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:c61a703063bdea486693851863e68745b7a939572411f162d7fb1d83d090fa13
+oid sha256:6628c07e632a154792d1c63a45e296337c556fd1251face0659bd3d5b1367340
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9926a337f66cc81f24896109f30b46a70004608b82acded2d4bd3335ce0a2b56
+oid sha256:e786d55905a609db6ab2a917d3e97a8e714ff52be0498de565aa710db0f21e29
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d923d48fb2fcf7040f8d10e52588aeafd6b65923876da200f48f651f63861d5
+oid sha256:1dbfa90b482bcb42de2c7728c69c0bb89c9b1ab5fc08226ee2bc83b7bac920e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a813c60367f9af34a299bf9f037615ff881a67f122209ab11739dff92467a086
+oid sha256:1ef2ee7569caf6cb02f8e3494255a9b17c28a36f7c9809abc200f5c1642324cf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ffa58affd3f0c1ee4b55aefa798065720c31fc6448d8413372058f630bcd97
+oid sha256:49b364b4e56642b48925422577608ebd5780d833f9c2ded89a47f3a8879ae507
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244d079499a0bec8f1cc7a002eb1c4f616bb41828409d1d6f28144fcec2b4233
+oid sha256:b70c80efa090d66b2916214b40cef616bd3d97d6dd69227643a007f1d3350724
 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": 0.2869703769683838,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.24721878862793573,
+  "best_metric": 0.22514864802360535,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.49443757725587145,
   "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": 87.07,
       "eval_steps_per_second": 10.996,
       "step": 25
+    },
+    {
+      "epoch": 0.25710754017305315,
+      "grad_norm": 0.2917296588420868,
+      "learning_rate": 5e-05,
+      "loss": 0.1985,
+      "step": 26
+    },
+    {
+      "epoch": 0.2669962917181706,
+      "grad_norm": 0.33820563554763794,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.21,
+      "step": 27
+    },
+    {
+      "epoch": 0.276885043263288,
+      "grad_norm": 0.3485124707221985,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2332,
+      "step": 28
+    },
+    {
+      "epoch": 0.2867737948084054,
+      "grad_norm": 0.3025939166545868,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2189,
+      "step": 29
+    },
+    {
+      "epoch": 0.29666254635352285,
+      "grad_norm": 0.31494253873825073,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2142,
+      "step": 30
+    },
+    {
+      "epoch": 0.3065512978986403,
+      "grad_norm": 0.4657946527004242,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2213,
+      "step": 31
+    },
+    {
+      "epoch": 0.3164400494437577,
+      "grad_norm": 0.3799411356449127,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2193,
+      "step": 32
+    },
+    {
+      "epoch": 0.3263288009888752,
+      "grad_norm": 0.2840307950973511,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2112,
+      "step": 33
+    },
+    {
+      "epoch": 0.3362175525339926,
+      "grad_norm": 0.35816898941993713,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2486,
+      "step": 34
+    },
+    {
+      "epoch": 0.34610630407911,
+      "grad_norm": 0.35439935326576233,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2388,
+      "step": 35
+    },
+    {
+      "epoch": 0.35599505562422745,
+      "grad_norm": 0.4249046742916107,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2357,
+      "step": 36
+    },
+    {
+      "epoch": 0.3658838071693449,
+      "grad_norm": 0.4100884199142456,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.284,
+      "step": 37
+    },
+    {
+      "epoch": 0.3757725587144623,
+      "grad_norm": 0.4879622161388397,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.298,
+      "step": 38
+    },
+    {
+      "epoch": 0.3856613102595797,
+      "grad_norm": 0.3166544735431671,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1693,
+      "step": 39
+    },
+    {
+      "epoch": 0.39555006180469715,
+      "grad_norm": 0.3027257025241852,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.187,
+      "step": 40
+    },
+    {
+      "epoch": 0.4054388133498146,
+      "grad_norm": 0.2633449137210846,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1846,
+      "step": 41
+    },
+    {
+      "epoch": 0.415327564894932,
+      "grad_norm": 0.2582716643810272,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.195,
+      "step": 42
+    },
+    {
+      "epoch": 0.4252163164400494,
+      "grad_norm": 0.24600811302661896,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.173,
+      "step": 43
+    },
+    {
+      "epoch": 0.43510506798516685,
+      "grad_norm": 0.29672151803970337,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.197,
+      "step": 44
+    },
+    {
+      "epoch": 0.44499381953028433,
+      "grad_norm": 0.3242957890033722,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1931,
+      "step": 45
+    },
+    {
+      "epoch": 0.45488257107540175,
+      "grad_norm": 0.3718074858188629,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2209,
+      "step": 46
+    },
+    {
+      "epoch": 0.4647713226205192,
+      "grad_norm": 0.3563547134399414,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2031,
+      "step": 47
+    },
+    {
+      "epoch": 0.4746600741656366,
+      "grad_norm": 0.360695481300354,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2244,
+      "step": 48
+    },
+    {
+      "epoch": 0.484548825710754,
+      "grad_norm": 0.3732745349407196,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2263,
+      "step": 49
+    },
+    {
+      "epoch": 0.49443757725587145,
+      "grad_norm": 1.110573649406433,
+      "learning_rate": 0.0,
+      "loss": 0.4603,
+      "step": 50
+    },
+    {
+      "epoch": 0.49443757725587145,
+      "eval_loss": 0.22514864802360535,
+      "eval_runtime": 7.7671,
+      "eval_samples_per_second": 87.678,
+      "eval_steps_per_second": 11.072,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null