Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d623d47fd691f224a1c82da7eefd5865f67ca003430791f855e21d5f86af3ff
+oid sha256:22cb2cceec32ee2ba293dd42a547a78f997320159d871f1c660aecf2a39d7dd7
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a45b6d25dfb5e846d077ea43e64dc2c6ea3d2352e3bbadf46f9469364331e5de
+oid sha256:5f7d6910256f196d7291786c57881bf7e8a1bd49ff9cdb0ea52a10f622e2111e
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734d90d9fcf719d29e386b3a72faf92aade43626b780a27a0bfc7a6468e057d1
+oid sha256:a97ec4e17d6b8494dfd8c98045ff7dee32c305624b250661ee43411674dfc9b8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80de0a5df355a29d45402432821c79e74c41e4c28c303e156bfea9478eb85a4e
+oid sha256:111395e38ae04afd98f9425f5d08875c7030451a29a8b543d784db44002d07bb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d226d22e52daf92b6179669adb758e41552b61fd7d5a3f2370e1c6e5fed615
+oid sha256:08fbc5e65faa3fab6e92bd186b7dfc5e9d469e14e96ebe0a7b912518bdbb6294
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1510936bc594c76a3c6e4e63b464875e90e9e0818db835902dabb29b654653d3
+oid sha256:07f3853056075aeeb5076bb3296950bf756b045ce56b7f7c6b35e195fa20c787
 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": 11.940805435180664,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11464603038119806,
+  "best_metric": 11.939474105834961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2292920607623961,
   "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": 471.834,
       "eval_steps_per_second": 59.059,
       "step": 25
+    },
+    {
+      "epoch": 0.11923187159644598,
+      "grad_norm": 0.05349224433302879,
+      "learning_rate": 5e-05,
+      "loss": 11.9391,
+      "step": 26
+    },
+    {
+      "epoch": 0.12381771281169389,
+      "grad_norm": 0.050973717123270035,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9392,
+      "step": 27
+    },
+    {
+      "epoch": 0.1284035540269418,
+      "grad_norm": 0.050512637943029404,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9378,
+      "step": 28
+    },
+    {
+      "epoch": 0.13298939524218975,
+      "grad_norm": 0.0520334467291832,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.941,
+      "step": 29
+    },
+    {
+      "epoch": 0.13757523645743766,
+      "grad_norm": 0.055656593292951584,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9406,
+      "step": 30
+    },
+    {
+      "epoch": 0.14216107767268557,
+      "grad_norm": 0.053649820387363434,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9397,
+      "step": 31
+    },
+    {
+      "epoch": 0.1467469188879335,
+      "grad_norm": 0.05413060635328293,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9393,
+      "step": 32
+    },
+    {
+      "epoch": 0.15133276010318142,
+      "grad_norm": 0.0558125339448452,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9418,
+      "step": 33
+    },
+    {
+      "epoch": 0.15591860131842936,
+      "grad_norm": 0.052829060703516006,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9406,
+      "step": 34
+    },
+    {
+      "epoch": 0.16050444253367727,
+      "grad_norm": 0.060385338962078094,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9413,
+      "step": 35
+    },
+    {
+      "epoch": 0.1650902837489252,
+      "grad_norm": 0.04723364859819412,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.942,
+      "step": 36
+    },
+    {
+      "epoch": 0.16967612496417311,
+      "grad_norm": 0.054764941334724426,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9409,
+      "step": 37
+    },
+    {
+      "epoch": 0.17426196617942102,
+      "grad_norm": 0.05203568935394287,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9395,
+      "step": 38
+    },
+    {
+      "epoch": 0.17884780739466896,
+      "grad_norm": 0.0577789843082428,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9406,
+      "step": 39
+    },
+    {
+      "epoch": 0.18343364860991687,
+      "grad_norm": 0.05892513692378998,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9378,
+      "step": 40
+    },
+    {
+      "epoch": 0.1880194898251648,
+      "grad_norm": 0.057550907135009766,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9383,
+      "step": 41
+    },
+    {
+      "epoch": 0.19260533104041272,
+      "grad_norm": 0.06069960817694664,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9408,
+      "step": 42
+    },
+    {
+      "epoch": 0.19719117225566066,
+      "grad_norm": 0.061215341091156006,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9385,
+      "step": 43
+    },
+    {
+      "epoch": 0.20177701347090857,
+      "grad_norm": 0.06457344442605972,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9388,
+      "step": 44
+    },
+    {
+      "epoch": 0.2063628546861565,
+      "grad_norm": 0.05859246104955673,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9378,
+      "step": 45
+    },
+    {
+      "epoch": 0.21094869590140441,
+      "grad_norm": 0.05629947409033775,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9402,
+      "step": 46
+    },
+    {
+      "epoch": 0.21553453711665232,
+      "grad_norm": 0.053209468722343445,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9402,
+      "step": 47
+    },
+    {
+      "epoch": 0.22012037833190026,
+      "grad_norm": 0.06205746904015541,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9398,
+      "step": 48
+    },
+    {
+      "epoch": 0.22470621954714817,
+      "grad_norm": 0.0625690147280693,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9395,
+      "step": 49
+    },
+    {
+      "epoch": 0.2292920607623961,
+      "grad_norm": 0.054081086069345474,
+      "learning_rate": 0.0,
+      "loss": 11.9422,
+      "step": 50
+    },
+    {
+      "epoch": 0.2292920607623961,
+      "eval_loss": 11.939474105834961,
+      "eval_runtime": 3.1182,
+      "eval_samples_per_second": 471.422,
+      "eval_steps_per_second": 59.008,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null