Training in progress, step 9000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0be03972159ec159a56e3e77ca8d38e2168af9dcdd4df0d68963ed1c60e6965
+oid sha256:9af7b37f06d07ef70d4988ce1f6299893bace9d6a7ba0c9cd136d9ea3fd941fa
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd5bd046dc3465f6df5b72e0a2552c5b0fda402004d2a228232c184835c93f0
+oid sha256:f921cb5d7c6f27660db1f17dd3595cd35f686682075ca581ae6001b538ec16f7
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85904f7c1b5e0d81333d46dd0befeb978507214982bf15efdfa380ed0f5f6789
+oid sha256:cf5f888e89f291e2093e87569b5763db1fc85cbdf17ee5606bd0221a799e468a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a757a49f50d9542b04e522a04786aa578e7821acc2014c546ec09d428c28168
+oid sha256:aaf2bc4e5abc828d18795c4a133d46fc971f9c25b1fb81b66f19e661f16cda00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006544234938034276,
+  "epoch": 0.006692967550262327,
   "eval_steps": 2000,
-  "global_step": 8800,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,6 +315,13 @@
       "learning_rate": 1.9999915674072735e-05,
       "loss": 1.6099,
       "step": 8800
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.3625733852386475,
+      "learning_rate": 1.9999911792618627e-05,
+      "loss": 1.5237,
+      "step": 9000
     }
   ],
   "logging_steps": 200,
@@ -322,7 +329,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.1521698789135974e+17,
+  "total_flos": 1.1786109336920064e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null