Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c34f3483a38621c250f62812d2fd9819040f889762c6de42506eaaafd3873fe
+oid sha256:238dce7c435f6b5bdbe530da6548984a476854ae1706aaf37c844bb147e7362e
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc1e7e0f7850289d1e6c7fa11db386bbf86d3fef990e2b896dfd2c764a4621e
+oid sha256:5709bd1fb1173fb94bf9fd8d4f45473fe9e31304074153f0a336044b210f4cf3
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58dcbbb34167098f45a31c89b1d2aba0c4e511e014d0db5a5a29f8c190e52b04
+oid sha256:ed810458cf913de304b71446bf48fb5daf1bcf4ca5ffb1be8e29e70ea2396ec7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a1c8e570470a0d0210f02abd46fba29629f586113562381ed428e4a52d43078
+oid sha256:997f46a113e98bd808dfe430a6b6e11f7f0f04c10171b36e981eec6703466064
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bbd45a64af96309071650287865386e3272194db4870c3044733f6faeafb9f9
+oid sha256:73e49efcbd485ab5c0867519a4900b2efd6b9d9823dfb7191d5cc270075ee52a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c17fb080923c87172ed83ca17bc061ab96d0f2ea48a09b8f4560ef03dc76b6f2
+oid sha256:ec812469b033fb6f8cf678135560949da6976e5ad150ccae7aac17f92b6f1ca6
 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": 0.20079676806926727,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22148394241417496,
+  "best_metric": 0.1689685732126236,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4429678848283499,
   "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": 86.93,
       "eval_steps_per_second": 10.966,
       "step": 25
+    },
+    {
+      "epoch": 0.23034330011074197,
+      "grad_norm": 0.23005038499832153,
+      "learning_rate": 5e-05,
+      "loss": 0.1945,
+      "step": 26
+    },
+    {
+      "epoch": 0.23920265780730898,
+      "grad_norm": 0.18238848447799683,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1718,
+      "step": 27
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 0.16891257464885712,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1674,
+      "step": 28
+    },
+    {
+      "epoch": 0.25692137320044295,
+      "grad_norm": 0.2011295109987259,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1689,
+      "step": 29
+    },
+    {
+      "epoch": 0.26578073089701,
+      "grad_norm": 0.175749734044075,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1605,
+      "step": 30
+    },
+    {
+      "epoch": 0.27464008859357697,
+      "grad_norm": 0.1887713372707367,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1546,
+      "step": 31
+    },
+    {
+      "epoch": 0.28349944629014395,
+      "grad_norm": 0.2062009572982788,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1687,
+      "step": 32
+    },
+    {
+      "epoch": 0.292358803986711,
+      "grad_norm": 0.23018425703048706,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1753,
+      "step": 33
+    },
+    {
+      "epoch": 0.301218161683278,
+      "grad_norm": 0.21273936331272125,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1499,
+      "step": 34
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 0.2382647693157196,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1556,
+      "step": 35
+    },
+    {
+      "epoch": 0.31893687707641194,
+      "grad_norm": 0.2492895871400833,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1324,
+      "step": 36
+    },
+    {
+      "epoch": 0.327796234772979,
+      "grad_norm": 0.31593284010887146,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1734,
+      "step": 37
+    },
+    {
+      "epoch": 0.33665559246954596,
+      "grad_norm": 0.1830340176820755,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1855,
+      "step": 38
+    },
+    {
+      "epoch": 0.34551495016611294,
+      "grad_norm": 0.14966778457164764,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1531,
+      "step": 39
+    },
+    {
+      "epoch": 0.35437430786268,
+      "grad_norm": 0.1577373743057251,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1528,
+      "step": 40
+    },
+    {
+      "epoch": 0.36323366555924697,
+      "grad_norm": 0.1569824367761612,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1601,
+      "step": 41
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.16769661009311676,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1691,
+      "step": 42
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.16713380813598633,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1555,
+      "step": 43
+    },
+    {
+      "epoch": 0.38981173864894797,
+      "grad_norm": 0.1945611983537674,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.151,
+      "step": 44
+    },
+    {
+      "epoch": 0.39867109634551495,
+      "grad_norm": 0.17325228452682495,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1316,
+      "step": 45
+    },
+    {
+      "epoch": 0.40753045404208194,
+      "grad_norm": 0.20813417434692383,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1633,
+      "step": 46
+    },
+    {
+      "epoch": 0.416389811738649,
+      "grad_norm": 0.22054564952850342,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1571,
+      "step": 47
+    },
+    {
+      "epoch": 0.42524916943521596,
+      "grad_norm": 0.23001566529273987,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1502,
+      "step": 48
+    },
+    {
+      "epoch": 0.43410852713178294,
+      "grad_norm": 0.26263147592544556,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1695,
+      "step": 49
+    },
+    {
+      "epoch": 0.4429678848283499,
+      "grad_norm": 0.5053365230560303,
+      "learning_rate": 0.0,
+      "loss": 0.2582,
+      "step": 50
+    },
+    {
+      "epoch": 0.4429678848283499,
+      "eval_loss": 0.1689685732126236,
+      "eval_runtime": 8.753,
+      "eval_samples_per_second": 86.942,
+      "eval_steps_per_second": 10.968,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null