Training in progress, step 337, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e0972e809f636f714cabaf7760abced4e8ac62b9b0d7d1e5af1957fd879d856
+oid sha256:9fa01b3abb7656551224fc4fbeb611a0886c86685343fa6406fe831c1db71f04
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e62a3caea9d1213a790ce42d8942f8d073a999f93a21cc68ae51d4b4cda784
+oid sha256:88fab551c9bf6c469ad35ab513b4416c08bfdf970747a1f23bd5b53582b807c8
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ad2ac46faf761aed288b5b7843e4fc844c5885618fe90eebd496352649b23c
+oid sha256:b12f765a366db773a3e801ac0d1a41ae53b843966dba1e15b6484a9f4d83233f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9080932784636488,
+  "epoch": 0.9245541838134431,
   "eval_steps": 500,
-  "global_step": 331,
+  "global_step": 337,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2324,6 +2324,48 @@
       "learning_rate": 2.5e-05,
       "loss": 1.1528,
       "step": 331
+    },
+    {
+      "epoch": 0.9108367626886146,
+      "grad_norm": 0.16983263194561005,
+      "learning_rate": 2.4242424242424244e-05,
+      "loss": 1.1711,
+      "step": 332
+    },
+    {
+      "epoch": 0.9135802469135802,
+      "grad_norm": 0.15927070379257202,
+      "learning_rate": 2.3484848484848487e-05,
+      "loss": 1.1595,
+      "step": 333
+    },
+    {
+      "epoch": 0.9163237311385459,
+      "grad_norm": 0.16879941523075104,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 1.1557,
+      "step": 334
+    },
+    {
+      "epoch": 0.9190672153635117,
+      "grad_norm": 0.15948091447353363,
+      "learning_rate": 2.1969696969696972e-05,
+      "loss": 1.149,
+      "step": 335
+    },
+    {
+      "epoch": 0.9218106995884774,
+      "grad_norm": 0.16563957929611206,
+      "learning_rate": 2.1212121212121215e-05,
+      "loss": 1.1512,
+      "step": 336
+    },
+    {
+      "epoch": 0.9245541838134431,
+      "grad_norm": 0.16133056581020355,
+      "learning_rate": 2.0454545454545457e-05,
+      "loss": 1.1601,
+      "step": 337
     }
   ],
   "logging_steps": 1,
@@ -2343,7 +2385,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.1040816234142925e+17,
+  "total_flos": 4.1769332820525466e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null