Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ffdeb5b0c9971fd4bc708ae8ba9d156294e0fa22c2d672c50eadf3ad52077bf
+oid sha256:b88a9e646634db79cb84e01628513984fda0ba92e71c7e78facdc8a078e9aeef
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d75bea1f854ccf45211b310ef21c23b2c3e9fe03ada188f67cb3c3c0c507ad
+oid sha256:20db41301a03d403789777abbab5fec436b228f62ad5a236f8797e838cac8b60
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ab6246b153f475a1cdde00ee344148098f311283b1adf6e6374b9996f1ca3e4
+oid sha256:db80d1ceaf79b13c80364a0497e156e5e55c26d0c0eec9d7045a0971697d3a90
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a8648d725732dfec9ae63a9ea715300772f909153c68b13d81e34c831d011f1
+oid sha256:09925c2a43e67960ebdd6a2f7c421b45f5fe8bcecf833b0ee4f61c0c3ce32a9d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46af0960f3c906cc2e5bbf35470d236ecdf9c1e2759ca612271f969d9eb4d0f1
+oid sha256:084b3926dec175486226a12c3c0421815923037e1874d2c6fbc1ce437d799543
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eda6132e8e3a8270c37166f87ddbff25c39b22434f57d397c3401c6ac5e73954
+oid sha256:7050b7477c7ba109a8b1c1e06178b989b44dd536e6501218f8fa2422d1dda687
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e23a2d1e485599a7b5fae1501ffcbc43db47e90bf1e1f6de6ac821e4368041
+oid sha256:eff6fb7d68f4fba752f9a34c10ead544a122d6bff4d10f27de692e046608ac1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.006207775324583054,
-  "best_model_checkpoint": "miner_id_24/checkpoint-125",
-  "epoch": 0.6108735491753207,
+  "best_metric": 0.004802440293133259,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.7330482590103848,
   "eval_steps": 25,
-  "global_step": 125,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -930,6 +930,189 @@
       "eval_samples_per_second": 15.436,
       "eval_steps_per_second": 4.013,
       "step": 125
+    },
+    {
+      "epoch": 0.6157605375687233,
+      "grad_norm": 0.2093576341867447,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0323,
+      "step": 126
+    },
+    {
+      "epoch": 0.6206475259621258,
+      "grad_norm": 0.24124690890312195,
+      "learning_rate": 1.5547295993162156e-05,
+      "loss": 0.0263,
+      "step": 127
+    },
+    {
+      "epoch": 0.6255345143555284,
+      "grad_norm": 0.22997763752937317,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.0246,
+      "step": 128
+    },
+    {
+      "epoch": 0.6304215027489309,
+      "grad_norm": 0.17232383787631989,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.024,
+      "step": 129
+    },
+    {
+      "epoch": 0.6353084911423336,
+      "grad_norm": 0.20387302339076996,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.021,
+      "step": 130
+    },
+    {
+      "epoch": 0.6401954795357361,
+      "grad_norm": 0.19521893560886383,
+      "learning_rate": 1.3810983439624881e-05,
+      "loss": 0.0224,
+      "step": 131
+    },
+    {
+      "epoch": 0.6450824679291387,
+      "grad_norm": 0.16281966865062714,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0145,
+      "step": 132
+    },
+    {
+      "epoch": 0.6499694563225412,
+      "grad_norm": 0.13637928664684296,
+      "learning_rate": 1.305964588227407e-05,
+      "loss": 0.0133,
+      "step": 133
+    },
+    {
+      "epoch": 0.6548564447159438,
+      "grad_norm": 0.194955512881279,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0181,
+      "step": 134
+    },
+    {
+      "epoch": 0.6597434331093464,
+      "grad_norm": 0.12221532315015793,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.009,
+      "step": 135
+    },
+    {
+      "epoch": 0.664630421502749,
+      "grad_norm": 0.14309658110141754,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.01,
+      "step": 136
+    },
+    {
+      "epoch": 0.6695174098961515,
+      "grad_norm": 0.1093713566660881,
+      "learning_rate": 1.1797756552633215e-05,
+      "loss": 0.0051,
+      "step": 137
+    },
+    {
+      "epoch": 0.674404398289554,
+      "grad_norm": 0.2528100609779358,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0218,
+      "step": 138
+    },
+    {
+      "epoch": 0.6792913866829566,
+      "grad_norm": 0.27401408553123474,
+      "learning_rate": 1.1289606858403237e-05,
+      "loss": 0.0312,
+      "step": 139
+    },
+    {
+      "epoch": 0.6841783750763591,
+      "grad_norm": 0.20631706714630127,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.0255,
+      "step": 140
+    },
+    {
+      "epoch": 0.6890653634697618,
+      "grad_norm": 0.2128758430480957,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0194,
+      "step": 141
+    },
+    {
+      "epoch": 0.6939523518631643,
+      "grad_norm": 0.24871855974197388,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.0204,
+      "step": 142
+    },
+    {
+      "epoch": 0.6988393402565669,
+      "grad_norm": 0.2161489576101303,
+      "learning_rate": 1.0523732028950771e-05,
+      "loss": 0.0172,
+      "step": 143
+    },
+    {
+      "epoch": 0.7037263286499694,
+      "grad_norm": 0.1810789704322815,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0137,
+      "step": 144
+    },
+    {
+      "epoch": 0.708613317043372,
+      "grad_norm": 0.1576724499464035,
+      "learning_rate": 1.0267464779995617e-05,
+      "loss": 0.014,
+      "step": 145
+    },
+    {
+      "epoch": 0.7135003054367746,
+      "grad_norm": 0.17585541307926178,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.0117,
+      "step": 146
+    },
+    {
+      "epoch": 0.7183872938301772,
+      "grad_norm": 0.13925491273403168,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0111,
+      "step": 147
+    },
+    {
+      "epoch": 0.7232742822235797,
+      "grad_norm": 0.11349561810493469,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.0082,
+      "step": 148
+    },
+    {
+      "epoch": 0.7281612706169823,
+      "grad_norm": 0.11688259989023209,
+      "learning_rate": 1.001070878140409e-05,
+      "loss": 0.0054,
+      "step": 149
+    },
+    {
+      "epoch": 0.7330482590103848,
+      "grad_norm": 0.05643425136804581,
+      "learning_rate": 1e-05,
+      "loss": 0.0018,
+      "step": 150
+    },
+    {
+      "epoch": 0.7330482590103848,
+      "eval_loss": 0.004802440293133259,
+      "eval_runtime": 3.2337,
+      "eval_samples_per_second": 15.462,
+      "eval_steps_per_second": 4.02,
+      "step": 150
     }
   ],
   "logging_steps": 1,
@@ -953,12 +1136,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.406014452662272e+18,
+  "total_flos": 1.6872173431947264e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null