Training in progress, step 2680, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac4c2e27c7954ba8f32458e86bce305764577f448e1ef7b05942fdf1638b8d3
+oid sha256:a8edf825d7e2ed21d2d16d8a88071fe27f783e5456eb6e2f0ae6c8dfef2d8ed1
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:281f3e1e3de94056c7322594abe70311fe1bd96ae510bce52c2cda2200510403
+oid sha256:3a3fd810244bbb9806c8d080b1a9cfc225f3cbfd1200f5a73aef5ff9d1728ffc
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c76e152102faadd3e0723a7b1e98668fc77dc3b57498a40931f275e4f17e53
+oid sha256:b0041b61de0cc7e619ce44504c6c5477bc99a6c82547e7c9dd6815272ffe05c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0efadb0abbc637034bafcf665143567ca2a6d58001c0ddda8fd674ac11d7db
+oid sha256:436b183fda379ac02abfc2e4c2b3ebe9640c6cb93100008fe5409c8282dc8c08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9516994633273703,
+  "epoch": 0.9588550983899821,
   "eval_steps": 500,
-  "global_step": 2660,
+  "global_step": 2680,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2135,14 +2135,30 @@
       "loss": 0.376,
       "num_input_tokens_seen": 1804337,
       "step": 2660
+    },
+    {
+      "epoch": 0.9552772808586762,
+      "grad_norm": 0.32699060440063477,
+      "learning_rate": 8.944543828264759e-06,
+      "loss": 0.4,
+      "num_input_tokens_seen": 1811353,
+      "step": 2670
+    },
+    {
+      "epoch": 0.9588550983899821,
+      "grad_norm": 0.37904760241508484,
+      "learning_rate": 8.228980322003579e-06,
+      "loss": 0.396,
+      "num_input_tokens_seen": 1817606,
+      "step": 2680
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1804337,
+  "num_input_tokens_seen": 1817606,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4.05731673087529e+16,
+  "total_flos": 4.087154026071245e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null