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:a642bf0c76686046ae5fdfcbc4b870bfe992c4d15cb23f56a3ab32c36ebf5031
+oid sha256:1aec5621fabf6b9ee401eced69eb22fdaa2eb342769e6764f8871e002f7ec826
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd69da3e15956249c14e1977eac8735c5480211409dca22d2de8b574ff95f97
+oid sha256:2eaf93b5baf70cfb64abe9ec88bbb376ebdd7486ce85deb90e8c3609d4b63f21
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c08643ff9ded7cf3f17055b08e868fee8b67e3aa233c6c8eb5798dd37033f1
+oid sha256:c50dc250577e4989c88a0d59f5ecf64ad61c2c5b008809a4c5ea29f12015cd43
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef663b9d5db5841aa748d92441d76e9b62f7ad2f7fb5f35e3b3591d861e0f09
+oid sha256:5a07ed83ddedf908da8dd6a92332440ab58b787bda2826b69287153f4d6b9be4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e39b2073930327567813d316cec79700bfb0903fdc6412c1761c4917af95a600
+oid sha256:1add1f684a88cdebe0890c24728dd42c8219691a760c2ef3cae4c278d1b24ebf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e8c0f4f7fcae199faf33506a1ab9b5b16193f32698a7aff842e59449068b2d
+oid sha256:319a3c64eb8f94bda442aba66d0c63427a0c6906f57f8d0c6d4ce79562b99d18
 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": 11.729475975036621,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5037783375314862,
+  "best_metric": 11.714941024780273,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0113350125944585,
   "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": 210.788,
       "eval_steps_per_second": 54.805,
       "step": 25
+    },
+    {
+      "epoch": 0.5239294710327456,
+      "grad_norm": 0.2579650282859802,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.736,
+      "step": 26
+    },
+    {
+      "epoch": 0.5440806045340051,
+      "grad_norm": 0.26697853207588196,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7348,
+      "step": 27
+    },
+    {
+      "epoch": 0.5642317380352645,
+      "grad_norm": 0.2875326871871948,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7314,
+      "step": 28
+    },
+    {
+      "epoch": 0.5843828715365239,
+      "grad_norm": 0.2794216275215149,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7338,
+      "step": 29
+    },
+    {
+      "epoch": 0.6045340050377834,
+      "grad_norm": 0.29902562499046326,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7307,
+      "step": 30
+    },
+    {
+      "epoch": 0.6246851385390428,
+      "grad_norm": 0.31257784366607666,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.7296,
+      "step": 31
+    },
+    {
+      "epoch": 0.6448362720403022,
+      "grad_norm": 0.33045539259910583,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.7292,
+      "step": 32
+    },
+    {
+      "epoch": 0.6649874055415617,
+      "grad_norm": 0.34876877069473267,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.7245,
+      "step": 33
+    },
+    {
+      "epoch": 0.6851385390428212,
+      "grad_norm": 0.3831596076488495,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.7261,
+      "step": 34
+    },
+    {
+      "epoch": 0.7052896725440806,
+      "grad_norm": 0.42519307136535645,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.72,
+      "step": 35
+    },
+    {
+      "epoch": 0.72544080604534,
+      "grad_norm": 0.5558383464813232,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7175,
+      "step": 36
+    },
+    {
+      "epoch": 0.7455919395465995,
+      "grad_norm": 0.6615725755691528,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.7201,
+      "step": 37
+    },
+    {
+      "epoch": 0.7657430730478589,
+      "grad_norm": 0.2927505671977997,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.7276,
+      "step": 38
+    },
+    {
+      "epoch": 0.7858942065491183,
+      "grad_norm": 0.30705034732818604,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7277,
+      "step": 39
+    },
+    {
+      "epoch": 0.8060453400503779,
+      "grad_norm": 0.3004220724105835,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7239,
+      "step": 40
+    },
+    {
+      "epoch": 0.8261964735516373,
+      "grad_norm": 0.3230566680431366,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.7258,
+      "step": 41
+    },
+    {
+      "epoch": 0.8463476070528967,
+      "grad_norm": 0.33532920479774475,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7218,
+      "step": 42
+    },
+    {
+      "epoch": 0.8664987405541562,
+      "grad_norm": 0.33905598521232605,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.7208,
+      "step": 43
+    },
+    {
+      "epoch": 0.8866498740554156,
+      "grad_norm": 0.3514050245285034,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.7215,
+      "step": 44
+    },
+    {
+      "epoch": 0.906801007556675,
+      "grad_norm": 0.3620823621749878,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.7219,
+      "step": 45
+    },
+    {
+      "epoch": 0.9269521410579346,
+      "grad_norm": 0.41333243250846863,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7201,
+      "step": 46
+    },
+    {
+      "epoch": 0.947103274559194,
+      "grad_norm": 0.44582945108413696,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.7167,
+      "step": 47
+    },
+    {
+      "epoch": 0.9672544080604534,
+      "grad_norm": 0.5057469010353088,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7142,
+      "step": 48
+    },
+    {
+      "epoch": 0.9874055415617129,
+      "grad_norm": 0.7562864422798157,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.7146,
+      "step": 49
+    },
+    {
+      "epoch": 1.0113350125944585,
+      "grad_norm": 0.5126062631607056,
+      "learning_rate": 1e-05,
+      "loss": 18.5015,
+      "step": 50
+    },
+    {
+      "epoch": 1.0113350125944585,
+      "eval_loss": 11.714941024780273,
+      "eval_runtime": 0.2407,
+      "eval_samples_per_second": 207.712,
+      "eval_steps_per_second": 54.005,
+      "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": 81943068672000.0,
+  "total_flos": 163886137344000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null