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:f31e004ffeb0bb82903918c032d4ebe1553278699c28e1e3d66900a7f0a40186
+oid sha256:fc3202e07b9e43627121d05bcfb66ebfe28c7070440d624eaf42e95d527a8df3
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3bd894f79f381b44cadb6afa65987bf8e59aff988e329a21882ee6afaa9b68c
+oid sha256:645204367fcf34215df68d7e75cff6055b6d955e1741235fc9c3040de0c8684b
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623d6ca3983582c2cb6d0c1eaf09adfb0f689b80dd1b2f572e177b9381168271
+oid sha256:6cf89cfa1385769d46a5c55c1d44b6ed7ac9f2ec77e410923c8aa4cf7e49fda0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b0bf93171008d838f403a7f1d32ef8b9e49a01ea2b97f411af8fa38e9f9011
+oid sha256:fe6cb0461cd8d987013207d6b281d2155504e0373f1ae2dedcbfd288613e5200
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca59f199f6fc8dec84b8fdf3984cd23db43ad2d1edf0103cbc8aeb9eb7244b2f
+oid sha256:1aae79dc007c4d9b025dd303db5b1607d6989f73af092dff9d1c074e1e3bfb0d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05992eb520f4e48c3b78ab22dd52906afbb83845d689e94c2be4e2ce3db21420
+oid sha256:08665753f4b3f1babeab6a1af367300b163eb8bb9261798b6f36fb8d9f9b44d0
 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": 0.9058130383491516,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.13175230566534915,
+  "best_metric": 0.8705747127532959,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2635046113306983,
   "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": 12.817,
       "eval_steps_per_second": 1.605,
       "step": 25
+    },
+    {
+      "epoch": 0.1370223978919631,
+      "grad_norm": 6.496657371520996,
+      "learning_rate": 5e-05,
+      "loss": 14.1128,
+      "step": 26
+    },
+    {
+      "epoch": 0.1422924901185771,
+      "grad_norm": 6.763591289520264,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 15.1578,
+      "step": 27
+    },
+    {
+      "epoch": 0.14756258234519104,
+      "grad_norm": 6.154540538787842,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 14.8887,
+      "step": 28
+    },
+    {
+      "epoch": 0.152832674571805,
+      "grad_norm": 5.286479949951172,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 15.2464,
+      "step": 29
+    },
+    {
+      "epoch": 0.15810276679841898,
+      "grad_norm": 4.394895553588867,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 15.6726,
+      "step": 30
+    },
+    {
+      "epoch": 0.16337285902503293,
+      "grad_norm": 3.7572078704833984,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 14.6112,
+      "step": 31
+    },
+    {
+      "epoch": 0.1686429512516469,
+      "grad_norm": 4.391316890716553,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 12.8835,
+      "step": 32
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 4.463949680328369,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 12.9088,
+      "step": 33
+    },
+    {
+      "epoch": 0.17918313570487485,
+      "grad_norm": 3.8616714477539062,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 13.0846,
+      "step": 34
+    },
+    {
+      "epoch": 0.1844532279314888,
+      "grad_norm": 4.396023750305176,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 13.2153,
+      "step": 35
+    },
+    {
+      "epoch": 0.18972332015810275,
+      "grad_norm": 4.106069564819336,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 13.286,
+      "step": 36
+    },
+    {
+      "epoch": 0.19499341238471674,
+      "grad_norm": 4.250127792358398,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 13.9948,
+      "step": 37
+    },
+    {
+      "epoch": 0.2002635046113307,
+      "grad_norm": 3.1949825286865234,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 14.2964,
+      "step": 38
+    },
+    {
+      "epoch": 0.20553359683794467,
+      "grad_norm": 3.5179386138916016,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 14.2741,
+      "step": 39
+    },
+    {
+      "epoch": 0.21080368906455862,
+      "grad_norm": 4.0739970207214355,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 14.7172,
+      "step": 40
+    },
+    {
+      "epoch": 0.2160737812911726,
+      "grad_norm": 4.186811447143555,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 15.4209,
+      "step": 41
+    },
+    {
+      "epoch": 0.22134387351778656,
+      "grad_norm": 4.2096452713012695,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 15.429,
+      "step": 42
+    },
+    {
+      "epoch": 0.22661396574440051,
+      "grad_norm": 4.489388465881348,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 15.578,
+      "step": 43
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 3.9326608180999756,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 13.0144,
+      "step": 44
+    },
+    {
+      "epoch": 0.23715415019762845,
+      "grad_norm": 3.543126106262207,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 13.1908,
+      "step": 45
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 2.9515583515167236,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 12.4912,
+      "step": 46
+    },
+    {
+      "epoch": 0.24769433465085638,
+      "grad_norm": 2.6371042728424072,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 13.0061,
+      "step": 47
+    },
+    {
+      "epoch": 0.25296442687747034,
+      "grad_norm": 2.5240566730499268,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 13.5621,
+      "step": 48
+    },
+    {
+      "epoch": 0.25823451910408435,
+      "grad_norm": 3.0576345920562744,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 13.9055,
+      "step": 49
+    },
+    {
+      "epoch": 0.2635046113306983,
+      "grad_norm": 3.395519971847534,
+      "learning_rate": 0.0,
+      "loss": 13.8772,
+      "step": 50
+    },
+    {
+      "epoch": 0.2635046113306983,
+      "eval_loss": 0.8705747127532959,
+      "eval_runtime": 100.1532,
+      "eval_samples_per_second": 12.76,
+      "eval_steps_per_second": 1.598,
+      "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": 3.932824275748127e+17,
+  "total_flos": 7.873865919150162e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null