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:c1227bb2040dd3224b047d84e9fbce0f8d851046f6ebab5a9b8ee7e86427e4a5
+oid sha256:b193d1346f639cd860104f4f44c2294acd3c65a76bfe71e1043429c4de081962
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8005344986fa90bdc12f83bc61db5ce9ac87efbc3847387261d031cc827d31a5
+oid sha256:d5944d7ba4dfc1cefbb6830ebceb8747c7c0e92248560b709fa79c63ddf7f6b6
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b020059346fca6c95ecc16fed1be477ac4453684f922ceafad1679cbc4b7d3
+oid sha256:5a8611dc1cdfdeded65043babb31680e93d5b1cb17f656015bba69138a562e21
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b40ca13566cce19a3cd05985057a97851a61c48c19977e8b50bc9d627b2c368
+oid sha256:e1abab4857972b1d87883cf5e407dba1e927ef6b935010d4b4f769df5e8627d0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0621e1416501df904d791be978ee1b90ad186937434a1d59ec742192e877b557
+oid sha256:40983249445e9034ffde0a836c53e7c0b56e1fe83e3c02941c8cfb37db59891c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97be44a15368c80021ffa5c8a4895d011f63d575c0c971501a8b127cc400b26e
+oid sha256:1077347fe2505ff97c2614dca1d786653d991fc75d35e785c308ba63ad6f827f
 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": 1.3843603134155273,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22727272727272727,
+  "best_metric": 1.328393816947937,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45454545454545453,
   "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": 31.172,
       "eval_steps_per_second": 3.912,
       "step": 25
+    },
+    {
+      "epoch": 0.23636363636363636,
+      "grad_norm": 0.36956995725631714,
+      "learning_rate": 5e-05,
+      "loss": 1.5298,
+      "step": 26
+    },
+    {
+      "epoch": 0.24545454545454545,
+      "grad_norm": 0.49253299832344055,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4411,
+      "step": 27
+    },
+    {
+      "epoch": 0.2545454545454545,
+      "grad_norm": 0.5202022194862366,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3987,
+      "step": 28
+    },
+    {
+      "epoch": 0.2636363636363636,
+      "grad_norm": 0.5346823334693909,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4693,
+      "step": 29
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.5093651413917542,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4682,
+      "step": 30
+    },
+    {
+      "epoch": 0.2818181818181818,
+      "grad_norm": 0.7494578957557678,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4346,
+      "step": 31
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.41236063838005066,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5035,
+      "step": 32
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.569702684879303,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3644,
+      "step": 33
+    },
+    {
+      "epoch": 0.3090909090909091,
+      "grad_norm": 0.6248189210891724,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4663,
+      "step": 34
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 0.7485700845718384,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3821,
+      "step": 35
+    },
+    {
+      "epoch": 0.32727272727272727,
+      "grad_norm": 1.061784029006958,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2502,
+      "step": 36
+    },
+    {
+      "epoch": 0.33636363636363636,
+      "grad_norm": 1.3697577714920044,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2969,
+      "step": 37
+    },
+    {
+      "epoch": 0.34545454545454546,
+      "grad_norm": 0.2654924690723419,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0297,
+      "step": 38
+    },
+    {
+      "epoch": 0.35454545454545455,
+      "grad_norm": 0.20454204082489014,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.341,
+      "step": 39
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.24198082089424133,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3627,
+      "step": 40
+    },
+    {
+      "epoch": 0.37272727272727274,
+      "grad_norm": 0.23670072853565216,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3985,
+      "step": 41
+    },
+    {
+      "epoch": 0.38181818181818183,
+      "grad_norm": 0.2668602466583252,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4415,
+      "step": 42
+    },
+    {
+      "epoch": 0.39090909090909093,
+      "grad_norm": 0.2617162764072418,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.4121,
+      "step": 43
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2912660241127014,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4957,
+      "step": 44
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 0.31733399629592896,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3998,
+      "step": 45
+    },
+    {
+      "epoch": 0.41818181818181815,
+      "grad_norm": 0.3562355935573578,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3615,
+      "step": 46
+    },
+    {
+      "epoch": 0.42727272727272725,
+      "grad_norm": 0.3990439474582672,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3774,
+      "step": 47
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.4939119517803192,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4047,
+      "step": 48
+    },
+    {
+      "epoch": 0.44545454545454544,
+      "grad_norm": 0.6996358036994934,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2233,
+      "step": 49
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.5292341709136963,
+      "learning_rate": 0.0,
+      "loss": 1.4825,
+      "step": 50
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "eval_loss": 1.328393816947937,
+      "eval_runtime": 52.3704,
+      "eval_samples_per_second": 14.149,
+      "eval_steps_per_second": 1.776,
+      "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": 3.008287135267553e+17,
+  "total_flos": 6.01284422028755e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null