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:a69700d40336104ec21855ca0320e8b7412158747886c4e8ea50c5af4c52fabe
+oid sha256:f24ce67e16ec135bf21d08501230e2df964d79959a8882daea2cc1c4a94aca63
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26be46e8ff7e73438f72b7ee91f66452f3c71336fd15b9b066d47bb030505d4e
+oid sha256:d082fb3955126a26486c6be3303ba88a34f66626c7475267473593806211c462
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8457bfb0d4e8dcaaf338b4628ea24e45d9e5d9a4b3b72ca055855c1f0215f128
+oid sha256:0eb21e82b011b7d30fd0ac496fedf28752f9ea329a1c568233af406b22fbcc7c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ceebb1fd0bd792e381df2a37e60e1e9c391ef0ed860efb8fe0dcb4ffd6a747e
+oid sha256:dfbf53b715a886085ccdc997a79c5c0e5e1656108a19e7a182849c2d386d26d2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba12122b6e97d44b0aac29e2f7d4039e43b1e2fdeb394dde46ef1514e981bfdb
+oid sha256:36f0761e8e30fa05afa7f1ac56ac5f11c18b7bf7a8f7e4963d9240b364a79651
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a8b253551205423cdfa748932b9f8d4f3424464790e7f8042f97df81e11333
+oid sha256:306349d9dda1c5e1befe66a7b5744cb7d21ada3b6747bc797fe6187d4f5c7ae7
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6495192050933838,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14492753623188406,
+  "best_metric": 0.39716607332229614,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2898550724637681,
   "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": 44.983,
       "eval_steps_per_second": 11.696,
       "step": 25
+    },
+    {
+      "epoch": 0.15072463768115943,
+      "grad_norm": 3.3572421073913574,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6819,
+      "step": 26
+    },
+    {
+      "epoch": 0.1565217391304348,
+      "grad_norm": 2.560725212097168,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6434,
+      "step": 27
+    },
+    {
+      "epoch": 0.16231884057971013,
+      "grad_norm": 2.2695226669311523,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6025,
+      "step": 28
+    },
+    {
+      "epoch": 0.1681159420289855,
+      "grad_norm": 2.8875999450683594,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6578,
+      "step": 29
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 2.134882688522339,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5826,
+      "step": 30
+    },
+    {
+      "epoch": 0.17971014492753623,
+      "grad_norm": 1.8630090951919556,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5471,
+      "step": 31
+    },
+    {
+      "epoch": 0.1855072463768116,
+      "grad_norm": 3.8702120780944824,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5753,
+      "step": 32
+    },
+    {
+      "epoch": 0.19130434782608696,
+      "grad_norm": 1.330750584602356,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5259,
+      "step": 33
+    },
+    {
+      "epoch": 0.19710144927536233,
+      "grad_norm": 1.5397303104400635,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5233,
+      "step": 34
+    },
+    {
+      "epoch": 0.2028985507246377,
+      "grad_norm": 1.617982268333435,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5063,
+      "step": 35
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 1.4378247261047363,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4855,
+      "step": 36
+    },
+    {
+      "epoch": 0.2144927536231884,
+      "grad_norm": 1.699135661125183,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.5608,
+      "step": 37
+    },
+    {
+      "epoch": 0.22028985507246376,
+      "grad_norm": 1.7574081420898438,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5302,
+      "step": 38
+    },
+    {
+      "epoch": 0.22608695652173913,
+      "grad_norm": 1.6374109983444214,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4257,
+      "step": 39
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 2.2475686073303223,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5505,
+      "step": 40
+    },
+    {
+      "epoch": 0.23768115942028986,
+      "grad_norm": 2.40238881111145,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5059,
+      "step": 41
+    },
+    {
+      "epoch": 0.24347826086956523,
+      "grad_norm": 2.1908628940582275,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4962,
+      "step": 42
+    },
+    {
+      "epoch": 0.2492753623188406,
+      "grad_norm": 2.013533592224121,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5273,
+      "step": 43
+    },
+    {
+      "epoch": 0.25507246376811593,
+      "grad_norm": 2.148557186126709,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.447,
+      "step": 44
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 1.5102720260620117,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4032,
+      "step": 45
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.6244993209838867,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4339,
+      "step": 46
+    },
+    {
+      "epoch": 0.27246376811594203,
+      "grad_norm": 1.256397008895874,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4239,
+      "step": 47
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "grad_norm": 2.4411745071411133,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5304,
+      "step": 48
+    },
+    {
+      "epoch": 0.28405797101449276,
+      "grad_norm": 1.6444889307022095,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4382,
+      "step": 49
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 2.026066303253174,
+      "learning_rate": 1e-05,
+      "loss": 0.4483,
+      "step": 50
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "eval_loss": 0.39716607332229614,
+      "eval_runtime": 1.1118,
+      "eval_samples_per_second": 44.974,
+      "eval_steps_per_second": 11.693,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null