Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7edad36884b2c5cb3a70c9d58bc0276e29fc623d13ac5c53ba14e933a8877ec
+oid sha256:55106b2193e7e96cb29be1ff917c68aa09b015696f358032fe14437de80815f9
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b91b36ca732ecfc4a6a799e347bd343d84f4e9f7eea1f53b96857295218dca0
+oid sha256:9e00bb8f99b1dd8d3a520d6d77d51622c0a84ed374efd76777ab8511819175a1
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64c41d4f060b02491b840b82539c5d36233e5c364d451d022f310b8f8d58b082
+oid sha256:f072cc679b4591b13343c2f99b073847ce7e3f6b186430a222f04d73655cf2d9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80afb9bb349ed31472ed0057f7f4691e56b8069dcc4276748f3beb567454664b
+oid sha256:103d807a8aa9689d726be76a6c7b722b5b60393fd4668639765cffced2175eb7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497c314ea56ff7c7a5aa14a80788746005e8b8fa3518a26a09112cc8124c09f6
+oid sha256:12c0aeb5969863fdbec01080313f102e53ee36b002fb9383bfa48ce9dc0cb119
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3dfb0e1e3e4bd3795aa487cb423594c38f927acae2a21adedb40f6b23a13d0a
+oid sha256:93f7493a121accf25f35377a404b720511fa423ee8ba2b2f8561afc5def4838e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff07b2dac43cc1ae8276fc70b3c16c2f6801a37034beff7540efa566da8b878
+oid sha256:33e81119d658b18407dc132d7fdb38f3caf7aed57798ea11f920c85dc8964b35
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0208630561828613,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16035277610743637,
+  "best_metric": 0.9231343865394592,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.32070555221487274,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 48.573,
       "eval_steps_per_second": 12.629,
       "step": 25
+    },
+    {
+      "epoch": 0.16676688715173382,
+      "grad_norm": 0.5933877229690552,
+      "learning_rate": 9.578385041664925e-05,
+      "loss": 1.1207,
+      "step": 26
+    },
+    {
+      "epoch": 0.17318099819603128,
+      "grad_norm": 0.7073403000831604,
+      "learning_rate": 9.535927336897098e-05,
+      "loss": 1.0747,
+      "step": 27
+    },
+    {
+      "epoch": 0.17959510924032873,
+      "grad_norm": 0.6395047903060913,
+      "learning_rate": 9.491548749301997e-05,
+      "loss": 1.0038,
+      "step": 28
+    },
+    {
+      "epoch": 0.1860092202846262,
+      "grad_norm": 0.5215311050415039,
+      "learning_rate": 9.445270400683786e-05,
+      "loss": 0.9655,
+      "step": 29
+    },
+    {
+      "epoch": 0.19242333132892364,
+      "grad_norm": 0.5276326537132263,
+      "learning_rate": 9.397114317029975e-05,
+      "loss": 0.9261,
+      "step": 30
+    },
+    {
+      "epoch": 0.1988374423732211,
+      "grad_norm": 0.45551949739456177,
+      "learning_rate": 9.34710341802826e-05,
+      "loss": 0.9266,
+      "step": 31
+    },
+    {
+      "epoch": 0.20525155341751855,
+      "grad_norm": 0.5097278356552124,
+      "learning_rate": 9.295261506157986e-05,
+      "loss": 0.9474,
+      "step": 32
+    },
+    {
+      "epoch": 0.211665664461816,
+      "grad_norm": 0.4889874756336212,
+      "learning_rate": 9.241613255361455e-05,
+      "loss": 0.9348,
+      "step": 33
+    },
+    {
+      "epoch": 0.21807977550611346,
+      "grad_norm": 0.6000301837921143,
+      "learning_rate": 9.186184199300464e-05,
+      "loss": 0.9084,
+      "step": 34
+    },
+    {
+      "epoch": 0.22449388655041091,
+      "grad_norm": 0.6574684977531433,
+      "learning_rate": 9.129000719203672e-05,
+      "loss": 0.9656,
+      "step": 35
+    },
+    {
+      "epoch": 0.23090799759470837,
+      "grad_norm": 0.6883850693702698,
+      "learning_rate": 9.070090031310558e-05,
+      "loss": 0.894,
+      "step": 36
+    },
+    {
+      "epoch": 0.23732210863900582,
+      "grad_norm": 0.7173681855201721,
+      "learning_rate": 9.009480173917968e-05,
+      "loss": 1.0018,
+      "step": 37
+    },
+    {
+      "epoch": 0.24373621968330328,
+      "grad_norm": 0.3584338128566742,
+      "learning_rate": 8.947199994035401e-05,
+      "loss": 1.0744,
+      "step": 38
+    },
+    {
+      "epoch": 0.25015033072760073,
+      "grad_norm": 0.4074675440788269,
+      "learning_rate": 8.883279133655399e-05,
+      "loss": 0.9454,
+      "step": 39
+    },
+    {
+      "epoch": 0.2565644417718982,
+      "grad_norm": 0.5095922350883484,
+      "learning_rate": 8.817748015645558e-05,
+      "loss": 0.9923,
+      "step": 40
+    },
+    {
+      "epoch": 0.26297855281619564,
+      "grad_norm": 0.511969268321991,
+      "learning_rate": 8.7506378292689e-05,
+      "loss": 0.9529,
+      "step": 41
+    },
+    {
+      "epoch": 0.2693926638604931,
+      "grad_norm": 0.5053486824035645,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.9017,
+      "step": 42
+    },
+    {
+      "epoch": 0.27580677490479055,
+      "grad_norm": 0.547535240650177,
+      "learning_rate": 8.611808751020213e-05,
+      "loss": 0.9219,
+      "step": 43
+    },
+    {
+      "epoch": 0.282220885949088,
+      "grad_norm": 0.47144246101379395,
+      "learning_rate": 8.540155934270471e-05,
+      "loss": 0.9067,
+      "step": 44
+    },
+    {
+      "epoch": 0.28863499699338546,
+      "grad_norm": 0.49577343463897705,
+      "learning_rate": 8.467056167950311e-05,
+      "loss": 0.9403,
+      "step": 45
+    },
+    {
+      "epoch": 0.2950491080376829,
+      "grad_norm": 0.5017397403717041,
+      "learning_rate": 8.392544243589427e-05,
+      "loss": 0.9151,
+      "step": 46
+    },
+    {
+      "epoch": 0.30146321908198037,
+      "grad_norm": 0.49621936678886414,
+      "learning_rate": 8.316655624828267e-05,
+      "loss": 0.8998,
+      "step": 47
+    },
+    {
+      "epoch": 0.3078773301262778,
+      "grad_norm": 0.4927474856376648,
+      "learning_rate": 8.239426430539243e-05,
+      "loss": 0.9294,
+      "step": 48
+    },
+    {
+      "epoch": 0.3142914411705753,
+      "grad_norm": 0.7246368527412415,
+      "learning_rate": 8.160893417636122e-05,
+      "loss": 0.8953,
+      "step": 49
+    },
+    {
+      "epoch": 0.32070555221487274,
+      "grad_norm": 0.7401767373085022,
+      "learning_rate": 8.081093963579707e-05,
+      "loss": 0.9852,
+      "step": 50
+    },
+    {
+      "epoch": 0.32070555221487274,
+      "eval_loss": 0.9231343865394592,
+      "eval_runtime": 1.0157,
+      "eval_samples_per_second": 49.226,
+      "eval_steps_per_second": 12.799,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.168384167647642e+16,
+  "total_flos": 8.335466128054682e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null