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:f4791fe3ce7674ec5d6aac00b69bcd63e7225491548832a92d5ac8ac3049e303
+oid sha256:8dd16809d49cbb2e0913ef0e5e70d6a1cf27ea8274906a6ec8897f72549965f5
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab76817b8d1796c25e0f140c63539c0ffd1a2176da5e528c75ac6766204403e
+oid sha256:22b0b5a8a77a96c9b9d065fb4f21532b1d807848b0115043a77f33ecf438d1f5
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b87926436ba272c1bc8e2b8213755600e87b668e49014386324b43afff8538
+oid sha256:9205a43f8ba8a4e45bf86439d9891d5e3768cacca3416f9078fb61d9a835a6c8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930b3221b1d61bd466d0731fcd5481e116e308cb44496692424bc22b147c736c
+oid sha256:3701e8df01a382eb2869fd5fd1530f7b495f861fc3da620f77ecec8413c86545
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849a2e6b84480a2ac2b40fc1a631b634049fc0c6fdb2b98d4c5416f2dfe5712b
+oid sha256:25a81b1318d401588b5c81cdedf4f2e744ee3740edc5dd8efed3198201225237
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ef52079f9ae2b05dda7ebd108a14d3a869e83ab5058def7b9a301a241fa022
+oid sha256:5630351f2937d2f70904dc053d91700c7c3a12fbdfcc723e726f1283d246ba54
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.930604934692383,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06609385327164574,
+  "best_metric": 11.930046081542969,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13218770654329148,
   "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": 511.231,
       "eval_steps_per_second": 63.979,
       "step": 25
+    },
+    {
+      "epoch": 0.06873760740251157,
+      "grad_norm": 0.023965967819094658,
+      "learning_rate": 5e-05,
+      "loss": 11.9315,
+      "step": 26
+    },
+    {
+      "epoch": 0.0713813615333774,
+      "grad_norm": 0.028746068477630615,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9309,
+      "step": 27
+    },
+    {
+      "epoch": 0.07402511566424323,
+      "grad_norm": 0.02350783348083496,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9309,
+      "step": 28
+    },
+    {
+      "epoch": 0.07666886979510905,
+      "grad_norm": 0.023529646918177605,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9306,
+      "step": 29
+    },
+    {
+      "epoch": 0.07931262392597488,
+      "grad_norm": 0.029583023861050606,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.931,
+      "step": 30
+    },
+    {
+      "epoch": 0.08195637805684071,
+      "grad_norm": 0.03481192886829376,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9314,
+      "step": 31
+    },
+    {
+      "epoch": 0.08460013218770654,
+      "grad_norm": 0.029739735648036003,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9306,
+      "step": 32
+    },
+    {
+      "epoch": 0.08724388631857237,
+      "grad_norm": 0.045527901500463486,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9296,
+      "step": 33
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 0.04223807901144028,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9297,
+      "step": 34
+    },
+    {
+      "epoch": 0.09253139458030403,
+      "grad_norm": 0.04213787242770195,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9264,
+      "step": 35
+    },
+    {
+      "epoch": 0.09517514871116986,
+      "grad_norm": 0.05223255604505539,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9304,
+      "step": 36
+    },
+    {
+      "epoch": 0.09781890284203569,
+      "grad_norm": 0.06267008930444717,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.93,
+      "step": 37
+    },
+    {
+      "epoch": 0.10046265697290152,
+      "grad_norm": 0.028014397248625755,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9311,
+      "step": 38
+    },
+    {
+      "epoch": 0.10310641110376735,
+      "grad_norm": 0.027659038081765175,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.931,
+      "step": 39
+    },
+    {
+      "epoch": 0.10575016523463318,
+      "grad_norm": 0.02421857975423336,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.931,
+      "step": 40
+    },
+    {
+      "epoch": 0.10839391936549901,
+      "grad_norm": 0.028048740699887276,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9312,
+      "step": 41
+    },
+    {
+      "epoch": 0.11103767349636484,
+      "grad_norm": 0.029408879578113556,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9307,
+      "step": 42
+    },
+    {
+      "epoch": 0.11368142762723067,
+      "grad_norm": 0.030845344066619873,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9309,
+      "step": 43
+    },
+    {
+      "epoch": 0.1163251817580965,
+      "grad_norm": 0.037856973707675934,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9294,
+      "step": 44
+    },
+    {
+      "epoch": 0.11896893588896233,
+      "grad_norm": 0.04141073301434517,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9316,
+      "step": 45
+    },
+    {
+      "epoch": 0.12161269001982816,
+      "grad_norm": 0.034333162009716034,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9299,
+      "step": 46
+    },
+    {
+      "epoch": 0.12425644415069398,
+      "grad_norm": 0.04394075274467468,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.928,
+      "step": 47
+    },
+    {
+      "epoch": 0.12690019828155982,
+      "grad_norm": 0.05368373543024063,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.927,
+      "step": 48
+    },
+    {
+      "epoch": 0.12954395241242564,
+      "grad_norm": 0.042175471782684326,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9265,
+      "step": 49
+    },
+    {
+      "epoch": 0.13218770654329148,
+      "grad_norm": 0.05652758851647377,
+      "learning_rate": 0.0,
+      "loss": 11.9265,
+      "step": 50
+    },
+    {
+      "epoch": 0.13218770654329148,
+      "eval_loss": 11.930046081542969,
+      "eval_runtime": 5.012,
+      "eval_samples_per_second": 508.575,
+      "eval_steps_per_second": 63.647,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null