Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7985813bc03bfc81b9feebeea3cbc77d4de7d68948cc294cfa4f2aa68ed76709
+oid sha256:544225313c187e379f63b265ceafe6472c23e47825988ce09e1192ef97d88e4e
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cca849b8a121a6de10233be5f1349dbb7fc4037cc06b2c2fb5dd1bd6a2c6f98
+oid sha256:f05104d834896fd6933b01f572df2823d8ce7c2bcee375bc7de6a7b2a7e0ea85
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46df7acc17174f82fcc162d2cb6a3262ff0b09e6b0894b0e2339ae9e0b37c8f6
+oid sha256:c9593dba680efd96f842e4c23f4a739270b3da12bcfa59ad2c17b2854bbcc451
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cd552c0f76c7c1efbf51effe22b102ffe9216a02fdd643e08efeb5949d562a
+oid sha256:ed1cd7302869f38ccb9eb8bf85680d2bc823b9c8ca05c16060a1216df8e51140
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5180f4746e0c14fb50458ccff5f1386aa0344dde9d72f29fe546e9bde14944
+oid sha256:6bfd57743e233a17dbe09750dda148134913a811bcdbdff11639740afb6d6fd2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db88ccd5c49682064d797a19b1bd7f6642b684976bc75954b72ed6034614a87
+oid sha256:3cb68ca83535203c5c23a0c0628b371f5cbf0faa01325061f2956319720049c8
 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": 0.8497164845466614,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.35810205908683973,
+  "best_metric": 0.8260481357574463,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7162041181736795,
   "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": 17.883,
       "eval_steps_per_second": 2.245,
       "step": 25
+    },
+    {
+      "epoch": 0.37242614145031333,
+      "grad_norm": 0.06810956448316574,
+      "learning_rate": 5e-05,
+      "loss": 0.7427,
+      "step": 26
+    },
+    {
+      "epoch": 0.38675022381378693,
+      "grad_norm": 0.07532549649477005,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.844,
+      "step": 27
+    },
+    {
+      "epoch": 0.40107430617726053,
+      "grad_norm": 0.08530668914318085,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7301,
+      "step": 28
+    },
+    {
+      "epoch": 0.41539838854073413,
+      "grad_norm": 0.09383714199066162,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.746,
+      "step": 29
+    },
+    {
+      "epoch": 0.4297224709042077,
+      "grad_norm": 0.10356415808200836,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7789,
+      "step": 30
+    },
+    {
+      "epoch": 0.4440465532676813,
+      "grad_norm": 0.137028768658638,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7823,
+      "step": 31
+    },
+    {
+      "epoch": 0.4583706356311549,
+      "grad_norm": 0.1444852352142334,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8793,
+      "step": 32
+    },
+    {
+      "epoch": 0.4726947179946285,
+      "grad_norm": 0.14780306816101074,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8477,
+      "step": 33
+    },
+    {
+      "epoch": 0.4870188003581021,
+      "grad_norm": 0.16937947273254395,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8519,
+      "step": 34
+    },
+    {
+      "epoch": 0.5013428827215757,
+      "grad_norm": 0.16218450665473938,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8925,
+      "step": 35
+    },
+    {
+      "epoch": 0.5156669650850493,
+      "grad_norm": 0.1833808720111847,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8988,
+      "step": 36
+    },
+    {
+      "epoch": 0.5299910474485229,
+      "grad_norm": 0.22939519584178925,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9816,
+      "step": 37
+    },
+    {
+      "epoch": 0.5443151298119964,
+      "grad_norm": 0.08518178761005402,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8183,
+      "step": 38
+    },
+    {
+      "epoch": 0.55863921217547,
+      "grad_norm": 0.07068660110235214,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8179,
+      "step": 39
+    },
+    {
+      "epoch": 0.5729632945389436,
+      "grad_norm": 0.08099059760570526,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8127,
+      "step": 40
+    },
+    {
+      "epoch": 0.5872873769024172,
+      "grad_norm": 0.08545270562171936,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7382,
+      "step": 41
+    },
+    {
+      "epoch": 0.6016114592658908,
+      "grad_norm": 0.09283125400543213,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7788,
+      "step": 42
+    },
+    {
+      "epoch": 0.6159355416293644,
+      "grad_norm": 0.10766535252332687,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7369,
+      "step": 43
+    },
+    {
+      "epoch": 0.630259623992838,
+      "grad_norm": 0.13231581449508667,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.788,
+      "step": 44
+    },
+    {
+      "epoch": 0.6445837063563116,
+      "grad_norm": 0.1386619359254837,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7723,
+      "step": 45
+    },
+    {
+      "epoch": 0.6589077887197852,
+      "grad_norm": 0.14434082806110382,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7922,
+      "step": 46
+    },
+    {
+      "epoch": 0.6732318710832588,
+      "grad_norm": 0.16179312765598297,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8169,
+      "step": 47
+    },
+    {
+      "epoch": 0.6875559534467324,
+      "grad_norm": 0.1684214323759079,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8452,
+      "step": 48
+    },
+    {
+      "epoch": 0.7018800358102059,
+      "grad_norm": 0.19974979758262634,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9585,
+      "step": 49
+    },
+    {
+      "epoch": 0.7162041181736795,
+      "grad_norm": 0.3124803304672241,
+      "learning_rate": 0.0,
+      "loss": 1.142,
+      "step": 50
+    },
+    {
+      "epoch": 0.7162041181736795,
+      "eval_loss": 0.8260481357574463,
+      "eval_runtime": 26.2734,
+      "eval_samples_per_second": 17.889,
+      "eval_steps_per_second": 2.246,
+      "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": 5.5835639355644314e+17,
+  "total_flos": 1.1160183123759596e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null