Training in progress, step 1640, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a048f86601ba971f672b82718f94bad132e5b83ef0518c001ab7d8b04f8761c4
+oid sha256:f10257b7014e9aac14048d4c25d8edac512b0d9b68ecd3b472b859543cdef14b
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade7968eeaa11d7a71f3ef59ccd75f826f2bc6dee5950963249d4f00175a0086
+oid sha256:b9380c503afe8a570e3b4d2d7682a1be66462065c80d82ec8ac42553b0ce37b6
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7229499a03050ced172a76d8d9d236be1759d890b794401cb65a0ba41ba1aaf3
+oid sha256:9e4bae246be55e0c5c479cc3228ea806f5dad96bfbd997b22379ceb5166207ba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:093216f4a2f15aa62a41addc634f987432a9234bc35332dcb2fa9dd6e471f24c
+oid sha256:a7b5d3fd1283600a406407d024141f0dd9978a7bb53ae522b56311cc64308157
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5796064400715564,
+  "epoch": 0.5867620751341681,
   "eval_steps": 500,
-  "global_step": 1620,
+  "global_step": 1640,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1303,14 +1303,30 @@
       "loss": 0.4022,
       "num_input_tokens_seen": 1087604,
       "step": 1620
+    },
+    {
+      "epoch": 0.5831842576028623,
+      "grad_norm": 0.36473724246025085,
+      "learning_rate": 8.336314847942756e-05,
+      "loss": 0.3857,
+      "num_input_tokens_seen": 1094532,
+      "step": 1630
+    },
+    {
+      "epoch": 0.5867620751341681,
+      "grad_norm": 0.29369673132896423,
+      "learning_rate": 8.264758497316637e-05,
+      "loss": 0.405,
+      "num_input_tokens_seen": 1100973,
+      "step": 1640
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1087604,
+  "num_input_tokens_seen": 1100973,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.445637320393523e+16,
+  "total_flos": 2.4756994802755584e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null