Training in progress, step 325, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905e964f4324984e53eb7fef6e0e34dce4aee31dea6117380645f6ac838e05b2
+oid sha256:711515011bc9a1118e2a2cd48fe663da98c9e69a5329f85b8db220971cc778a5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2138a28601906805f7004fd88f4ab2c01a76fd327549739267888df4772ddf
+oid sha256:125640ca1c2270dcc43bfec9b85910ec5f542fe4a3d0331918c3c607c5c1ec3a
 size 42546196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767c70768d113efa4dcbdb70d4f9a493e78092c5f49e743619a1df4eb0fa7663
+oid sha256:760e2590ede718fcb118f4dc8d958bdba98e4ac3f71ddbb83deefe6280da4030
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a490f516731d84c5ebbd21bb085cd67e0db15849165333c36e7773f44b973d6b
+oid sha256:62e5062625ff30e631b3308d37f5a5550bd7d782dfc6daef7e3c2f2f13956f99
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.056716135740618207,
+  "epoch": 0.061442480385669726,
   "eval_steps": 1000,
-  "global_step": 300,
+  "global_step": 325,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1807,13 +1807,163 @@
       "learning_rate": 8.185483870967743e-05,
       "loss": 1.6695,
       "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.145161290322582e-05,
+      "loss": 1.6221,
+      "step": 301
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.104838709677419e-05,
+      "loss": 1.5938,
+      "step": 302
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.064516129032258e-05,
+      "loss": 1.7077,
+      "step": 303
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.024193548387097e-05,
+      "loss": 1.3318,
+      "step": 304
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.983870967741936e-05,
+      "loss": 1.4808,
+      "step": 305
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.943548387096774e-05,
+      "loss": 1.6729,
+      "step": 306
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.903225806451613e-05,
+      "loss": 1.6133,
+      "step": 307
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.862903225806451e-05,
+      "loss": 1.6705,
+      "step": 308
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.82258064516129e-05,
+      "loss": 1.5732,
+      "step": 309
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.78225806451613e-05,
+      "loss": 1.3341,
+      "step": 310
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.741935483870968e-05,
+      "loss": 1.7081,
+      "step": 311
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.701612903225807e-05,
+      "loss": 1.6325,
+      "step": 312
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.661290322580645e-05,
+      "loss": 1.5734,
+      "step": 313
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.620967741935484e-05,
+      "loss": 1.5356,
+      "step": 314
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.580645161290323e-05,
+      "loss": 1.6806,
+      "step": 315
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.540322580645162e-05,
+      "loss": 1.5687,
+      "step": 316
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.6411,
+      "step": 317
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.45967741935484e-05,
+      "loss": 1.6724,
+      "step": 318
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.419354838709677e-05,
+      "loss": 1.5039,
+      "step": 319
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.379032258064516e-05,
+      "loss": 1.6331,
+      "step": 320
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.338709677419355e-05,
+      "loss": 1.629,
+      "step": 321
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.298387096774194e-05,
+      "loss": 1.6863,
+      "step": 322
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.258064516129033e-05,
+      "loss": 1.5211,
+      "step": 323
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.217741935483872e-05,
+      "loss": 1.6081,
+      "step": 324
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.177419354838711e-05,
+      "loss": 1.6189,
+      "step": 325
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1.844334073434931e+16,
+  "total_flos": 2.003409395608781e+16,
   "trial_name": null,
   "trial_params": null
 }