Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f383172b8ac08b0c03f59fe0654f0985f02e8d08edfd78789d0b672926eedf9
+oid sha256:a95738c4e8b193c1faf7de3af887447f7b2aaf14c89383b14b60597ff85a6043
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e807b26587f4e8c580a9d22d6cc05e7e90bf73666fa5b8314af2b31a6092f9bb
+oid sha256:d864d1fd3652a2ce8a2bd723c73dcdc4e94f3636b9e1e5dd6fdac58e30ac7a7d
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07966ffbc514ab7bb09c4e967d607ed65a27a1c578d34e13246507c2e317e335
+oid sha256:6799fb34bb7259c838f2c578702863001b7a82de5e97fed7d21befa349b2fad6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29b56251c4e24ffc4ab6e7b1442f17eee70c7e5c3d7149bf63a81a2d8367222
+oid sha256:8ce44b29c5773ea6c8207ad803f6257dab6995355276e3b5843c352f16ad5d25
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f22f079fada1ec451f568e2a7254f4164ba8cd5bd308e838e8f234f4aad0978
+oid sha256:053a15424190df82ce3f5d66704fb1aa6cf2fcf09604c2df06b60ee2f713511b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af9f23e2cf5f2872141c4e257934ce4dce4859a23205b8652f099a03524fe63
+oid sha256:39548ca2e57776c1f074bbabc115a985448e856c2377cb31d60750c5b4eaebcf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.368042945861816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011638395065320493,
+  "best_metric": 10.364083290100098,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.023276790130640986,
   "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": 551.66,
       "eval_steps_per_second": 143.432,
       "step": 25
+    },
+    {
+      "epoch": 0.012103930867933313,
+      "grad_norm": 0.088835708796978,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3711,
+      "step": 26
+    },
+    {
+      "epoch": 0.012569466670546132,
+      "grad_norm": 0.08981330692768097,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3715,
+      "step": 27
+    },
+    {
+      "epoch": 0.013035002473158952,
+      "grad_norm": 0.09010516852140427,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3703,
+      "step": 28
+    },
+    {
+      "epoch": 0.013500538275771771,
+      "grad_norm": 0.09101559221744537,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3702,
+      "step": 29
+    },
+    {
+      "epoch": 0.01396607407838459,
+      "grad_norm": 0.10025133192539215,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.366,
+      "step": 30
+    },
+    {
+      "epoch": 0.01443160988099741,
+      "grad_norm": 0.10704360902309418,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3676,
+      "step": 31
+    },
+    {
+      "epoch": 0.01489714568361023,
+      "grad_norm": 0.1047937422990799,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3676,
+      "step": 32
+    },
+    {
+      "epoch": 0.01536268148622305,
+      "grad_norm": 0.11303725093603134,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3647,
+      "step": 33
+    },
+    {
+      "epoch": 0.01582821728883587,
+      "grad_norm": 0.1116722822189331,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3672,
+      "step": 34
+    },
+    {
+      "epoch": 0.01629375309144869,
+      "grad_norm": 0.11525017023086548,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3665,
+      "step": 35
+    },
+    {
+      "epoch": 0.01675928889406151,
+      "grad_norm": 0.1219276413321495,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.365,
+      "step": 36
+    },
+    {
+      "epoch": 0.01722482469667433,
+      "grad_norm": 0.11378883570432663,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3676,
+      "step": 37
+    },
+    {
+      "epoch": 0.01769036049928715,
+      "grad_norm": 0.10344327986240387,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3703,
+      "step": 38
+    },
+    {
+      "epoch": 0.018155896301899968,
+      "grad_norm": 0.10504771023988724,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3691,
+      "step": 39
+    },
+    {
+      "epoch": 0.018621432104512788,
+      "grad_norm": 0.10149096697568893,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3687,
+      "step": 40
+    },
+    {
+      "epoch": 0.019086967907125607,
+      "grad_norm": 0.10587392747402191,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3699,
+      "step": 41
+    },
+    {
+      "epoch": 0.019552503709738427,
+      "grad_norm": 0.11104900389909744,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3664,
+      "step": 42
+    },
+    {
+      "epoch": 0.020018039512351246,
+      "grad_norm": 0.11142737418413162,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3642,
+      "step": 43
+    },
+    {
+      "epoch": 0.020483575314964066,
+      "grad_norm": 0.11694959551095963,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3663,
+      "step": 44
+    },
+    {
+      "epoch": 0.020949111117576885,
+      "grad_norm": 0.12871791422367096,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3631,
+      "step": 45
+    },
+    {
+      "epoch": 0.021414646920189705,
+      "grad_norm": 0.12332888692617416,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3643,
+      "step": 46
+    },
+    {
+      "epoch": 0.021880182722802524,
+      "grad_norm": 0.1396578997373581,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3664,
+      "step": 47
+    },
+    {
+      "epoch": 0.022345718525415344,
+      "grad_norm": 0.13164079189300537,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3642,
+      "step": 48
+    },
+    {
+      "epoch": 0.022811254328028163,
+      "grad_norm": 0.13550512492656708,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3674,
+      "step": 49
+    },
+    {
+      "epoch": 0.023276790130640986,
+      "grad_norm": 0.16089946031570435,
+      "learning_rate": 1e-05,
+      "loss": 10.3669,
+      "step": 50
+    },
+    {
+      "epoch": 0.023276790130640986,
+      "eval_loss": 10.364083290100098,
+      "eval_runtime": 0.0915,
+      "eval_samples_per_second": 546.639,
+      "eval_steps_per_second": 142.126,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null