Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df2ea981d81ee8cdbd90fd50290a5b2ec4d3c33cccc6d1b6ba2063787376211
+oid sha256:581dcfed72b6cabc038681dea4147192bcb2d00de05170b92d252c70afcff1ff
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf91235f5159ad35faebe8283a77d814dccc5ebbfea38a1cc2b8d868af0373d4
+oid sha256:f97b83ff88315676c58d64129c3f7156391aad3ec8c29fd8d210bd0025f57f0d
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84276e3ce2274c6506f2a2a6dbd452e9e9ea0d87d136f91fcbd64c21c32d5b97
+oid sha256:c9c85348a4c11fc4b28eda0f9c8e4af71b6bf5108092464ea981d90b6fd77f9a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15853d7cfce5f159327bf509f76182ce250f23ddd7235a62f90479968cdc93b1
+oid sha256:64c9b6e55279ff42771c7f8b92ba56c3cd578f68aa6b0f97681bc59235b0002e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668c49fe2b1e2d4d44367fcafb9f88dc599c1841758373c8cccf13913166cf98
+oid sha256:c44d6499f10ead3d7059e7c512ac45b56c9af4b24cc9c116e3411fdfa25b32c2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c2cb3e8855cb597256e03001ea8f797fd6f10884b0ad6d09008ffe5edb4b13
+oid sha256:8f82bb2a6e23dc8db7f89aee8daab97c847939f6c65ca10d83b63713dad6bf80
 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": 2.690415859222412,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10319917440660474,
+  "best_metric": 2.642500877380371,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.20639834881320948,
   "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": 17.477,
       "eval_steps_per_second": 2.185,
       "step": 25
+    },
+    {
+      "epoch": 0.10732714138286893,
+      "grad_norm": 22.026641845703125,
+      "learning_rate": 5e-05,
+      "loss": 2.5545,
+      "step": 26
+    },
+    {
+      "epoch": 0.11145510835913312,
+      "grad_norm": 11.724824905395508,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.598,
+      "step": 27
+    },
+    {
+      "epoch": 0.11558307533539731,
+      "grad_norm": 19.44083595275879,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.5938,
+      "step": 28
+    },
+    {
+      "epoch": 0.1197110423116615,
+      "grad_norm": 15.541399002075195,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.607,
+      "step": 29
+    },
+    {
+      "epoch": 0.1238390092879257,
+      "grad_norm": 8.880937576293945,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.6641,
+      "step": 30
+    },
+    {
+      "epoch": 0.12796697626418987,
+      "grad_norm": 16.82801055908203,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.6351,
+      "step": 31
+    },
+    {
+      "epoch": 0.13209494324045407,
+      "grad_norm": 11.607008934020996,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.6259,
+      "step": 32
+    },
+    {
+      "epoch": 0.13622291021671826,
+      "grad_norm": 10.484081268310547,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.6745,
+      "step": 33
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 15.66185188293457,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.6962,
+      "step": 34
+    },
+    {
+      "epoch": 0.14447884416924664,
+      "grad_norm": 8.911550521850586,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.6688,
+      "step": 35
+    },
+    {
+      "epoch": 0.14860681114551083,
+      "grad_norm": 9.620184898376465,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.6953,
+      "step": 36
+    },
+    {
+      "epoch": 0.15273477812177502,
+      "grad_norm": 19.419748306274414,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.7416,
+      "step": 37
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 21.67677116394043,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6487,
+      "step": 38
+    },
+    {
+      "epoch": 0.1609907120743034,
+      "grad_norm": 9.815399169921875,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.5291,
+      "step": 39
+    },
+    {
+      "epoch": 0.1651186790505676,
+      "grad_norm": 10.651171684265137,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.5695,
+      "step": 40
+    },
+    {
+      "epoch": 0.1692466460268318,
+      "grad_norm": 8.446441650390625,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.5696,
+      "step": 41
+    },
+    {
+      "epoch": 0.17337461300309598,
+      "grad_norm": 7.351607322692871,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.6273,
+      "step": 42
+    },
+    {
+      "epoch": 0.17750257997936017,
+      "grad_norm": 8.186249732971191,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.634,
+      "step": 43
+    },
+    {
+      "epoch": 0.18163054695562436,
+      "grad_norm": 7.671238899230957,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.614,
+      "step": 44
+    },
+    {
+      "epoch": 0.18575851393188855,
+      "grad_norm": 7.866890907287598,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.6279,
+      "step": 45
+    },
+    {
+      "epoch": 0.18988648090815274,
+      "grad_norm": 9.127365112304688,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.7079,
+      "step": 46
+    },
+    {
+      "epoch": 0.19401444788441694,
+      "grad_norm": 8.691065788269043,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.6868,
+      "step": 47
+    },
+    {
+      "epoch": 0.19814241486068113,
+      "grad_norm": 10.210210800170898,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.6897,
+      "step": 48
+    },
+    {
+      "epoch": 0.20227038183694532,
+      "grad_norm": 9.142345428466797,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.7448,
+      "step": 49
+    },
+    {
+      "epoch": 0.20639834881320948,
+      "grad_norm": 19.186899185180664,
+      "learning_rate": 0.0,
+      "loss": 2.7931,
+      "step": 50
+    },
+    {
+      "epoch": 0.20639834881320948,
+      "eval_loss": 2.642500877380371,
+      "eval_runtime": 93.387,
+      "eval_samples_per_second": 17.476,
+      "eval_steps_per_second": 2.184,
+      "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": 4.85137494048768e+16,
+  "total_flos": 9.70274988097536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null