Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256c2f8e1260a7622cf1d8e11977e803610b022bbd6703f88d4b64b356373ca4
+oid sha256:c94000dc6a3f677caf82a3bc5d59fbbc988a83809dd3b4d8e33e0287cf13a7e8
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5719c097bc43798993b97b9e60e96a4099df1a22c73304502ecdac11ab9df3
+oid sha256:d2525e4c0e14d00dfc89ffc8ca73aea1a8edd92c5b461f130ca6ad437d3541be
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7526fbb52368d9791c5e6b6c040afce75d06fc96730ff4060a984bb482fc32a
+oid sha256:6b969c711c43ebe82f770cd279a2a626ab920349ac7e4f17702874b5f2e47c0f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde1f6f4bb694ab3ea42ee05def9789e4cae430686e62495b448e5d25442e09a
+oid sha256:de9393c7d1cddee85effde6dd4d6075dade1f83fad28f1a809520932a49a26ec
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5cef2e2d8f907778c441c204e7ba0ee793ae3963ba303f54c93404a5a91d105
+oid sha256:4431ecc4347224255b137f48a08b8f962a34003a612c15c66b23915c57c188d4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a53a617abee2e173e9852e97655cb7c5569f6ce731bf6c49e7471d26d7d9c1e9
+oid sha256:1ca90aad1383fb19411bfa470d6d1675e2327ae99ecb717f8fd9702ae25df423
 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": 10.758125305175781,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.046739892498247254,
+  "best_metric": 10.649374961853027,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09347978499649451,
   "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": 586.422,
       "eval_steps_per_second": 152.47,
       "step": 25
+    },
+    {
+      "epoch": 0.04860948819817715,
+      "grad_norm": 63.860252380371094,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 172.4219,
+      "step": 26
+    },
+    {
+      "epoch": 0.050479083898107034,
+      "grad_norm": 63.61211013793945,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 172.3281,
+      "step": 27
+    },
+    {
+      "epoch": 0.05234867959803693,
+      "grad_norm": 62.87015151977539,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 172.125,
+      "step": 28
+    },
+    {
+      "epoch": 0.054218275297966814,
+      "grad_norm": 54.35555648803711,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 171.8021,
+      "step": 29
+    },
+    {
+      "epoch": 0.05608787099789671,
+      "grad_norm": 55.90229415893555,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 171.6797,
+      "step": 30
+    },
+    {
+      "epoch": 0.057957466697826594,
+      "grad_norm": 53.78763961791992,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 171.4062,
+      "step": 31
+    },
+    {
+      "epoch": 0.05982706239775649,
+      "grad_norm": 52.55021286010742,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 171.2891,
+      "step": 32
+    },
+    {
+      "epoch": 0.061696658097686374,
+      "grad_norm": 51.70108413696289,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 171.125,
+      "step": 33
+    },
+    {
+      "epoch": 0.06356625379761627,
+      "grad_norm": 51.2154655456543,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 171.0859,
+      "step": 34
+    },
+    {
+      "epoch": 0.06543584949754616,
+      "grad_norm": 49.51068115234375,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 170.6875,
+      "step": 35
+    },
+    {
+      "epoch": 0.06730544519747604,
+      "grad_norm": 48.02348327636719,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 170.6172,
+      "step": 36
+    },
+    {
+      "epoch": 0.06917504089740593,
+      "grad_norm": 52.98481750488281,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 170.8828,
+      "step": 37
+    },
+    {
+      "epoch": 0.07104463659733583,
+      "grad_norm": 36.483245849609375,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 171.2031,
+      "step": 38
+    },
+    {
+      "epoch": 0.07291423229726572,
+      "grad_norm": 55.7339973449707,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 171.7656,
+      "step": 39
+    },
+    {
+      "epoch": 0.0747838279971956,
+      "grad_norm": 54.79682540893555,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 171.75,
+      "step": 40
+    },
+    {
+      "epoch": 0.0766534236971255,
+      "grad_norm": 35.19290542602539,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 171.0078,
+      "step": 41
+    },
+    {
+      "epoch": 0.07852301939705539,
+      "grad_norm": 43.35811233520508,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 170.1641,
+      "step": 42
+    },
+    {
+      "epoch": 0.08039261509698528,
+      "grad_norm": 43.71001052856445,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 170.2266,
+      "step": 43
+    },
+    {
+      "epoch": 0.08226221079691516,
+      "grad_norm": 45.270477294921875,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 170.3828,
+      "step": 44
+    },
+    {
+      "epoch": 0.08413180649684505,
+      "grad_norm": 47.626712799072266,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 170.4922,
+      "step": 45
+    },
+    {
+      "epoch": 0.08600140219677495,
+      "grad_norm": 44.49309539794922,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 170.2969,
+      "step": 46
+    },
+    {
+      "epoch": 0.08787099789670484,
+      "grad_norm": 43.53394317626953,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 170.1562,
+      "step": 47
+    },
+    {
+      "epoch": 0.08974059359663472,
+      "grad_norm": 43.8607177734375,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 170.1562,
+      "step": 48
+    },
+    {
+      "epoch": 0.09161018929656461,
+      "grad_norm": 41.6094970703125,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 169.9922,
+      "step": 49
+    },
+    {
+      "epoch": 0.09347978499649451,
+      "grad_norm": 43.91381072998047,
+      "learning_rate": 1e-05,
+      "loss": 170.2109,
+      "step": 50
+    },
+    {
+      "epoch": 0.09347978499649451,
+      "eval_loss": 10.649374961853027,
+      "eval_runtime": 0.0851,
+      "eval_samples_per_second": 587.469,
+      "eval_steps_per_second": 152.742,
+      "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": 2101346304000.0,
+  "total_flos": 4202692608000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null