Training in progress, step 2340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6279bb72a1a41fb48956b4feb1a93393d18d4e6392ad78211fc04c9f099df2
+oid sha256:8abb44f6aca403f71064a572c838010e4fcf7984d9faf66f884911976f427e2c
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ccf80491212ab3533b791bb0a94ac69d6d47751d6deeebce7061fdefd9b30f
+oid sha256:5421b6835db3269773718c76f42b20f1029476f55863aace65468871b75acead
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19bb1874a3bf4e8cd76c40201bfecc47f7333e535e927638bb37015a23fd28aa
+oid sha256:e2906515e1bcbf65ec65f30890fb86fc07abf4f380736f4d75d70f44ddd1a161
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830ffa36a2cc85b79b79c8f68dead7aaec7fb58f5ebad1169970ef47fdf22b5f
+oid sha256:c0edca768de2b612c93b0f82e9eb2540d009ac62af5eb1b92baccfef4a526aeb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8300536672629696,
+  "epoch": 0.8372093023255814,
   "eval_steps": 500,
-  "global_step": 2320,
+  "global_step": 2340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1863,14 +1863,30 @@
       "loss": 0.3971,
       "num_input_tokens_seen": 1572070,
       "step": 2320
+    },
+    {
+      "epoch": 0.8336314847942755,
+      "grad_norm": 0.3011910021305084,
+      "learning_rate": 3.3273703041144904e-05,
+      "loss": 0.4008,
+      "num_input_tokens_seen": 1579014,
+      "step": 2330
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 0.3195567727088928,
+      "learning_rate": 3.2558139534883724e-05,
+      "loss": 0.362,
+      "num_input_tokens_seen": 1586863,
+      "step": 2340
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1572070,
+  "num_input_tokens_seen": 1586863,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.535030270457856e+16,
+  "total_flos": 3.5682945034696704e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null