2023,6 +2023,13 @@
       "learning_rate": 2.5061004322976953e-05,
       "loss": 3.4351,
       "step": 5760
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 92.71965789794922,
+      "learning_rate": 2.5024918927404005e-05,
+      "loss": 3.5194,
+      "step": 5780
     }
   ],
   "logging_steps": 20,
@@ -2030,7 +2037,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.364496321773568e+16,
+  "total_flos": 1.3688234216423424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null