Training in progress, step 920, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df5141e8ddeb3a52fde5e36fc601b5e98a35a760b21dad4d770c16f1eab93ed
+oid sha256:c80d0cc296c9aca69746bef2484e11ff18da0d10137405a84bdb5b47da0b2fda
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ead4589f80294e6843eb8b95d2991b1dc0bd7f68680239a89942448b55a764
+oid sha256:c6bb63f7e63d0bb877282c464d113433128c3280a6e53182bfc42899506e4622
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e6c6b149a116cec483f2a17b2bb809f7cc6274383aca9dd5c6e24801ded5e5
+oid sha256:9b5c274f729f78aaa763e0731ccb54809267c56bffe03386fccc50594bf6ee56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71dd396b34c87932ecfea63e93418697d0d152f826f8e27acd4064174d59bd1
+oid sha256:6048c9d241563f2d3e6c4169ee79753731cd3df1e3a9e7b7b302429a0457fa3f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3220035778175313,
+  "epoch": 0.3291592128801431,
   "eval_steps": 500,
-  "global_step": 900,
+  "global_step": 920,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,14 +727,30 @@
       "loss": 0.4217,
       "num_input_tokens_seen": 601425,
       "step": 900
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "grad_norm": 0.3325401544570923,
+      "learning_rate": 0.00013488372093023256,
+      "loss": 0.399,
+      "num_input_tokens_seen": 607033,
+      "step": 910
+    },
+    {
+      "epoch": 0.3291592128801431,
+      "grad_norm": 0.4284108877182007,
+      "learning_rate": 0.00013416815742397137,
+      "loss": 0.4329,
+      "num_input_tokens_seen": 612959,
+      "step": 920
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 601425,
+  "num_input_tokens_seen": 612959,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.35239243825664e+16,
+  "total_flos": 1.3783283311491072e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null