Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bfa79e921bfbb2cd9bbdbfb8d7679b0ee39a79ce4ca28dc5255828f59a95eda
+oid sha256:e816b461b2543d773351f0fd195002153e8992e2087a8bb88888fc3f328aef83
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37578db6a65332470901fd7b88d36befa16c9b9a54752fb56d7d6e5cd1f12403
+oid sha256:35aaeca0d8467b2187165c2bd99387e3b86052b14d2fbf893b66cd4c9844f9ee
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d974d8e5b4aa9cae9ae0cf1deea4ea37d35a52a0e3716f2c1a1f6328819880
+oid sha256:dd8f93b1b04cf4dfc5ecf277aa74cca69e707f80b83bd825a34275dcd0f8781a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2dd24d20c1d5a9e717e2ea159cc3bd87778b670925001f237f3e1345203a0e2
+oid sha256:0a05f80b3dc6426a18dbd8a0a5f366ddcb59cdc2b271aa856999b7bcd38ac209
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fe8a263129c498b4d6b77613b15f1041b97aae86f89f00ebc3e5de30faabbe
+oid sha256:9123b9b845fee54265c954a324a57ba5d898f5a8695ff4c1725647dc616cfe3e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f833d7b54d297127c8c701e39b231352aa2ae45e3c80a6064b51ed5b7e0c17
+oid sha256:f9dc2850a21c06d1afec19dba07f8abbfe17d77e82b5aee3a1277bc433b1db45
 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": 11.0306396484375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.061274509803921566,
+  "best_metric": 10.99184799194336,
+  "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": 541.767,
       "eval_steps_per_second": 140.859,
       "step": 25
+    },
+    {
+      "epoch": 0.06372549019607843,
+      "grad_norm": 5.44142484664917,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 187.5009,
+      "step": 26
+    },
+    {
+      "epoch": 0.0661764705882353,
+      "grad_norm": 4.920271873474121,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 176.5958,
+      "step": 27
+    },
+    {
+      "epoch": 0.06862745098039216,
+      "grad_norm": 5.284728050231934,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 176.5206,
+      "step": 28
+    },
+    {
+      "epoch": 0.07107843137254902,
+      "grad_norm": 5.332001686096191,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 176.4909,
+      "step": 29
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 5.19172477722168,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 176.4136,
+      "step": 30
+    },
+    {
+      "epoch": 0.07598039215686274,
+      "grad_norm": 5.826201438903809,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 176.1769,
+      "step": 31
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 5.31245756149292,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 176.325,
+      "step": 32
+    },
+    {
+      "epoch": 0.08088235294117647,
+      "grad_norm": 5.744202136993408,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 176.1636,
+      "step": 33
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 5.508240222930908,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 176.1452,
+      "step": 34
+    },
+    {
+      "epoch": 0.0857843137254902,
+      "grad_norm": 5.379641532897949,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 176.256,
+      "step": 35
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 5.405764579772949,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 176.2521,
+      "step": 36
+    },
+    {
+      "epoch": 0.09068627450980392,
+      "grad_norm": 5.883171558380127,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 176.2494,
+      "step": 37
+    },
+    {
+      "epoch": 0.09313725490196079,
+      "grad_norm": 5.785599231719971,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 176.2912,
+      "step": 38
+    },
+    {
+      "epoch": 0.09558823529411764,
+      "grad_norm": 5.51578426361084,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 176.0724,
+      "step": 39
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 5.5537285804748535,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 176.0884,
+      "step": 40
+    },
+    {
+      "epoch": 0.10049019607843138,
+      "grad_norm": 5.462303161621094,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 176.0427,
+      "step": 41
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 5.737156867980957,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 175.98,
+      "step": 42
+    },
+    {
+      "epoch": 0.1053921568627451,
+      "grad_norm": 5.694828987121582,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 175.9308,
+      "step": 43
+    },
+    {
+      "epoch": 0.10784313725490197,
+      "grad_norm": 6.074409484863281,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 175.8056,
+      "step": 44
+    },
+    {
+      "epoch": 0.11029411764705882,
+      "grad_norm": 5.782948970794678,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 175.8875,
+      "step": 45
+    },
+    {
+      "epoch": 0.11274509803921569,
+      "grad_norm": 6.181939125061035,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 175.8657,
+      "step": 46
+    },
+    {
+      "epoch": 0.11519607843137254,
+      "grad_norm": 5.735159873962402,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 175.8872,
+      "step": 47
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 5.784780025482178,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 175.9216,
+      "step": 48
+    },
+    {
+      "epoch": 0.12009803921568628,
+      "grad_norm": 5.5713701248168945,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 176.1538,
+      "step": 49
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "grad_norm": 6.3290205001831055,
+      "learning_rate": 1e-05,
+      "loss": 176.2121,
+      "step": 50
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "eval_loss": 10.99184799194336,
+      "eval_runtime": 0.0933,
+      "eval_samples_per_second": 535.863,
+      "eval_steps_per_second": 139.324,
+      "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": 19484312076288.0,
+  "total_flos": 38992443604992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null