Training in progress, step 238, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410b91c48e370417f87515a2eaae1a7f535d115bdfa83c50e64334080b1f0b62
+oid sha256:e5f938f590c16a2da7e7003b5726decdca766113cb8c6bf1132392eec1032131
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:912ad228eb3b6d149e12e4ade24a7080c1aa79a5940fd0cf0ff1e0684af11de3
+oid sha256:242a26a061ea5d980a98bce60edfbf0494218ef54aba0d781b0dca84f1a1c629
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbb06d4550f69a6f5bcf553617c3e68e7fa013d474d5f9b6a819f651cff51fa
+oid sha256:771fda137b95b0a53343c99caba02f0ddc4fde33ba4274f7584011ab1e463479
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9839d107756d9c8815de9164f2ebf92c05b3536704a349ca5892084df7663e
+oid sha256:bbcef9424696e41c7961bd91f0570d39d59ef33af28ed19a0eb9e4f50ed1b09a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06877950101146325,
+  "epoch": 0.08024275118004046,
   "eval_steps": 34,
-  "global_step": 204,
+  "global_step": 238,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -539,6 +539,91 @@
       "eval_samples_per_second": 14.615,
       "eval_steps_per_second": 1.829,
       "step": 204
+    },
+    {
+      "epoch": 0.06979096426163182,
+      "grad_norm": 1.039337396621704,
+      "learning_rate": 2.459724913431772e-05,
+      "loss": 0.439,
+      "step": 207
+    },
+    {
+      "epoch": 0.07080242751180041,
+      "grad_norm": 1.222737431526184,
+      "learning_rate": 2.399335149726463e-05,
+      "loss": 0.4838,
+      "step": 210
+    },
+    {
+      "epoch": 0.07181389076196898,
+      "grad_norm": 1.278668999671936,
+      "learning_rate": 2.3390041714589514e-05,
+      "loss": 0.4612,
+      "step": 213
+    },
+    {
+      "epoch": 0.07282535401213756,
+      "grad_norm": 1.1525593996047974,
+      "learning_rate": 2.2787672102216042e-05,
+      "loss": 0.4372,
+      "step": 216
+    },
+    {
+      "epoch": 0.07383681726230613,
+      "grad_norm": 1.3022117614746094,
+      "learning_rate": 2.2186594427034864e-05,
+      "loss": 0.4593,
+      "step": 219
+    },
+    {
+      "epoch": 0.07484828051247472,
+      "grad_norm": 1.4199026823043823,
+      "learning_rate": 2.1587159701481716e-05,
+      "loss": 0.455,
+      "step": 222
+    },
+    {
+      "epoch": 0.07585974376264329,
+      "grad_norm": 1.3410009145736694,
+      "learning_rate": 2.098971797855599e-05,
+      "loss": 0.6084,
+      "step": 225
+    },
+    {
+      "epoch": 0.07687120701281187,
+      "grad_norm": 1.2653465270996094,
+      "learning_rate": 2.0394618147399713e-05,
+      "loss": 0.497,
+      "step": 228
+    },
+    {
+      "epoch": 0.07788267026298044,
+      "grad_norm": 1.2599753141403198,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 0.4794,
+      "step": 231
+    },
+    {
+      "epoch": 0.07889413351314903,
+      "grad_norm": 1.176132321357727,
+      "learning_rate": 1.921283267602643e-05,
+      "loss": 0.4134,
+      "step": 234
+    },
+    {
+      "epoch": 0.0799055967633176,
+      "grad_norm": 1.2982177734375,
+      "learning_rate": 1.8626837165245165e-05,
+      "loss": 0.4404,
+      "step": 237
+    },
+    {
+      "epoch": 0.08024275118004046,
+      "eval_loss": 0.4182414412498474,
+      "eval_runtime": 341.5144,
+      "eval_samples_per_second": 14.626,
+      "eval_steps_per_second": 1.83,
+      "step": 238
     }
   ],
   "logging_steps": 3,
@@ -558,7 +643,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.85207786877354e+17,
+  "total_flos": 3.3274241802357965e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null