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:b7d185350f90d09388d7eb426463f798cae137a1fa973158174185bc65ac171a
+oid sha256:5170b5cff4b0f669537ee11b3782d518bfe5e73a2368ffe9adc52c1d50ea4c43
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ab8576a2d26dbe3553284478c77052a4d849f8f3397c0d897fbdfe7e902dc4
+oid sha256:99942b3f5032d2ae44afa66485b5ef65fa28c908db5990f2c9dd333bb87e984d
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8efc5bd7e02f5089fd86bde33c6d1752498ceb3cd8f9bc58ba94f242f5d1a094
+oid sha256:af87dc7e81576bca71b782a7d473962462174e0396693274330e8c5754b6d85e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff0dd9673fc0b730845ea7a1db60c09e9399ab323e9510010848a243e42d4b3
+oid sha256:d282403c6523c5e2b424ae068f3fc7f162ec7823fd1ca589632c01f14a4caf0f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a65ef146cc57b08caa4f6413e2b3eb88cdfc87eeaaaafbeadcab3f2e338648f
+oid sha256:47e082a4a8ffe70bf0c773e4ed5653f530b0c1026164d5a7fed8d84dbb7ae533
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2157d0c99e3a998588453bec8418324af8578e95466bd1a812bd82a0d3dda9c8
+oid sha256:669b6b43fc420fed85801409f9a5160aa43da0a7e0a8422ad2005d5eeded4f51
 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": 2.1840624809265137,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009861932938856016,
+  "best_metric": 0.3329808712005615,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01972386587771203,
   "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": 17.238,
       "eval_steps_per_second": 4.482,
       "step": 25
+    },
+    {
+      "epoch": 0.010256410256410256,
+      "grad_norm": 134.1509552001953,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 37.7689,
+      "step": 26
+    },
+    {
+      "epoch": 0.010650887573964497,
+      "grad_norm": 192.20062255859375,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 30.977,
+      "step": 27
+    },
+    {
+      "epoch": 0.011045364891518738,
+      "grad_norm": 278.26812744140625,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 27.1425,
+      "step": 28
+    },
+    {
+      "epoch": 0.011439842209072978,
+      "grad_norm": 349.2325439453125,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 23.5439,
+      "step": 29
+    },
+    {
+      "epoch": 0.011834319526627219,
+      "grad_norm": 398.40716552734375,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 18.3674,
+      "step": 30
+    },
+    {
+      "epoch": 0.01222879684418146,
+      "grad_norm": 395.0241394042969,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.8943,
+      "step": 31
+    },
+    {
+      "epoch": 0.0126232741617357,
+      "grad_norm": 240.70681762695312,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 8.0201,
+      "step": 32
+    },
+    {
+      "epoch": 0.01301775147928994,
+      "grad_norm": 94.83889770507812,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 5.7875,
+      "step": 33
+    },
+    {
+      "epoch": 0.013412228796844181,
+      "grad_norm": 37.95793151855469,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.7613,
+      "step": 34
+    },
+    {
+      "epoch": 0.013806706114398421,
+      "grad_norm": 26.57615089416504,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.4461,
+      "step": 35
+    },
+    {
+      "epoch": 0.014201183431952662,
+      "grad_norm": 23.705547332763672,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.7367,
+      "step": 36
+    },
+    {
+      "epoch": 0.014595660749506903,
+      "grad_norm": 576.8201293945312,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 35.7901,
+      "step": 37
+    },
+    {
+      "epoch": 0.014990138067061143,
+      "grad_norm": 454.54058837890625,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 28.4482,
+      "step": 38
+    },
+    {
+      "epoch": 0.015384615384615385,
+      "grad_norm": 13.692035675048828,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.371,
+      "step": 39
+    },
+    {
+      "epoch": 0.015779092702169626,
+      "grad_norm": 9.434082984924316,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.5141,
+      "step": 40
+    },
+    {
+      "epoch": 0.016173570019723867,
+      "grad_norm": 8.686306953430176,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.3778,
+      "step": 41
+    },
+    {
+      "epoch": 0.016568047337278107,
+      "grad_norm": 14.598600387573242,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.5165,
+      "step": 42
+    },
+    {
+      "epoch": 0.016962524654832348,
+      "grad_norm": 8.761627197265625,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.4743,
+      "step": 43
+    },
+    {
+      "epoch": 0.01735700197238659,
+      "grad_norm": 4.435027599334717,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.2297,
+      "step": 44
+    },
+    {
+      "epoch": 0.01775147928994083,
+      "grad_norm": 3.197697639465332,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.2066,
+      "step": 45
+    },
+    {
+      "epoch": 0.01814595660749507,
+      "grad_norm": 4.16876745223999,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.0468,
+      "step": 46
+    },
+    {
+      "epoch": 0.01854043392504931,
+      "grad_norm": 6.92716646194458,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.346,
+      "step": 47
+    },
+    {
+      "epoch": 0.01893491124260355,
+      "grad_norm": 6.868653774261475,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.3406,
+      "step": 48
+    },
+    {
+      "epoch": 0.01932938856015779,
+      "grad_norm": 76.7080307006836,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 8.5237,
+      "step": 49
+    },
+    {
+      "epoch": 0.01972386587771203,
+      "grad_norm": 772.5637817382812,
+      "learning_rate": 1e-05,
+      "loss": 47.5903,
+      "step": 50
+    },
+    {
+      "epoch": 0.01972386587771203,
+      "eval_loss": 0.3329808712005615,
+      "eval_runtime": 2.9191,
+      "eval_samples_per_second": 17.128,
+      "eval_steps_per_second": 4.453,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null