Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9950c03c675f1e80cb545a1c91b69bd24e4916534ffae9c56809afcadb1bb059
+oid sha256:c151e1cd47063632bd853405caeb31d325bdcc1c51a0fdfd4da8bf110a3ad901
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:246495ff63a2b2d2b1f84299849b5eb89bba613530314a91186fcec89a03b289
+oid sha256:7cb47e7cfbdc25421ff0b7bbf5e96fdffd059ff1ce2547708bad1076f2315667
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d368b173a563ef2a32343f3b488e3ef2f2c0b0c3fd7a542b6aad407892303399
+oid sha256:f652ced67260d8953f4193a546557acf7f7a4c99cd4ed942bca6d1d94039e145
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8945a32e00ffb141b397815b4443fbffb9257778a7f8fc33214f8923969aaabf
+oid sha256:31f6e5d8fc455915ca42f09d8b0672300c0d57cab1320287ec1afba874eee715
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d6edbe16018cfca0c706509cba24f4fe3f7ec65cbc2c5cf2d247554e299965
+oid sha256:24a833c90a427334acef173426c48342e21d54f41f0674e85bf2f8ac44934631
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac9fbedfe4618ffaa35ab46a7ab143bed8180754191adfca26574793765a2d3
+oid sha256:59d559dce9fbd272cb48484e0554cd033c360832de93ee3ca9a1cf026f9a2169
 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": 4.320591449737549,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2290950744558992,
+  "best_metric": 2.710082769393921,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4581901489117984,
   "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": 36.467,
       "eval_steps_per_second": 4.565,
       "step": 25
+    },
+    {
+      "epoch": 0.23825887743413515,
+      "grad_norm": 14.602640151977539,
+      "learning_rate": 5e-05,
+      "loss": 4.5919,
+      "step": 26
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 16.663705825805664,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 5.5504,
+      "step": 27
+    },
+    {
+      "epoch": 0.2565864833906071,
+      "grad_norm": 14.454683303833008,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 5.3415,
+      "step": 28
+    },
+    {
+      "epoch": 0.26575028636884307,
+      "grad_norm": 9.233696937561035,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 4.6802,
+      "step": 29
+    },
+    {
+      "epoch": 0.27491408934707906,
+      "grad_norm": 7.224252700805664,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.4319,
+      "step": 30
+    },
+    {
+      "epoch": 0.284077892325315,
+      "grad_norm": 7.030068874359131,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.4814,
+      "step": 31
+    },
+    {
+      "epoch": 0.293241695303551,
+      "grad_norm": 6.364577293395996,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4798,
+      "step": 32
+    },
+    {
+      "epoch": 0.3024054982817869,
+      "grad_norm": 6.61119270324707,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.2206,
+      "step": 33
+    },
+    {
+      "epoch": 0.3115693012600229,
+      "grad_norm": 7.3994035720825195,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.4515,
+      "step": 34
+    },
+    {
+      "epoch": 0.3207331042382589,
+      "grad_norm": 12.4517240524292,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.4029,
+      "step": 35
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 10.87969970703125,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.2815,
+      "step": 36
+    },
+    {
+      "epoch": 0.33906071019473083,
+      "grad_norm": 11.173131942749023,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.9704,
+      "step": 37
+    },
+    {
+      "epoch": 0.34822451317296677,
+      "grad_norm": 9.83188247680664,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.1668,
+      "step": 38
+    },
+    {
+      "epoch": 0.35738831615120276,
+      "grad_norm": 10.8068265914917,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.6899,
+      "step": 39
+    },
+    {
+      "epoch": 0.3665521191294387,
+      "grad_norm": 10.032576560974121,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.7501,
+      "step": 40
+    },
+    {
+      "epoch": 0.3757159221076747,
+      "grad_norm": 9.974946022033691,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.5821,
+      "step": 41
+    },
+    {
+      "epoch": 0.3848797250859107,
+      "grad_norm": 9.801668167114258,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.4434,
+      "step": 42
+    },
+    {
+      "epoch": 0.3940435280641466,
+      "grad_norm": 9.01752758026123,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.2707,
+      "step": 43
+    },
+    {
+      "epoch": 0.4032073310423826,
+      "grad_norm": 9.52054214477539,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7401,
+      "step": 44
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 8.228753089904785,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.2554,
+      "step": 45
+    },
+    {
+      "epoch": 0.4215349369988545,
+      "grad_norm": 13.116497039794922,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.9396,
+      "step": 46
+    },
+    {
+      "epoch": 0.4306987399770905,
+      "grad_norm": 14.946843147277832,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.3675,
+      "step": 47
+    },
+    {
+      "epoch": 0.43986254295532645,
+      "grad_norm": 7.809497833251953,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.3153,
+      "step": 48
+    },
+    {
+      "epoch": 0.44902634593356244,
+      "grad_norm": 8.037880897521973,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1886,
+      "step": 49
+    },
+    {
+      "epoch": 0.4581901489117984,
+      "grad_norm": 7.643946647644043,
+      "learning_rate": 0.0,
+      "loss": 2.1599,
+      "step": 50
+    },
+    {
+      "epoch": 0.4581901489117984,
+      "eval_loss": 2.710082769393921,
+      "eval_runtime": 20.1677,
+      "eval_samples_per_second": 36.444,
+      "eval_steps_per_second": 4.562,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null