Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00322f61234af91c3b3ab4ab3e26cb01cc4a9d6e6ba24702a9243f4847cb9352
+oid sha256:48173c29d0a53283a5158e2c6ab9797bbafebc851d778afbcb059be419f05f2b
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47daf541aed681fbccbbb2851123baec6f865a6a074c56826e1355325f85069
+oid sha256:3861dea34353a92f4697d99937718b7610b9f966fb41c666c48b2577eb4d4917
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3faf9f4b4a4d78c30cfbaa7c0c517b8982e110b7205e35e178baf39a356a69a0
+oid sha256:46addfbda18ff9b9d337346f94fecc408cd80c4f43db25ec1e2a3edb89fa2812
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2b9e983e3906808ceb50210a847e65e5fa417673c221a5c3d4f9dbb542de03
+oid sha256:13db002787eac5a3b1c72fd53ac7834264c174ccf89cfc8a2c85e4a987ea8b10
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2680fd68b116f98dd64cca2483e1acbd2ff42b76b9add6faf218df0b2287b39c
+oid sha256:08781b30a125ec9b2724f5e03ab0bc7c81ae341b2bbd45f22c85b375ddc24121
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3663cfda152f06d59e25a793ca1f67f459dc8e423ecdd519cbda51bd82ee155
+oid sha256:ab9f9902a18b8b1bd915728ddbcce202e1e9dcab3162ea192d8d302398b4addc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
+oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6996614336967468,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.39408866995073893,
+  "best_metric": 0.5248658061027527,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7881773399014779,
   "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": 71.253,
       "eval_steps_per_second": 18.526,
       "step": 25
+    },
+    {
+      "epoch": 0.4098522167487685,
+      "grad_norm": 25.538625717163086,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 0.8154,
+      "step": 26
+    },
+    {
+      "epoch": 0.42561576354679803,
+      "grad_norm": 25.62391471862793,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 0.8749,
+      "step": 27
+    },
+    {
+      "epoch": 0.4413793103448276,
+      "grad_norm": 21.496841430664062,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 0.7513,
+      "step": 28
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 6.727818489074707,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.5105,
+      "step": 29
+    },
+    {
+      "epoch": 0.4729064039408867,
+      "grad_norm": 10.45919418334961,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.5997,
+      "step": 30
+    },
+    {
+      "epoch": 0.4886699507389163,
+      "grad_norm": 12.25587272644043,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.665,
+      "step": 31
+    },
+    {
+      "epoch": 0.5044334975369458,
+      "grad_norm": 12.651376724243164,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.6593,
+      "step": 32
+    },
+    {
+      "epoch": 0.5201970443349754,
+      "grad_norm": 6.981288909912109,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 0.5065,
+      "step": 33
+    },
+    {
+      "epoch": 0.5359605911330049,
+      "grad_norm": 11.137550354003906,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.5894,
+      "step": 34
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 14.628920555114746,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.6922,
+      "step": 35
+    },
+    {
+      "epoch": 0.5674876847290641,
+      "grad_norm": 9.037491798400879,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.5246,
+      "step": 36
+    },
+    {
+      "epoch": 0.5832512315270936,
+      "grad_norm": 7.97292423248291,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.4837,
+      "step": 37
+    },
+    {
+      "epoch": 0.5990147783251232,
+      "grad_norm": 2.1145670413970947,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.5613,
+      "step": 38
+    },
+    {
+      "epoch": 0.6147783251231527,
+      "grad_norm": 9.712841033935547,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.6461,
+      "step": 39
+    },
+    {
+      "epoch": 0.6305418719211823,
+      "grad_norm": 15.202656745910645,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.731,
+      "step": 40
+    },
+    {
+      "epoch": 0.6463054187192119,
+      "grad_norm": 10.122875213623047,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.6261,
+      "step": 41
+    },
+    {
+      "epoch": 0.6620689655172414,
+      "grad_norm": 5.730849742889404,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.5371,
+      "step": 42
+    },
+    {
+      "epoch": 0.677832512315271,
+      "grad_norm": 1.8030896186828613,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.5414,
+      "step": 43
+    },
+    {
+      "epoch": 0.6935960591133005,
+      "grad_norm": 4.4432692527771,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.5234,
+      "step": 44
+    },
+    {
+      "epoch": 0.7093596059113301,
+      "grad_norm": 4.838330268859863,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.5282,
+      "step": 45
+    },
+    {
+      "epoch": 0.7251231527093596,
+      "grad_norm": 4.681862831115723,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.5099,
+      "step": 46
+    },
+    {
+      "epoch": 0.7408866995073892,
+      "grad_norm": 1.7629047632217407,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.5132,
+      "step": 47
+    },
+    {
+      "epoch": 0.7566502463054188,
+      "grad_norm": 6.828063011169434,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.5072,
+      "step": 48
+    },
+    {
+      "epoch": 0.7724137931034483,
+      "grad_norm": 12.11754035949707,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.5966,
+      "step": 49
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 11.806983947753906,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.5767,
+      "step": 50
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "eval_loss": 0.5248658061027527,
+      "eval_runtime": 0.7022,
+      "eval_samples_per_second": 71.202,
+      "eval_steps_per_second": 18.513,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null