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:dcd5560dd532c1fc43472e2f09ef6d11a4c95fe440a8e9c77abd2e1a8016102b
+oid sha256:4af9ab2ee86892367697f78b8c17c24efbe43d697972252c355a73ad75b6c74b
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc4ed1a0ab6a767c76d6981dedb731fd057d4aae6ddd00ad9ef95f1404410e2
+oid sha256:2f2566b1b6cfbbcc82efb8bde846fd2cef28f4211109dc1cc2a25355803ea404
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fea7f44c9cf8c01c44d993d41c5b2c69e29a9ba680fc1e08c3ab19b284242a
+oid sha256:a77c53bc138e3c494c930f06c88bd6720dfa8d90da361d8f862ab73b3047f81b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392bd8bbe03297ab7c4b9df9fd51ee66ad2ec583a2667d001f964a207365e199
+oid sha256:d4f6abfc9ba1dd673c96c01d6e226f87125530850c35c2dbe3aed2700dd21ccd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91873a058e2d6d613cd2af893da07d248f0487b89e0051292c25fbba5a047edf
+oid sha256:1c78c18ce52d3d627d763d09f353b3c51f013481592cf6bd1ecc2e2f00217f2f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc7c704e1e66c68286c5ddf74749fde05701934eb0dca6c141ae6494dee842a
+oid sha256:08f91be878dc42ce26a8e0dbed419c26643e10408826891e65fee64a9d8c7046
 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": 11.935075759887695,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08635578583765112,
+  "best_metric": 11.932692527770996,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.17271157167530224,
   "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": 229.652,
       "eval_steps_per_second": 28.721,
       "step": 25
+    },
+    {
+      "epoch": 0.08981001727115717,
+      "grad_norm": 0.06985343992710114,
+      "learning_rate": 5e-05,
+      "loss": 11.9375,
+      "step": 26
+    },
+    {
+      "epoch": 0.09326424870466321,
+      "grad_norm": 0.06996572017669678,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.934,
+      "step": 27
+    },
+    {
+      "epoch": 0.09671848013816926,
+      "grad_norm": 0.08063080906867981,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9362,
+      "step": 28
+    },
+    {
+      "epoch": 0.1001727115716753,
+      "grad_norm": 0.09464134275913239,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9325,
+      "step": 29
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 0.10078255087137222,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9353,
+      "step": 30
+    },
+    {
+      "epoch": 0.1070811744386874,
+      "grad_norm": 0.11674533039331436,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9342,
+      "step": 31
+    },
+    {
+      "epoch": 0.11053540587219343,
+      "grad_norm": 0.12914171814918518,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9355,
+      "step": 32
+    },
+    {
+      "epoch": 0.11398963730569948,
+      "grad_norm": 0.1331762671470642,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9333,
+      "step": 33
+    },
+    {
+      "epoch": 0.11744386873920552,
+      "grad_norm": 0.1348942667245865,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9311,
+      "step": 34
+    },
+    {
+      "epoch": 0.12089810017271158,
+      "grad_norm": 0.13685396313667297,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9319,
+      "step": 35
+    },
+    {
+      "epoch": 0.12435233160621761,
+      "grad_norm": 0.14600132405757904,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9309,
+      "step": 36
+    },
+    {
+      "epoch": 0.12780656303972365,
+      "grad_norm": 0.16344575583934784,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9316,
+      "step": 37
+    },
+    {
+      "epoch": 0.13126079447322972,
+      "grad_norm": 0.10145840793848038,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9345,
+      "step": 38
+    },
+    {
+      "epoch": 0.13471502590673576,
+      "grad_norm": 0.08084696531295776,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9366,
+      "step": 39
+    },
+    {
+      "epoch": 0.1381692573402418,
+      "grad_norm": 0.08430986106395721,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9352,
+      "step": 40
+    },
+    {
+      "epoch": 0.14162348877374784,
+      "grad_norm": 0.0992431789636612,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9346,
+      "step": 41
+    },
+    {
+      "epoch": 0.14507772020725387,
+      "grad_norm": 0.10876741260290146,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9335,
+      "step": 42
+    },
+    {
+      "epoch": 0.14853195164075994,
+      "grad_norm": 0.11824341118335724,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9327,
+      "step": 43
+    },
+    {
+      "epoch": 0.15198618307426598,
+      "grad_norm": 0.12585586309432983,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9324,
+      "step": 44
+    },
+    {
+      "epoch": 0.15544041450777202,
+      "grad_norm": 0.14251390099525452,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9351,
+      "step": 45
+    },
+    {
+      "epoch": 0.15889464594127806,
+      "grad_norm": 0.13823118805885315,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9348,
+      "step": 46
+    },
+    {
+      "epoch": 0.16234887737478412,
+      "grad_norm": 0.14277690649032593,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9315,
+      "step": 47
+    },
+    {
+      "epoch": 0.16580310880829016,
+      "grad_norm": 0.1486414670944214,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9307,
+      "step": 48
+    },
+    {
+      "epoch": 0.1692573402417962,
+      "grad_norm": 0.1497362107038498,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9301,
+      "step": 49
+    },
+    {
+      "epoch": 0.17271157167530224,
+      "grad_norm": 0.16538454592227936,
+      "learning_rate": 0.0,
+      "loss": 11.9283,
+      "step": 50
+    },
+    {
+      "epoch": 0.17271157167530224,
+      "eval_loss": 11.932692527770996,
+      "eval_runtime": 8.6042,
+      "eval_samples_per_second": 226.749,
+      "eval_steps_per_second": 28.358,
+      "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