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:f1a2e16d076c735f938fccede83488333275f1027b5948727c469172a64a321c
+oid sha256:f0091eb4076f31f4da19ea78a400453b90bf6910f657f63965a83111aa6f1ad1
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960a178d67aa25fbbac5cc5b7173acef0036ef9b23c07728a33aa79b8a3ae05d
+oid sha256:775bf08506081f6e0825063a9a06b040eceaad74a3f11d03c2660a3c71ed768f
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba20a5e53d8f84f842a14484889315df7057e9af59605fafe0edcbc796701514
+oid sha256:bbba19c82ace6c9f3883969ff90995e7b5e9c6536bbd5074723e7c50d479add5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc78efddb7c467d2ace910efafe6796005d00b004e10538a08ac0306bee1927c
+oid sha256:200c0457b349c4525c62dfd85e35fb01a1fb9e2e27dde1551d2dd0bccc1c710b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9659da13db61db3f9dc6dd8315fb96567d6f0f98c13e76cb4fe436aa193e294
+oid sha256:6955a8bac6188aecada019daa4c3ad4a0de4f68066cd6801e9719ba9b8a52e93
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12ffa19b6ce8cd16dec63bc67d3009e776b0e9ca5b1a2fc5f31103a6d68e8c1e
+oid sha256:fff2ebb61c159ddaf79c65ee8ba7454492b9a1736f15efc629b9d2ae89350427
 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": 2.9409637451171875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04092909035096695,
+  "best_metric": 2.9392035007476807,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0818581807019339,
   "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": 21.588,
       "eval_steps_per_second": 5.613,
       "step": 25
+    },
+    {
+      "epoch": 0.04256625396500563,
+      "grad_norm": 1.1100581884384155,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.9468,
+      "step": 26
+    },
+    {
+      "epoch": 0.04420341757904431,
+      "grad_norm": 0.9862481355667114,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.9487,
+      "step": 27
+    },
+    {
+      "epoch": 0.045840581193082985,
+      "grad_norm": 1.2358273267745972,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.9564,
+      "step": 28
+    },
+    {
+      "epoch": 0.04747774480712166,
+      "grad_norm": 0.9344875812530518,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.9207,
+      "step": 29
+    },
+    {
+      "epoch": 0.04911490842116034,
+      "grad_norm": 0.8685237169265747,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.9744,
+      "step": 30
+    },
+    {
+      "epoch": 0.05075207203519902,
+      "grad_norm": 2.7281575202941895,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.9912,
+      "step": 31
+    },
+    {
+      "epoch": 0.0523892356492377,
+      "grad_norm": 1.0124826431274414,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.9551,
+      "step": 32
+    },
+    {
+      "epoch": 0.054026399263276376,
+      "grad_norm": 0.9179672598838806,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.9473,
+      "step": 33
+    },
+    {
+      "epoch": 0.055663562877315054,
+      "grad_norm": 1.4163392782211304,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.9576,
+      "step": 34
+    },
+    {
+      "epoch": 0.05730072649135373,
+      "grad_norm": 1.061346173286438,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.9498,
+      "step": 35
+    },
+    {
+      "epoch": 0.05893789010539241,
+      "grad_norm": 1.157851219177246,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.9763,
+      "step": 36
+    },
+    {
+      "epoch": 0.06057505371943109,
+      "grad_norm": 2.304241180419922,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.9774,
+      "step": 37
+    },
+    {
+      "epoch": 0.062212217333469766,
+      "grad_norm": 0.8605313301086426,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.9791,
+      "step": 38
+    },
+    {
+      "epoch": 0.06384938094750844,
+      "grad_norm": 1.7160407304763794,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.9454,
+      "step": 39
+    },
+    {
+      "epoch": 0.06548654456154712,
+      "grad_norm": 1.476172685623169,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.9368,
+      "step": 40
+    },
+    {
+      "epoch": 0.0671237081755858,
+      "grad_norm": 1.650292992591858,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.9679,
+      "step": 41
+    },
+    {
+      "epoch": 0.06876087178962448,
+      "grad_norm": 1.0009685754776,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.9895,
+      "step": 42
+    },
+    {
+      "epoch": 0.07039803540366316,
+      "grad_norm": 1.6898332834243774,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.9291,
+      "step": 43
+    },
+    {
+      "epoch": 0.07203519901770183,
+      "grad_norm": 1.084354043006897,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.9211,
+      "step": 44
+    },
+    {
+      "epoch": 0.07367236263174051,
+      "grad_norm": 0.9894816875457764,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.952,
+      "step": 45
+    },
+    {
+      "epoch": 0.07530952624577919,
+      "grad_norm": 0.7082793116569519,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.9281,
+      "step": 46
+    },
+    {
+      "epoch": 0.07694668985981787,
+      "grad_norm": 1.433164119720459,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.9442,
+      "step": 47
+    },
+    {
+      "epoch": 0.07858385347385655,
+      "grad_norm": 0.9894217848777771,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.9341,
+      "step": 48
+    },
+    {
+      "epoch": 0.08022101708789522,
+      "grad_norm": 0.9443101286888123,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.947,
+      "step": 49
+    },
+    {
+      "epoch": 0.0818581807019339,
+      "grad_norm": 1.3589372634887695,
+      "learning_rate": 1e-05,
+      "loss": 2.9448,
+      "step": 50
+    },
+    {
+      "epoch": 0.0818581807019339,
+      "eval_loss": 2.9392035007476807,
+      "eval_runtime": 2.3169,
+      "eval_samples_per_second": 21.58,
+      "eval_steps_per_second": 5.611,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null