Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7263fa7b3e4f1a27836a9f8fce79ab6c80b5ccd28d6ae2820dd68030f9f49936
+oid sha256:498e18dad9a0b7dc745a9b751d40f6f285b65a5e34bdb7fae681cd096afcf39b
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1409d398f6ef13935de26ad6849703d64b9144c376c82c1ab0f6786598f79ee9
+oid sha256:34fa27e0b3d407cd61b8313ed7eb460bef42fd3342409f80104166dc5b3c4b8b
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90e75b624a116d593926c2f893193f435b8ad85c7b04c9f3135620718912208
+oid sha256:46cc9f1db2e82bbda4a000cf71ef60cf7abccb3cd052046669230cb3223a0d4c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c4fef201f7e36d21c8d168734c22e1a592bf1e1f436baf0b0a40b137195a97
+oid sha256:8f1fd19c47de3ad1ac6270e58c394fe040c72cae1684f44b8fa0e419a2d567f1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7b475027332b9e901c29257a640942435b54bf966fa2cc7cde0aee756bc8fb
+oid sha256:c1c9bacc152e9ae447b2a9afd3c51d5ea0811b6a8df79346535e0d19918d408b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a604a0cb7a4bd7ba3fbe13c45971c646d9490b4e8affd64f33fc745b521625a8
+oid sha256:03820cc91e698a7ff74a7f5173f673aefd2100a840b3bc61bc223515d1fe52a2
 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": 1.5651992559432983,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06501950585175553,
+  "best_metric": 1.5425931215286255,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13003901170351106,
   "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": 115.571,
       "eval_steps_per_second": 14.452,
       "step": 25
+    },
+    {
+      "epoch": 0.06762028608582575,
+      "grad_norm": 0.0953252986073494,
+      "learning_rate": 5e-05,
+      "loss": 1.4085,
+      "step": 26
+    },
+    {
+      "epoch": 0.07022106631989597,
+      "grad_norm": 0.09956612437963486,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4664,
+      "step": 27
+    },
+    {
+      "epoch": 0.07282184655396619,
+      "grad_norm": 0.11147274821996689,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.5273,
+      "step": 28
+    },
+    {
+      "epoch": 0.0754226267880364,
+      "grad_norm": 0.12826047837734222,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.5368,
+      "step": 29
+    },
+    {
+      "epoch": 0.07802340702210664,
+      "grad_norm": 0.13391107320785522,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.5507,
+      "step": 30
+    },
+    {
+      "epoch": 0.08062418725617686,
+      "grad_norm": 0.13899120688438416,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.5767,
+      "step": 31
+    },
+    {
+      "epoch": 0.08322496749024708,
+      "grad_norm": 0.15416182577610016,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5633,
+      "step": 32
+    },
+    {
+      "epoch": 0.0858257477243173,
+      "grad_norm": 0.19598853588104248,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5447,
+      "step": 33
+    },
+    {
+      "epoch": 0.08842652795838751,
+      "grad_norm": 0.24805714190006256,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5419,
+      "step": 34
+    },
+    {
+      "epoch": 0.09102730819245773,
+      "grad_norm": 0.32029539346694946,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5999,
+      "step": 35
+    },
+    {
+      "epoch": 0.09362808842652796,
+      "grad_norm": 0.3935973346233368,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5974,
+      "step": 36
+    },
+    {
+      "epoch": 0.09622886866059818,
+      "grad_norm": 0.5263167023658752,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4174,
+      "step": 37
+    },
+    {
+      "epoch": 0.0988296488946684,
+      "grad_norm": 0.10492201894521713,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3571,
+      "step": 38
+    },
+    {
+      "epoch": 0.10143042912873862,
+      "grad_norm": 0.10784497857093811,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5052,
+      "step": 39
+    },
+    {
+      "epoch": 0.10403120936280884,
+      "grad_norm": 0.09847010672092438,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4734,
+      "step": 40
+    },
+    {
+      "epoch": 0.10663198959687907,
+      "grad_norm": 0.11888845264911652,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5328,
+      "step": 41
+    },
+    {
+      "epoch": 0.10923276983094929,
+      "grad_norm": 0.12106700986623764,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5251,
+      "step": 42
+    },
+    {
+      "epoch": 0.11183355006501951,
+      "grad_norm": 0.14373373985290527,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6022,
+      "step": 43
+    },
+    {
+      "epoch": 0.11443433029908973,
+      "grad_norm": 0.15439628064632416,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5658,
+      "step": 44
+    },
+    {
+      "epoch": 0.11703511053315994,
+      "grad_norm": 0.18161892890930176,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6469,
+      "step": 45
+    },
+    {
+      "epoch": 0.11963589076723016,
+      "grad_norm": 0.2562808692455292,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6132,
+      "step": 46
+    },
+    {
+      "epoch": 0.1222366710013004,
+      "grad_norm": 0.2922062575817108,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5971,
+      "step": 47
+    },
+    {
+      "epoch": 0.12483745123537061,
+      "grad_norm": 0.37385690212249756,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6268,
+      "step": 48
+    },
+    {
+      "epoch": 0.12743823146944083,
+      "grad_norm": 0.42741650342941284,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.6055,
+      "step": 49
+    },
+    {
+      "epoch": 0.13003901170351106,
+      "grad_norm": 0.7190040946006775,
+      "learning_rate": 0.0,
+      "loss": 1.4895,
+      "step": 50
+    },
+    {
+      "epoch": 0.13003901170351106,
+      "eval_loss": 1.5425931215286255,
+      "eval_runtime": 22.4336,
+      "eval_samples_per_second": 115.497,
+      "eval_steps_per_second": 14.443,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null