Training in progress, step 6640, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf37fb9d99a5a966a288465c2366c3d30e92057587f61bde6eb015a0741f5df4
+oid sha256:e70f472f3208fce22e711727d3f51a955b9502ee4635cf3b354a7a5849495f64
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a468f66a69a897ea8cb002c953ac648196c88c5fe7343f089f868b782961b7
+oid sha256:0ce48b5f0a4182d0f3ca44b8f6292a94f1e4dd3c84342481403240c0341f492c
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:121f9d4684e576b3166761513a3b4b3158536830adb54aef4bcf454539fb4e2a
+oid sha256:f483dbbbbb5dc1b41e41475eede183d58a38381ca60f4870fc45bb7a64baedfd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8204e0c4867e8d38c506caa9e5d81b9a9b7021fd5bfa716504e4e01e9745e60f
+oid sha256:127254ff30131eb4f46f0ab26f5bfb221842284bc63a371736d3849e9dc192b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5296,
+  "epoch": 0.5312,
   "eval_steps": 500,
-  "global_step": 6620,
+  "global_step": 6640,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2324,6 +2324,13 @@
       "learning_rate": 2.341919248766422e-05,
       "loss": 3.5085,
       "step": 6620
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 27.481103897094727,
+      "learning_rate": 2.3378941214219545e-05,
+      "loss": 3.5401,
+      "step": 6640
     }
   ],
   "logging_steps": 20,
@@ -2331,7 +2338,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5626866814189568e+16,
+  "total_flos": 1.5672073361719296e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null