Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735d512c4e4f036c6a55c341efe6cb3f6c91300ed90198917af16e68195b338f
+oid sha256:5d87a8ce235d2e05abe6ee40ccb20b160cedc0ad4c245ceb6f232d2d30f4bbe9
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4943a2972509a5f8ed5bf002ea5800b5aad8f055671fcb806be354422c2a91ab
+oid sha256:33c1220790f166a66bcd8cc4deada46b58417ea85731cf238af116e47928b3df
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1f98808edd0998017e8b077f5ccabf5f191aa0c8c93ca000be28184b0f8de3
+oid sha256:b8e1c84184723fe76264aaf061fe4c7f8411d14dec741e81a2a7442f6e519c37
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386d18742273f0f5c6b2448b91fdae1a7c9b51e444b2432e80b0dfdc51e7db00
+oid sha256:7188f1679a60176bf3d9720334aaa1cbab990cf1211f0e5a07d5d38f159bdcf0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd9779fa492eee3707b84ff68ddf87fb9d386cf7b8625cc9fe6cd9db222a3837
+oid sha256:31406283527d0843b5ccfc5290180e63863224e0eb45d22b75713bdc28f77ab5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5f85f3929c847745165635857ea527a9ad11d034f83a150e00e55e64877484
+oid sha256:b83b1629e778b41ad9f50074a1fd9086bd0af6d51f9f970e697d8940145c5984
 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": 0.5917026996612549,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.352112676056338,
+  "best_metric": 0.4431842565536499,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.704225352112676,
   "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": 34.797,
       "eval_steps_per_second": 4.359,
       "step": 25
+    },
+    {
+      "epoch": 0.36619718309859156,
+      "grad_norm": 4.246863842010498,
+      "learning_rate": 5e-05,
+      "loss": 0.631,
+      "step": 26
+    },
+    {
+      "epoch": 0.38028169014084506,
+      "grad_norm": 4.5620503425598145,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8535,
+      "step": 27
+    },
+    {
+      "epoch": 0.39436619718309857,
+      "grad_norm": 2.339592456817627,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.522,
+      "step": 28
+    },
+    {
+      "epoch": 0.4084507042253521,
+      "grad_norm": 2.5191361904144287,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5956,
+      "step": 29
+    },
+    {
+      "epoch": 0.4225352112676056,
+      "grad_norm": 3.5583834648132324,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5882,
+      "step": 30
+    },
+    {
+      "epoch": 0.43661971830985913,
+      "grad_norm": 2.130383014678955,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5102,
+      "step": 31
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 1.9885919094085693,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.525,
+      "step": 32
+    },
+    {
+      "epoch": 0.4647887323943662,
+      "grad_norm": 1.752604365348816,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4971,
+      "step": 33
+    },
+    {
+      "epoch": 0.4788732394366197,
+      "grad_norm": 1.4558221101760864,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.441,
+      "step": 34
+    },
+    {
+      "epoch": 0.49295774647887325,
+      "grad_norm": 0.9350324869155884,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4291,
+      "step": 35
+    },
+    {
+      "epoch": 0.5070422535211268,
+      "grad_norm": 0.8899381160736084,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4157,
+      "step": 36
+    },
+    {
+      "epoch": 0.5211267605633803,
+      "grad_norm": 0.6941632032394409,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3612,
+      "step": 37
+    },
+    {
+      "epoch": 0.5352112676056338,
+      "grad_norm": 1.4537720680236816,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4386,
+      "step": 38
+    },
+    {
+      "epoch": 0.5492957746478874,
+      "grad_norm": 1.35344398021698,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5339,
+      "step": 39
+    },
+    {
+      "epoch": 0.5633802816901409,
+      "grad_norm": 0.8420842289924622,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4795,
+      "step": 40
+    },
+    {
+      "epoch": 0.5774647887323944,
+      "grad_norm": 0.8056310415267944,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.491,
+      "step": 41
+    },
+    {
+      "epoch": 0.5915492957746479,
+      "grad_norm": 0.7623363733291626,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.478,
+      "step": 42
+    },
+    {
+      "epoch": 0.6056338028169014,
+      "grad_norm": 1.0704370737075806,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4453,
+      "step": 43
+    },
+    {
+      "epoch": 0.6197183098591549,
+      "grad_norm": 1.269627332687378,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4703,
+      "step": 44
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "grad_norm": 1.4033896923065186,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4217,
+      "step": 45
+    },
+    {
+      "epoch": 0.647887323943662,
+      "grad_norm": 0.8467299938201904,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.433,
+      "step": 46
+    },
+    {
+      "epoch": 0.6619718309859155,
+      "grad_norm": 0.46602192521095276,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3919,
+      "step": 47
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": 0.6642929315567017,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3828,
+      "step": 48
+    },
+    {
+      "epoch": 0.6901408450704225,
+      "grad_norm": 1.1457411050796509,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3629,
+      "step": 49
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": 1.6525368690490723,
+      "learning_rate": 0.0,
+      "loss": 0.3039,
+      "step": 50
+    },
+    {
+      "epoch": 0.704225352112676,
+      "eval_loss": 0.4431842565536499,
+      "eval_runtime": 13.7585,
+      "eval_samples_per_second": 34.815,
+      "eval_steps_per_second": 4.361,
+      "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": 2.654300032425001e+17,
+  "total_flos": 5.308600064850002e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null