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:c9105b7055a63f30f29fb32590945ebd2c1c2eec6ffb528e9ef702fe9fce1a3b
+oid sha256:d1af39b1fb18ecc10628149bf8b77c59aa8bbf9640638a4f6fe6acbb691aa726
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1061a48936537d7921184e4b32c18dff2b1d44d65d379375741149505534e410
+oid sha256:a57dece82a08e51811282a2ec08d35a89700422d8e345ccb0fccea8360542e7d
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74cfa8cf61312720f5a3bdc445b3ff343a3c56f9f684e5f463f32c0f47d67ba4
+oid sha256:975404b4025d9324258f7a44d83e4aa803cd0b1ef60f074d9c45c96e73902b86
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782d59748f38954bc2487463e6c7e83bb2678e6ca0e18c5d2939f203ebb0ab3b
+oid sha256:330c65b489f4809a3b1f07b3875d8172be227714ebc08d2c69bab3aa10fbf81c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f99d2261117aca85e8fb858e0eef961fc66c63a54e118860885750f9117983b3
+oid sha256:d7243305e45fbefd795e8d0ea082c272dd7c763e0278a38bc9e5b705c9ee0deb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6db1b29536c5780046633ae6cfbdc8661ff13aed7f0068290fbb4834593e5c
+oid sha256:053ab63088aa495a0474d02bbc2e39ba250d669e2bb0ea0cabe2b7a8313f2268
 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": 0.10299577564001083,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09248554913294797,
+  "best_metric": 0.09621890634298325,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.18497109826589594,
   "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": 37.895,
       "eval_steps_per_second": 4.745,
       "step": 25
+    },
+    {
+      "epoch": 0.09618497109826589,
+      "grad_norm": 0.2436722069978714,
+      "learning_rate": 5e-05,
+      "loss": 0.1035,
+      "step": 26
+    },
+    {
+      "epoch": 0.09988439306358382,
+      "grad_norm": 0.16461080312728882,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1078,
+      "step": 27
+    },
+    {
+      "epoch": 0.10358381502890174,
+      "grad_norm": 0.14472082257270813,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1051,
+      "step": 28
+    },
+    {
+      "epoch": 0.10728323699421966,
+      "grad_norm": 0.17404970526695251,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1087,
+      "step": 29
+    },
+    {
+      "epoch": 0.11098265895953757,
+      "grad_norm": 0.12008468806743622,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1049,
+      "step": 30
+    },
+    {
+      "epoch": 0.11468208092485549,
+      "grad_norm": 0.13445191085338593,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0999,
+      "step": 31
+    },
+    {
+      "epoch": 0.1183815028901734,
+      "grad_norm": 0.08790981024503708,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0981,
+      "step": 32
+    },
+    {
+      "epoch": 0.12208092485549132,
+      "grad_norm": 0.08825737237930298,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0995,
+      "step": 33
+    },
+    {
+      "epoch": 0.12578034682080924,
+      "grad_norm": 0.06886397302150726,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0978,
+      "step": 34
+    },
+    {
+      "epoch": 0.12947976878612716,
+      "grad_norm": 0.15950433909893036,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0991,
+      "step": 35
+    },
+    {
+      "epoch": 0.13317919075144508,
+      "grad_norm": 0.15729287266731262,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0908,
+      "step": 36
+    },
+    {
+      "epoch": 0.136878612716763,
+      "grad_norm": 0.09872325509786606,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0954,
+      "step": 37
+    },
+    {
+      "epoch": 0.14057803468208094,
+      "grad_norm": 0.14306682348251343,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0959,
+      "step": 38
+    },
+    {
+      "epoch": 0.14427745664739886,
+      "grad_norm": 0.06087346002459526,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.103,
+      "step": 39
+    },
+    {
+      "epoch": 0.14797687861271677,
+      "grad_norm": 0.04816189408302307,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1025,
+      "step": 40
+    },
+    {
+      "epoch": 0.1516763005780347,
+      "grad_norm": 0.06453908234834671,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1042,
+      "step": 41
+    },
+    {
+      "epoch": 0.1553757225433526,
+      "grad_norm": 0.05799945443868637,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1007,
+      "step": 42
+    },
+    {
+      "epoch": 0.15907514450867052,
+      "grad_norm": 0.08636831492185593,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0977,
+      "step": 43
+    },
+    {
+      "epoch": 0.16277456647398844,
+      "grad_norm": 0.08446965366601944,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1025,
+      "step": 44
+    },
+    {
+      "epoch": 0.16647398843930636,
+      "grad_norm": 0.06017603725194931,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0972,
+      "step": 45
+    },
+    {
+      "epoch": 0.17017341040462428,
+      "grad_norm": 0.15928272902965546,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0973,
+      "step": 46
+    },
+    {
+      "epoch": 0.1738728323699422,
+      "grad_norm": 0.13271377980709076,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0946,
+      "step": 47
+    },
+    {
+      "epoch": 0.1775722543352601,
+      "grad_norm": 0.1516481637954712,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0962,
+      "step": 48
+    },
+    {
+      "epoch": 0.18127167630057803,
+      "grad_norm": 0.19494952261447906,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0885,
+      "step": 49
+    },
+    {
+      "epoch": 0.18497109826589594,
+      "grad_norm": 0.149687722325325,
+      "learning_rate": 0.0,
+      "loss": 0.0891,
+      "step": 50
+    },
+    {
+      "epoch": 0.18497109826589594,
+      "eval_loss": 0.09621890634298325,
+      "eval_runtime": 48.0237,
+      "eval_samples_per_second": 37.919,
+      "eval_steps_per_second": 4.748,
+      "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