Training in progress, step 1560, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f24760c3a76f03c11ceb3b090eb745146db3c3cceff8d0f5c2208a02ff460a
+oid sha256:1b1b606eb9fd42d003e24e4c311d5a76dc8b2194c3359be99a0f7877260ebc45
 size 1316913776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b20a7be78cf9001416e8e87742c91e3bbdbd5a574b71733c30e9526d3e8fef
+oid sha256:d9009dfe23d5ba22f1b4f8a4580763d728a499c43d2116dd63b636be2a270eae
 size 8908124

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3284671532846715,
+  "epoch": 0.334907685702018,
   "eval_steps": 500,
-  "global_step": 1530,
+  "global_step": 1560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1078,6 +1078,27 @@
       "learning_rate": 0.00033576642335766423,
       "loss": 0.7974,
       "step": 1530
+    },
+    {
+      "epoch": 0.33061399742378705,
+      "grad_norm": 1.8875946998596191,
+      "learning_rate": 0.0003346930012881065,
+      "loss": 0.7835,
+      "step": 1540
+    },
+    {
+      "epoch": 0.33276084156290253,
+      "grad_norm": 1.5482693910598755,
+      "learning_rate": 0.0003336195792185487,
+      "loss": 0.7866,
+      "step": 1550
+    },
+    {
+      "epoch": 0.334907685702018,
+      "grad_norm": 1.1274839639663696,
+      "learning_rate": 0.000332546157148991,
+      "loss": 0.7964,
+      "step": 1560
     }
   ],
   "logging_steps": 10,
@@ -1085,7 +1106,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 30,
-  "total_flos": 1.156634896584983e+17,
+  "total_flos": 1.1783823328185754e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null