Training in progress, step 340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7c5c0bb66466d7e29226f80d5cc217cf4256670467b8a4081f5c23852a3af7
+oid sha256:80dbb1c54c0d5b697ffb1db9777ecd0e4186f5de71249b858bcf512f10de7aee
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a553c2eb71e73f0c1eda48c6b9ee7a1eaaa3208af2a76b8e5dbafcd6476db69a
+oid sha256:96f943a705f415cf465b2a80496bdaa14239fc12e3961065fffdc8ba616e9619
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2a2d99c0e8f2ac5f91854c3cc393c4031b8b2b320bd2130073e550304e4d8b
+oid sha256:1149733eec3e645a88cec88e3d630409b2fd607fe44382620dcd32de8875ec30
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ae66eeabf39a4e204f66b969f521166fbc3f93e43500ebb37520ec3747848cb
+oid sha256:90bff0e02e91ee65835a68194924a84afe4e4f8f7cdb643caca99db3408d318f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11449016100178891,
+  "epoch": 0.12164579606440072,
   "eval_steps": 500,
-  "global_step": 320,
+  "global_step": 340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -263,14 +263,30 @@
       "loss": 0.4431,
       "num_input_tokens_seen": 217965,
       "step": 320
+    },
+    {
+      "epoch": 0.11806797853309481,
+      "grad_norm": 0.39270082116127014,
+      "learning_rate": 0.00017638640429338106,
+      "loss": 0.4475,
+      "num_input_tokens_seen": 224249,
+      "step": 330
+    },
+    {
+      "epoch": 0.12164579606440072,
+      "grad_norm": 0.37138304114341736,
+      "learning_rate": 0.00017567084078711986,
+      "loss": 0.4139,
+      "num_input_tokens_seen": 230513,
+      "step": 340
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 217965,
+  "num_input_tokens_seen": 230513,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4901263130142720.0,
+  "total_flos": 5183423338235904.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null