Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b18784f2bff49757881bfa73ea5608056924e56bbf0954144e05f09a2df4d7
+oid sha256:d32ea6b2cf0cadccc61043a4d637bfd931e625072df7e920819036f3b5750136
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4541cf17b9095a7e00b9aadba1e3019e838b2a54bb5219ed7fc0ee6bd07189e
+oid sha256:1db8e62d7482b255fc60e3f175461ffc4613f7e41ebd2b2c303dd5e35bc98ddb
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5a3b594f8cf48999e8a72760c0e912bdeddb093ff1bc42eeed1cd4499efe80
+oid sha256:5fb4d58ffc82fe9a54ac69644784032b45149128ab122f258f46e3aa970e432f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce4a7d0e1522652c764632b2f0fe7880d0e3972e7c0f300a7a6e1266ed78e477
+oid sha256:94938323398c1cd7a96b545cd91c527643655fec3d183603e610ebcaaaa3d790
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b0980c7126c0921feebc170b5717445c05e59010c08acad4e7353536abb9be
+oid sha256:07cfdc9468617e9af902fc3853686b6bd4876278d05e1bc2f7f2e4ff864e149a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:991ae65022bfa8095c7e9fe298ba348e658ab46dd6a863c553bf5cc26cad4bf2
+oid sha256:e2c5e76bc81398f0b8b8b031637c9d76cd00eda211b67fdba2e6b17ccd395448
 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": 1.927670955657959,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6069802731411229,
+  "best_metric": 1.6710065603256226,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2139605462822458,
   "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": 37.094,
       "eval_steps_per_second": 4.67,
       "step": 25
+    },
+    {
+      "epoch": 0.6312594840667678,
+      "grad_norm": 1.6241158246994019,
+      "learning_rate": 5e-05,
+      "loss": 1.8182,
+      "step": 26
+    },
+    {
+      "epoch": 0.6555386949924128,
+      "grad_norm": 1.8087726831436157,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.7736,
+      "step": 27
+    },
+    {
+      "epoch": 0.6798179059180577,
+      "grad_norm": 1.6155797243118286,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.7638,
+      "step": 28
+    },
+    {
+      "epoch": 0.7040971168437026,
+      "grad_norm": 1.3127691745758057,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.7378,
+      "step": 29
+    },
+    {
+      "epoch": 0.7283763277693475,
+      "grad_norm": 1.5962766408920288,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.7503,
+      "step": 30
+    },
+    {
+      "epoch": 0.7526555386949925,
+      "grad_norm": 5.721963405609131,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.168,
+      "step": 31
+    },
+    {
+      "epoch": 0.7769347496206374,
+      "grad_norm": 5.783325672149658,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1028,
+      "step": 32
+    },
+    {
+      "epoch": 0.8012139605462822,
+      "grad_norm": 2.1208581924438477,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8764,
+      "step": 33
+    },
+    {
+      "epoch": 0.8254931714719271,
+      "grad_norm": 1.8140983581542969,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7664,
+      "step": 34
+    },
+    {
+      "epoch": 0.849772382397572,
+      "grad_norm": 1.8352196216583252,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6668,
+      "step": 35
+    },
+    {
+      "epoch": 0.874051593323217,
+      "grad_norm": 1.4118400812149048,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.596,
+      "step": 36
+    },
+    {
+      "epoch": 0.8983308042488619,
+      "grad_norm": 1.183858036994934,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.6097,
+      "step": 37
+    },
+    {
+      "epoch": 0.9226100151745068,
+      "grad_norm": 1.1412922143936157,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5944,
+      "step": 38
+    },
+    {
+      "epoch": 0.9468892261001517,
+      "grad_norm": 1.0928421020507812,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6146,
+      "step": 39
+    },
+    {
+      "epoch": 0.9711684370257967,
+      "grad_norm": 0.8960613012313843,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6443,
+      "step": 40
+    },
+    {
+      "epoch": 0.9954476479514416,
+      "grad_norm": 2.1606767177581787,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.7848,
+      "step": 41
+    },
+    {
+      "epoch": 1.0197268588770865,
+      "grad_norm": 5.754116535186768,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.3251,
+      "step": 42
+    },
+    {
+      "epoch": 1.0440060698027314,
+      "grad_norm": 2.2257285118103027,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.7731,
+      "step": 43
+    },
+    {
+      "epoch": 1.0682852807283763,
+      "grad_norm": 1.3417719602584839,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6985,
+      "step": 44
+    },
+    {
+      "epoch": 1.0925644916540211,
+      "grad_norm": 1.3849780559539795,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.591,
+      "step": 45
+    },
+    {
+      "epoch": 1.1168437025796663,
+      "grad_norm": 1.1332714557647705,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5775,
+      "step": 46
+    },
+    {
+      "epoch": 1.1411229135053111,
+      "grad_norm": 1.1728425025939941,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.55,
+      "step": 47
+    },
+    {
+      "epoch": 1.165402124430956,
+      "grad_norm": 1.065137267112732,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5417,
+      "step": 48
+    },
+    {
+      "epoch": 1.189681335356601,
+      "grad_norm": 1.141374945640564,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5862,
+      "step": 49
+    },
+    {
+      "epoch": 1.2139605462822458,
+      "grad_norm": 0.9663513898849487,
+      "learning_rate": 0.0,
+      "loss": 1.6085,
+      "step": 50
+    },
+    {
+      "epoch": 1.2139605462822458,
+      "eval_loss": 1.6710065603256226,
+      "eval_runtime": 8.276,
+      "eval_samples_per_second": 33.591,
+      "eval_steps_per_second": 4.229,
+      "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": 8.33416392081408e+16,
+  "total_flos": 1.666832784162816e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null