Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b703e9cc83f09aa1645c1fb06d119545c0773a385bec0479c387e0db122e890
+oid sha256:d103416ee9b67b8bbc643c4785c8828fb4130efe24b7aa9572ffddb1754d93d7
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba95886ca1c5e495b12095924f3042c285fbcf531441e2cf247bba02379672f
+oid sha256:8611580277b87c7e80dc955e45b2e5f73cd7d65f6998fc2f0714542a5d1b8d2e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb1509b8f4a8bf89e21531458710b8b2db7090eec7bfd331c27e599b27ddf9a
+oid sha256:ac823423652be56132551c4c005c8e2c82e9948f609145126da9ae7f5df35f5d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b6e6f556507ecc21c5895a591175c26aaca67e14a8528c16a3a98bf406f3fce
+oid sha256:3581779bc3b4a75a98a31d28e2c7575597a5019a46fe3c2c27a9a508d508fc26
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b8163a3b6dfa01cb41030813839a542f976c7fe30f3d4dc592a804d6e6a65c
+oid sha256:8fec4572488448c1b2af0d256063b65260830a03f347908bd781876dfac34377
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40383d6b5f32a953f1a38f4009e45e69507007711a0de00f4b309db88b15d81
+oid sha256:a3e91c9e849665857cfa5f83636b6d0274520074c850ece1e8e81ef46ebd6080
 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": 1.8366632461547852,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004505011825656042,
+  "best_metric": 1.2600817680358887,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009010023651312085,
   "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": 34.276,
       "eval_steps_per_second": 4.285,
       "step": 25
+    },
+    {
+      "epoch": 0.004685212298682284,
+      "grad_norm": 396.5668640136719,
+      "learning_rate": 5e-05,
+      "loss": 1.9594,
+      "step": 26
+    },
+    {
+      "epoch": 0.004865412771708526,
+      "grad_norm": 294.597412109375,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.634,
+      "step": 27
+    },
+    {
+      "epoch": 0.005045613244734767,
+      "grad_norm": 136.92575073242188,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3111,
+      "step": 28
+    },
+    {
+      "epoch": 0.005225813717761009,
+      "grad_norm": 110.47759246826172,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.064,
+      "step": 29
+    },
+    {
+      "epoch": 0.005406014190787251,
+      "grad_norm": 58.943016052246094,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9738,
+      "step": 30
+    },
+    {
+      "epoch": 0.005586214663813493,
+      "grad_norm": 59.696449279785156,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0141,
+      "step": 31
+    },
+    {
+      "epoch": 0.005766415136839734,
+      "grad_norm": 85.00813293457031,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8938,
+      "step": 32
+    },
+    {
+      "epoch": 0.005946615609865976,
+      "grad_norm": 85.3294448852539,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9989,
+      "step": 33
+    },
+    {
+      "epoch": 0.006126816082892218,
+      "grad_norm": 75.4062728881836,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7484,
+      "step": 34
+    },
+    {
+      "epoch": 0.006307016555918459,
+      "grad_norm": 41.243289947509766,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.7629,
+      "step": 35
+    },
+    {
+      "epoch": 0.006487217028944701,
+      "grad_norm": 109.47763061523438,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8702,
+      "step": 36
+    },
+    {
+      "epoch": 0.006667417501970942,
+      "grad_norm": 91.96109771728516,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4017,
+      "step": 37
+    },
+    {
+      "epoch": 0.006847617974997184,
+      "grad_norm": 108.82039642333984,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4319,
+      "step": 38
+    },
+    {
+      "epoch": 0.007027818448023426,
+      "grad_norm": 140.50625610351562,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0842,
+      "step": 39
+    },
+    {
+      "epoch": 0.007208018921049668,
+      "grad_norm": 125.83114624023438,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1076,
+      "step": 40
+    },
+    {
+      "epoch": 0.00738821939407591,
+      "grad_norm": 99.77587127685547,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9724,
+      "step": 41
+    },
+    {
+      "epoch": 0.007568419867102151,
+      "grad_norm": 74.81304931640625,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8177,
+      "step": 42
+    },
+    {
+      "epoch": 0.007748620340128393,
+      "grad_norm": 87.92131042480469,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8535,
+      "step": 43
+    },
+    {
+      "epoch": 0.007928820813154635,
+      "grad_norm": 61.635467529296875,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0801,
+      "step": 44
+    },
+    {
+      "epoch": 0.008109021286180877,
+      "grad_norm": 25.429811477661133,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.7536,
+      "step": 45
+    },
+    {
+      "epoch": 0.008289221759207118,
+      "grad_norm": 25.9411563873291,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6849,
+      "step": 46
+    },
+    {
+      "epoch": 0.00846942223223336,
+      "grad_norm": 59.82724380493164,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7406,
+      "step": 47
+    },
+    {
+      "epoch": 0.008649622705259602,
+      "grad_norm": 39.6214485168457,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.7147,
+      "step": 48
+    },
+    {
+      "epoch": 0.008829823178285843,
+      "grad_norm": 57.82444381713867,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7065,
+      "step": 49
+    },
+    {
+      "epoch": 0.009010023651312085,
+      "grad_norm": 90.7107925415039,
+      "learning_rate": 0.0,
+      "loss": 1.6246,
+      "step": 50
+    },
+    {
+      "epoch": 0.009010023651312085,
+      "eval_loss": 1.2600817680358887,
+      "eval_runtime": 1090.8587,
+      "eval_samples_per_second": 34.272,
+      "eval_steps_per_second": 4.285,
+      "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": 2.8307820210290688e+17,
+  "total_flos": 5.659795911396557e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null