Training in progress, step 1420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a974007ef9d7482ec73c602b4c33b2b6a79dd0d6d4f92c708ef4a91c57e41d99
+oid sha256:6808dd327f6b3084d418d704b1410ab5b4920ece09285db52a32aa7605a852aa
 size 1316913776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82bd0f5feb416ef82bf97472847920a322c711edd9e32c69d9594e850f0e929
+oid sha256:72c67711d65987cd86d63dd8b7abad826d13d8fd78a67946d2b4d7ddf43251fd
 size 8908124

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3027050236152855,
+  "epoch": 0.30485186775440104,
   "eval_steps": 500,
-  "global_step": 1410,
+  "global_step": 1420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -994,6 +994,13 @@
       "learning_rate": 0.00034864748819235725,
       "loss": 0.7759,
       "step": 1410
+    },
+    {
+      "epoch": 0.30485186775440104,
+      "grad_norm": 1.721113681793213,
+      "learning_rate": 0.0003475740661227995,
+      "loss": 0.7792,
+      "step": 1420
     }
   ],
   "logging_steps": 10,
@@ -1001,7 +1008,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 1.069964032530286e+17,
+  "total_flos": 1.0767132782165837e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null