Training in progress, step 2700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8edf825d7e2ed21d2d16d8a88071fe27f783e5456eb6e2f0ae6c8dfef2d8ed1
+oid sha256:b7339f7334e0a031a15795ba5320c294805f948a198df237f83f4e5327e0cad8
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a3fd810244bbb9806c8d080b1a9cfc225f3cbfd1200f5a73aef5ff9d1728ffc
+oid sha256:f00d069498569089a5048ef3befc73614bd70e4e5ed8485f9cc4cbc6780121aa
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0041b61de0cc7e619ce44504c6c5477bc99a6c82547e7c9dd6815272ffe05c3
+oid sha256:fb2d63f8e4e8d5f7bea5acbac004de06c0ad244850838fc3302028e95e97171e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436b183fda379ac02abfc2e4c2b3ebe9640c6cb93100008fe5409c8282dc8c08
+oid sha256:717f2df67856162e81b3e0ed9d50fa4a8bb3e40a242042617cbc33e8d11a5c3f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9588550983899821,
+  "epoch": 0.9660107334525939,
   "eval_steps": 500,
-  "global_step": 2680,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2151,14 +2151,30 @@
       "loss": 0.396,
       "num_input_tokens_seen": 1817606,
       "step": 2680
+    },
+    {
+      "epoch": 0.962432915921288,
+      "grad_norm": 0.401185005903244,
+      "learning_rate": 7.513416815742398e-06,
+      "loss": 0.4044,
+      "num_input_tokens_seen": 1826557,
+      "step": 2690
+    },
+    {
+      "epoch": 0.9660107334525939,
+      "grad_norm": 0.3426940441131592,
+      "learning_rate": 6.797853309481217e-06,
+      "loss": 0.3881,
+      "num_input_tokens_seen": 1832731,
+      "step": 2700
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1817606,
+  "num_input_tokens_seen": 1832731,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4.087154026071245e+16,
+  "total_flos": 4.121164809840845e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null