Training in progress, step 317, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7c3c17c79bfe154805c8425180fc8d90019d8728ec51988b6a862dbd598007
+oid sha256:a6875a604710246338188ff29d5cbc563ba25baf48c6d1e3cc1d0b7e80ff70d7
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ba5c923acaf2e1ed47acc58d6e9aa13d44a747e391f8730de77c1999d30e90
+oid sha256:6c5e4fb6735708560c95e693cdfd10bf7dce1637be1427c5932901b16d00b7e4
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325d5ceabf189137a8e26a47ad2db0bafe3423961947489f0a619958b73d9909
+oid sha256:94632ab6bd0f8c5abd180847d8d11ab76bee1258bb52de95785e40d5948b6c6c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8449931412894376,
+  "epoch": 0.869684499314129,
   "eval_steps": 500,
-  "global_step": 308,
+  "global_step": 317,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2163,6 +2163,69 @@
       "learning_rate": 4.242424242424243e-05,
       "loss": 1.1626,
       "step": 308
+    },
+    {
+      "epoch": 0.8477366255144033,
+      "grad_norm": 0.1584944874048233,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.2979,
+      "step": 309
+    },
+    {
+      "epoch": 0.850480109739369,
+      "grad_norm": 0.16384479403495789,
+      "learning_rate": 4.0909090909090915e-05,
+      "loss": 1.1728,
+      "step": 310
+    },
+    {
+      "epoch": 0.8532235939643347,
+      "grad_norm": 0.16321486234664917,
+      "learning_rate": 4.015151515151515e-05,
+      "loss": 1.1622,
+      "step": 311
+    },
+    {
+      "epoch": 0.8559670781893004,
+      "grad_norm": 0.1510697901248932,
+      "learning_rate": 3.939393939393939e-05,
+      "loss": 1.2212,
+      "step": 312
+    },
+    {
+      "epoch": 0.8587105624142661,
+      "grad_norm": 0.15566690266132355,
+      "learning_rate": 3.8636363636363636e-05,
+      "loss": 1.2098,
+      "step": 313
+    },
+    {
+      "epoch": 0.8614540466392319,
+      "grad_norm": 0.1588331162929535,
+      "learning_rate": 3.787878787878788e-05,
+      "loss": 1.2401,
+      "step": 314
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.15694394707679749,
+      "learning_rate": 3.712121212121212e-05,
+      "loss": 1.2619,
+      "step": 315
+    },
+    {
+      "epoch": 0.8669410150891632,
+      "grad_norm": 0.15612713992595673,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 1.1761,
+      "step": 316
+    },
+    {
+      "epoch": 0.869684499314129,
+      "grad_norm": 0.15668469667434692,
+      "learning_rate": 3.560606060606061e-05,
+      "loss": 1.1711,
+      "step": 317
     }
   ],
   "logging_steps": 1,
@@ -2182,7 +2245,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.813357723602903e+17,
+  "total_flos": 3.928463201780613e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null