Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820b49159e8c1daec1ba173f61ea510a95b372c56515462a6ae5e114fb06ba25
+oid sha256:f16f209390021dff27afc35bda21154f6a7e7d3f6cbdf197332fee69575b9fe7
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c5047cf61285cb1f44422562c8dbdf3cc560682adb2e230faac26039efa1fa1
+oid sha256:84991100c8eb7edd84e804994315bed006c7b0884cf6f35e6d29097e34e0d3fe
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cdacccd04fd26d1137e792bc18a05b635c2e4ceaf793dddf94c9141dad3ff3
+oid sha256:221198369c1566da1159ec8a2bc190ba62dc34c69d72a6c6090338fc5850d857
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359f5c7ab44f94f3e5bc77d4e7bbd9494903e4e5d67b9a12d4b7888489305a30
+oid sha256:7ce9b27abc028148f4e046db0fdb3c75524356023eefb9d160eba70fc43adf53
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5873a7efc7bce037fe32cfc3edcf74d4d700fdcb2c37a3d90a9a62c6e5f2e6
+oid sha256:a23c21358137a6b2d37019c9a155b20098ad36930434459a67ad2e59b5e2d7de
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a90229a75e37d4fa6a22bbdfbc72b8eb14aef898083e1ae1d02ea2de2180cef4
+oid sha256:ef8df6fce005b965c15f581470abbf89b215a5a74997a7b4f70a7240bbe3974a
 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": 1.6629419405944645e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09282896263634254,
+  "best_metric": 5.9604641222676946e-08,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.18565792527268507,
   "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": 24.603,
       "eval_steps_per_second": 3.077,
       "step": 25
+    },
+    {
+      "epoch": 0.09654212114179624,
+      "grad_norm": 0.004678704310208559,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.10025527964724994,
+      "grad_norm": 0.009269794449210167,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.10396843815270364,
+      "grad_norm": 0.0021353906486183405,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.10768159665815734,
+      "grad_norm": 0.0019365429179742932,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.11139475516361105,
+      "grad_norm": 0.001062785042449832,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 0.007692957296967506,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.11882107217451846,
+      "grad_norm": 0.0004157963558100164,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.12253423067997216,
+      "grad_norm": 0.0002727754763327539,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.12624738918542586,
+      "grad_norm": 0.00023943185806274414,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.12996054769087956,
+      "grad_norm": 8.647178765386343e-05,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.13367370619633326,
+      "grad_norm": 0.00021716480841860175,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.13738686470178696,
+      "grad_norm": 0.00011382108641555533,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.14110002320724066,
+      "grad_norm": 7.642527634743601e-05,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.14481318171269436,
+      "grad_norm": 7.74165746406652e-05,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.14852634021814806,
+      "grad_norm": 3.6338700738269836e-05,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.15223949872360176,
+      "grad_norm": 3.927394936908968e-05,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.15595265722905546,
+      "grad_norm": 0.00011530683696037158,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.15966581573450916,
+      "grad_norm": 3.756599107873626e-05,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.16337897423996287,
+      "grad_norm": 9.324763232143596e-05,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.16709213274541657,
+      "grad_norm": 4.730185173684731e-05,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.17080529125087027,
+      "grad_norm": 6.137853051768616e-05,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.17451844975632397,
+      "grad_norm": 2.7098336431663483e-05,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.17823160826177767,
+      "grad_norm": 7.346120401052758e-05,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.18194476676723137,
+      "grad_norm": 2.8820741135859862e-05,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.18565792527268507,
+      "grad_norm": 4.6881395974196494e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.18565792527268507,
+      "eval_loss": 5.9604641222676946e-08,
+      "eval_runtime": 73.7395,
+      "eval_samples_per_second": 24.614,
+      "eval_steps_per_second": 3.078,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null