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:cca31f57cc1cc6837956a5085dcecb1a8107acedcdeefd2fd9319c7ef57352d4
+oid sha256:ed4ec9e2291c801ef98d9360cc6206aa3075bab39c39595c6ce0aba814f6565b
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0f93d21720a7d9c28c152138dcb7880887f778736b27736a3c047684eae40f
+oid sha256:e3dabc6ceff078140b4459dc312b31976eba1c0c853a3b6c4a738d122dbe17d5
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:853601b1d775a876d0fb0b491e9e5a68bf43d1a9507b2aad09c66ae7c70ef2b6
+oid sha256:af04e08e383367a11516f22b7c639451e4a06dd3a071f2b5b8476a664a57493e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebcb53d7232e132a8ee441f203f1c4d7d8cfc473f6c0028742f98dcb223c3da9
+oid sha256:9ac5f656e63158f1fd557bfb097501153cdd39464776a3d87635eb69b198d25d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a32ed513dde31d93722908578f1881d698a4f5d6c5aeaaee53a93368f1e480
+oid sha256:396f14416e0abf32a7767f6548a82284006238607cf28edb5497eaaaee22f158
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523a10915adacc9126c6ed2bc95f0aad9edcff0c4362399ea6e30a433e2213d8
+oid sha256:27810978b624149cb4afab27826b5b1dc6c9e355eb6c7b014348b25fec5572e0
 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": 7.274782180786133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.061274509803921566,
+  "best_metric": 7.173201084136963,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12254901960784313,
   "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": 140.38,
       "eval_steps_per_second": 36.499,
       "step": 25
+    },
+    {
+      "epoch": 0.06372549019607843,
+      "grad_norm": 2.4334850311279297,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 7.5853,
+      "step": 26
+    },
+    {
+      "epoch": 0.0661764705882353,
+      "grad_norm": 1.9980462789535522,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 7.6894,
+      "step": 27
+    },
+    {
+      "epoch": 0.06862745098039216,
+      "grad_norm": 1.1127245426177979,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 7.4654,
+      "step": 28
+    },
+    {
+      "epoch": 0.07107843137254902,
+      "grad_norm": 1.1269689798355103,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 7.516,
+      "step": 29
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 0.969700813293457,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 7.3744,
+      "step": 30
+    },
+    {
+      "epoch": 0.07598039215686274,
+      "grad_norm": 0.9497419595718384,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 7.33,
+      "step": 31
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 0.9529443979263306,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 7.2131,
+      "step": 32
+    },
+    {
+      "epoch": 0.08088235294117647,
+      "grad_norm": 0.9932823181152344,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 7.0009,
+      "step": 33
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.9452614784240723,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.7679,
+      "step": 34
+    },
+    {
+      "epoch": 0.0857843137254902,
+      "grad_norm": 0.9876568913459778,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.7409,
+      "step": 35
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 0.9435369372367859,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.7302,
+      "step": 36
+    },
+    {
+      "epoch": 0.09068627450980392,
+      "grad_norm": 1.037487506866455,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.665,
+      "step": 37
+    },
+    {
+      "epoch": 0.09313725490196079,
+      "grad_norm": 1.9251594543457031,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 7.3112,
+      "step": 38
+    },
+    {
+      "epoch": 0.09558823529411764,
+      "grad_norm": 2.173351526260376,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 7.5422,
+      "step": 39
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 1.453737497329712,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 7.2394,
+      "step": 40
+    },
+    {
+      "epoch": 0.10049019607843138,
+      "grad_norm": 1.0192174911499023,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 7.4375,
+      "step": 41
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 1.0053462982177734,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 7.3853,
+      "step": 42
+    },
+    {
+      "epoch": 0.1053921568627451,
+      "grad_norm": 1.0146454572677612,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 7.2052,
+      "step": 43
+    },
+    {
+      "epoch": 0.10784313725490197,
+      "grad_norm": 0.9978232979774475,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 7.1877,
+      "step": 44
+    },
+    {
+      "epoch": 0.11029411764705882,
+      "grad_norm": 0.906777024269104,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 7.0487,
+      "step": 45
+    },
+    {
+      "epoch": 0.11274509803921569,
+      "grad_norm": 0.9139236211776733,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 7.0347,
+      "step": 46
+    },
+    {
+      "epoch": 0.11519607843137254,
+      "grad_norm": 0.8226746320724487,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.9112,
+      "step": 47
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.8334608674049377,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.8026,
+      "step": 48
+    },
+    {
+      "epoch": 0.12009803921568628,
+      "grad_norm": 0.9400653839111328,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.6872,
+      "step": 49
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "grad_norm": 1.1902639865875244,
+      "learning_rate": 1e-05,
+      "loss": 6.3615,
+      "step": 50
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "eval_loss": 7.173201084136963,
+      "eval_runtime": 0.3489,
+      "eval_samples_per_second": 143.317,
+      "eval_steps_per_second": 37.263,
+      "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": 119197088612352.0,
+  "total_flos": 238684194471936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null