Training in progress, step 1410, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542ddd20925f9f729850d504410f10c2a3df824698c924e30515ae9306a1279b
+oid sha256:a974007ef9d7482ec73c602b4c33b2b6a79dd0d6d4f92c708ef4a91c57e41d99
 size 1316913776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2081e17194d96df30382e979670b3c694506f49e574891709e93a48654fe91
+oid sha256:a82bd0f5feb416ef82bf97472847920a322c711edd9e32c69d9594e850f0e929
 size 8908124

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30055817947617003,
+  "epoch": 0.3027050236152855,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1410,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -987,6 +987,13 @@
       "learning_rate": 0.000349720910261915,
       "loss": 0.7967,
       "step": 1400
+    },
+    {
+      "epoch": 0.3027050236152855,
+      "grad_norm": 1.5339765548706055,
+      "learning_rate": 0.00034864748819235725,
+      "loss": 0.7759,
+      "step": 1410
     }
   ],
   "logging_steps": 10,
@@ -994,7 +1001,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 1.0627028991160934e+17,
+  "total_flos": 1.069964032530286e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null