Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5203def3dfaa585f2709854cb7081b5402cb1703c0ef445c0dc93d47a9fca86
+oid sha256:09e42426f9664501195569e96f5a7ee0fc64f3214acdb3a4a74cd24a1fb23b0a
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5587744a36631b994d493b042e7e0940c3917efca8cab938c21c474e8c07d606
+oid sha256:054f9aaa885b76d5260a4407dab68a0639efed60781407198b8607dce79f34e2
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a3dae860874f4f9ec7b9723c4571a24fa5277582ebca2166c3d9dd7790aae41
+oid sha256:2864730966c44a4d9e96d3cf646276472e29551ad2c5f921b0c4c643dd9b0a39
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.803840877914952,
+  "epoch": 0.823045267489712,
   "eval_steps": 500,
-  "global_step": 293,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2058,6 +2058,55 @@
       "learning_rate": 5.378787878787879e-05,
       "loss": 1.1965,
       "step": 293
+    },
+    {
+      "epoch": 0.8065843621399177,
+      "grad_norm": 0.15758417546749115,
+      "learning_rate": 5.303030303030303e-05,
+      "loss": 1.2708,
+      "step": 294
+    },
+    {
+      "epoch": 0.8093278463648834,
+      "grad_norm": 0.16219446063041687,
+      "learning_rate": 5.2272727272727274e-05,
+      "loss": 1.175,
+      "step": 295
+    },
+    {
+      "epoch": 0.8120713305898491,
+      "grad_norm": 0.181773379445076,
+      "learning_rate": 5.151515151515152e-05,
+      "loss": 1.0874,
+      "step": 296
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.1878584921360016,
+      "learning_rate": 5.075757575757576e-05,
+      "loss": 1.2115,
+      "step": 297
+    },
+    {
+      "epoch": 0.8175582990397805,
+      "grad_norm": 0.1562959998846054,
+      "learning_rate": 5e-05,
+      "loss": 1.1326,
+      "step": 298
+    },
+    {
+      "epoch": 0.8203017832647462,
+      "grad_norm": 0.1604573130607605,
+      "learning_rate": 4.9242424242424245e-05,
+      "loss": 1.1464,
+      "step": 299
+    },
+    {
+      "epoch": 0.823045267489712,
+      "grad_norm": 0.17849043011665344,
+      "learning_rate": 4.848484848484849e-05,
+      "loss": 1.0647,
+      "step": 300
     }
   ],
   "logging_steps": 1,
@@ -2077,7 +2126,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.62592285449429e+17,
+  "total_flos": 3.711016873109668e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null