Training in progress, step 294, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9712c86078961cd9f3a8663293c6282fa47f5858200f9941450b82ef4014cf
+oid sha256:ac8066d8618fb64be2b7faf41fa7b3d7fddf6534795172bb25bde20b59e6c4ff
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dce1a8f7dce5667d5b6c4d2cf60ccefedf33892d6f8d61c5059640a01ae30d67
+oid sha256:0e0e88d1e758b2d942c5d8dfb1b4aeae98139e8b2d7ef5f9e51eb4f00514fef3
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5534d35f620616a57793fd6cbb1afb4369bf452a60440fde4d3e848a5ba93a
+oid sha256:e958b5311b12f031b567f23b298951420ae35c9252f43db99115fccddb611c82
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc4c947fbc9c9dca3af245fd32a570156e6b78d4eaec238dedd3231429128b70
+oid sha256:168cc6d91836120c82b575ebf5734abdb841b4263d9f2f41a03d08fad1f896b4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0cda03be8969147a49c0ef4dde3c548369e603b8592b5f852a74a539ddc2d9
+oid sha256:405794cde8faebc39bd31ecef58d05da57c890cf01b9aa621202411aa70597e3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce24fb28254be2a4282f7fedfa170e840115f3e06e7e48095ca5c7a28a68c469
+oid sha256:aa89b254c849b8c89c11fda2f7202c45b30deae097716d903b96cad962e9a032
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee19ddad9c4c375a1de2d74fb4c1cf5e15d36c1ed47a2cb80f7cb0fbacb3b29e
+oid sha256:318b114b83c26bcba11815378a88e0015bce044b0002c702e0a2627e1a1d1e56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6583932070542129,
+  "epoch": 0.768125408229915,
   "eval_steps": 42,
-  "global_step": 252,
+  "global_step": 294,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -651,6 +651,112 @@
       "eval_samples_per_second": 777.394,
       "eval_steps_per_second": 24.425,
       "step": 252
+    },
+    {
+      "epoch": 0.6662312214239059,
+      "grad_norm": 0.01651047170162201,
+      "learning_rate": 5e-05,
+      "loss": 11.9174,
+      "step": 255
+    },
+    {
+      "epoch": 0.674069235793599,
+      "grad_norm": 0.016767192631959915,
+      "learning_rate": 4.903834726061565e-05,
+      "loss": 11.9184,
+      "step": 258
+    },
+    {
+      "epoch": 0.681907250163292,
+      "grad_norm": 0.01721210964024067,
+      "learning_rate": 4.807705027948008e-05,
+      "loss": 11.9177,
+      "step": 261
+    },
+    {
+      "epoch": 0.689745264532985,
+      "grad_norm": 0.0172222089022398,
+      "learning_rate": 4.711646468323129e-05,
+      "loss": 11.9178,
+      "step": 264
+    },
+    {
+      "epoch": 0.697583278902678,
+      "grad_norm": 0.016364743933081627,
+      "learning_rate": 4.6156945835334184e-05,
+      "loss": 11.9181,
+      "step": 267
+    },
+    {
+      "epoch": 0.705421293272371,
+      "grad_norm": 0.016128098592162132,
+      "learning_rate": 4.5198848704615914e-05,
+      "loss": 11.9178,
+      "step": 270
+    },
+    {
+      "epoch": 0.713259307642064,
+      "grad_norm": 0.015332392416894436,
+      "learning_rate": 4.424252773394704e-05,
+      "loss": 11.9177,
+      "step": 273
+    },
+    {
+      "epoch": 0.721097322011757,
+      "grad_norm": 0.01631457917392254,
+      "learning_rate": 4.328833670911724e-05,
+      "loss": 11.9181,
+      "step": 276
+    },
+    {
+      "epoch": 0.72893533638145,
+      "grad_norm": 0.018029581755399704,
+      "learning_rate": 4.23366286279542e-05,
+      "loss": 11.9173,
+      "step": 279
+    },
+    {
+      "epoch": 0.736773350751143,
+      "grad_norm": 0.016118017956614494,
+      "learning_rate": 4.138775556973406e-05,
+      "loss": 11.9175,
+      "step": 282
+    },
+    {
+      "epoch": 0.744611365120836,
+      "grad_norm": 0.0235885176807642,
+      "learning_rate": 4.04420685649314e-05,
+      "loss": 11.9174,
+      "step": 285
+    },
+    {
+      "epoch": 0.752449379490529,
+      "grad_norm": 0.02053360641002655,
+      "learning_rate": 3.9499917465357534e-05,
+      "loss": 11.9178,
+      "step": 288
+    },
+    {
+      "epoch": 0.760287393860222,
+      "grad_norm": 0.018186945468187332,
+      "learning_rate": 3.856165081473474e-05,
+      "loss": 11.9181,
+      "step": 291
+    },
+    {
+      "epoch": 0.768125408229915,
+      "grad_norm": 0.029430339112877846,
+      "learning_rate": 3.762761571975429e-05,
+      "loss": 11.9174,
+      "step": 294
+    },
+    {
+      "epoch": 0.768125408229915,
+      "eval_loss": 11.917236328125,
+      "eval_runtime": 3.3236,
+      "eval_samples_per_second": 775.653,
+      "eval_steps_per_second": 24.371,
+      "step": 294
     }
   ],
   "logging_steps": 3,
@@ -670,7 +776,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4860599992320.0,
+  "total_flos": 5671704330240.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null