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:f12fe7776df5d3c3505abba7b31e63bacd898d7aa1abf191f7fe6328fc83d0c5
+oid sha256:f3720f048f0e0d5bb3af893066bfb1914d0c131628fb657807ad6b9376801e38
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc7592851645f5ba6bb0b8128cd9247746d7c1dbe1da7d9f129df405146d994
+oid sha256:eea8146b9a45a50d4677f46f81c71cf2760d4f610bc2f82c664d27de4c3719eb
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928213ab2e09763e116d1bfb478aad8f4139c963ed129d921a2501493e30efdd
+oid sha256:19ba59754b31e5e79014ce130754a8a3fdf9772677ff18499997328c0d9c7146
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:004d7c9b66ee0132acc47b6d5e9cb18d0a333840a025bac015ed1d6ed63c4eb2
+oid sha256:a7de3ad2b13e4a7ba5f0a10459abaecc1f8b8fd8b60df9729954c4f5b657c917
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd4edda31bf9d44bcea92ce7553db96d7effb20ed51068a52ee0d69285b7d6f
+oid sha256:e36a52e22bbc9b8b07d332783d70b5d67be7c5d641e448758d33c9fb54f4a57d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6656893e56520b745793e71047f05cb9279d9ef3478b134f3967730170f391bc
+oid sha256:4d38ebc3e63761f676d20556f4357162d5180abd6204d3d2f4a79245e233103a
 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": 0.13296709954738617,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33783783783783783,
+  "best_metric": 0.10377126187086105,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6756756756756757,
   "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": 34.094,
       "eval_steps_per_second": 4.304,
       "step": 25
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 1.1895753145217896,
+      "learning_rate": 5e-05,
+      "loss": 0.1106,
+      "step": 26
+    },
+    {
+      "epoch": 0.36486486486486486,
+      "grad_norm": 2.3610384464263916,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2791,
+      "step": 27
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 1.643008828163147,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1546,
+      "step": 28
+    },
+    {
+      "epoch": 0.3918918918918919,
+      "grad_norm": 1.6177732944488525,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1978,
+      "step": 29
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 1.8108652830123901,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2273,
+      "step": 30
+    },
+    {
+      "epoch": 0.4189189189189189,
+      "grad_norm": 2.1313583850860596,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1894,
+      "step": 31
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 1.4777275323867798,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.232,
+      "step": 32
+    },
+    {
+      "epoch": 0.44594594594594594,
+      "grad_norm": 1.6066914796829224,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2551,
+      "step": 33
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 1.397235631942749,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.253,
+      "step": 34
+    },
+    {
+      "epoch": 0.47297297297297297,
+      "grad_norm": 1.329254150390625,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2383,
+      "step": 35
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 1.3167423009872437,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1335,
+      "step": 36
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0337791442871094,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1781,
+      "step": 37
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.6120166778564453,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1018,
+      "step": 38
+    },
+    {
+      "epoch": 0.527027027027027,
+      "grad_norm": 0.6781937479972839,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1015,
+      "step": 39
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.6627649068832397,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0898,
+      "step": 40
+    },
+    {
+      "epoch": 0.5540540540540541,
+      "grad_norm": 0.9930323362350464,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.073,
+      "step": 41
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 0.8100405931472778,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1591,
+      "step": 42
+    },
+    {
+      "epoch": 0.581081081081081,
+      "grad_norm": 0.8315913677215576,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1893,
+      "step": 43
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 1.6323856115341187,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.21,
+      "step": 44
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "grad_norm": 1.213604211807251,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1902,
+      "step": 45
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 1.0373070240020752,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1713,
+      "step": 46
+    },
+    {
+      "epoch": 0.6351351351351351,
+      "grad_norm": 0.6015317440032959,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1038,
+      "step": 47
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 1.1619991064071655,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1853,
+      "step": 48
+    },
+    {
+      "epoch": 0.6621621621621622,
+      "grad_norm": 0.6225360035896301,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1095,
+      "step": 49
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.8265971541404724,
+      "learning_rate": 0.0,
+      "loss": 0.1351,
+      "step": 50
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "eval_loss": 0.10377126187086105,
+      "eval_runtime": 14.6286,
+      "eval_samples_per_second": 34.111,
+      "eval_steps_per_second": 4.307,
+      "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": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null