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:e9e1c7d4f4f4bf1d2daa1ef2f8323e4e88ccf6835a5830171189786c32066e4c
+oid sha256:62e5578d04108688eb421e3cca657a723fca7e0fc2a137a726249ab40d3b5044
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c6e16683be7933bda4774fdb528a0e200870a1e3ec49176d088b708bce04e16
+oid sha256:d6e3176ac60eb899d965d8be5cec3898d3b43c54ffb27f9e16060e594ffde2f3
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57bbb8b4ff796a995e23a66fbd55779265bb3110567c0c01ac48141641446be5
+oid sha256:a06389c591137227674d6e3233138237b76ebcba3cde6f250080abd531fd2cae
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3650bf25e7c04c18172a54042aff810aaaaedcec5bd05e7450764195614c2f6
+oid sha256:ffaebd47d82791c3bf319f97c55e934836ec9f27ce03311665a63952cd5c3180
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6a3525e6ffe22ae7d39ead75575c7b0d9395a03435a7eef48e16b01fd55594
+oid sha256:dcb91c3957e312620676109804ef3403fbea8ce11234ae0c375335865e6b8cfc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbd6a2e5980719a7d3a812ad5c259107709f06b9846e317c3fb3b03d44b937c
+oid sha256:ad60a99c48cc56f079ad1dc67def138ac7908ed5bf0b7ba558c862c748acc789
 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": 0.5041758418083191,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2724795640326976,
+  "best_metric": 0.4216839075088501,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5449591280653951,
   "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": 19.052,
       "eval_steps_per_second": 2.405,
       "step": 25
+    },
+    {
+      "epoch": 0.28337874659400547,
+      "grad_norm": 4.118583679199219,
+      "learning_rate": 5e-05,
+      "loss": 0.4394,
+      "step": 26
+    },
+    {
+      "epoch": 0.29427792915531337,
+      "grad_norm": 2.555344581604004,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4048,
+      "step": 27
+    },
+    {
+      "epoch": 0.30517711171662126,
+      "grad_norm": 2.8441410064697266,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4419,
+      "step": 28
+    },
+    {
+      "epoch": 0.31607629427792916,
+      "grad_norm": 1.463327407836914,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3937,
+      "step": 29
+    },
+    {
+      "epoch": 0.32697547683923706,
+      "grad_norm": 1.5427021980285645,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4078,
+      "step": 30
+    },
+    {
+      "epoch": 0.33787465940054495,
+      "grad_norm": 1.2628159523010254,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4284,
+      "step": 31
+    },
+    {
+      "epoch": 0.34877384196185285,
+      "grad_norm": 1.524219274520874,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.405,
+      "step": 32
+    },
+    {
+      "epoch": 0.35967302452316074,
+      "grad_norm": 1.321671962738037,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4124,
+      "step": 33
+    },
+    {
+      "epoch": 0.37057220708446864,
+      "grad_norm": 1.3506972789764404,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3914,
+      "step": 34
+    },
+    {
+      "epoch": 0.3814713896457766,
+      "grad_norm": 1.0806541442871094,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3978,
+      "step": 35
+    },
+    {
+      "epoch": 0.3923705722070845,
+      "grad_norm": 0.7781311869621277,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3966,
+      "step": 36
+    },
+    {
+      "epoch": 0.4032697547683924,
+      "grad_norm": 1.2545527219772339,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3881,
+      "step": 37
+    },
+    {
+      "epoch": 0.4141689373297003,
+      "grad_norm": 1.2499167919158936,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4066,
+      "step": 38
+    },
+    {
+      "epoch": 0.4250681198910082,
+      "grad_norm": 1.8262399435043335,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3859,
+      "step": 39
+    },
+    {
+      "epoch": 0.4359673024523161,
+      "grad_norm": 1.667894721031189,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4104,
+      "step": 40
+    },
+    {
+      "epoch": 0.44686648501362397,
+      "grad_norm": 0.9992119669914246,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3886,
+      "step": 41
+    },
+    {
+      "epoch": 0.45776566757493187,
+      "grad_norm": 1.4388220310211182,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.379,
+      "step": 42
+    },
+    {
+      "epoch": 0.46866485013623976,
+      "grad_norm": 1.5127443075180054,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3874,
+      "step": 43
+    },
+    {
+      "epoch": 0.47956403269754766,
+      "grad_norm": 1.4673212766647339,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3158,
+      "step": 44
+    },
+    {
+      "epoch": 0.4904632152588556,
+      "grad_norm": 1.724837064743042,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4141,
+      "step": 45
+    },
+    {
+      "epoch": 0.5013623978201635,
+      "grad_norm": 1.2674442529678345,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3687,
+      "step": 46
+    },
+    {
+      "epoch": 0.5122615803814714,
+      "grad_norm": 2.083022356033325,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.42,
+      "step": 47
+    },
+    {
+      "epoch": 0.5231607629427792,
+      "grad_norm": 1.465240240097046,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3703,
+      "step": 48
+    },
+    {
+      "epoch": 0.5340599455040872,
+      "grad_norm": 1.7388436794281006,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4232,
+      "step": 49
+    },
+    {
+      "epoch": 0.5449591280653951,
+      "grad_norm": 1.4903584718704224,
+      "learning_rate": 0.0,
+      "loss": 0.4242,
+      "step": 50
+    },
+    {
+      "epoch": 0.5449591280653951,
+      "eval_loss": 0.4216839075088501,
+      "eval_runtime": 32.4334,
+      "eval_samples_per_second": 19.054,
+      "eval_steps_per_second": 2.405,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null