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:e1fb1676c2693577869c4ad45b16e461cb9b1c3c5db208d39fca60735d151dbc
+oid sha256:5a35696fd80254447112c400af132eb418b733403d5edcb415583952956e5acf
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f107c58afd4362e412144ae1dd6b97092d038ead9b693057b1ccfe1a818143
+oid sha256:b04bd1796f2bcb03adb6b9a54203793774726beb7f3fbed4368a5a09bd85ada6
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad2833fbb1ad4aecc88b01f4f976b175492890e1c170425f2fbcd8e7171ca4f
+oid sha256:24366d0f29c989f31a0dab77bc11a51e1f7b8fef5da01a4053eda702447e24ab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72562cef5d926b619e47695d12d1656ecc509d47b15f329da9568177bbe56a16
+oid sha256:56286a49f6468ed0bc3196c5bf91fe69c27aef7ce8b7fcf995de332be078e533
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5113a80bbc27c0566ef9f6d20e337ee2ba08b8e69546c76aa2057419e0b6a1f1
+oid sha256:ce7941ad040128a012ec3d61c8411e8cd3e6783db16f0fd10d4d6210475199ee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def2bd81424f70ae22cf53e48c6f077963bc659a6829cc2bc897274f0ced0177
+oid sha256:f94b52228f6f8095bfae241ae3a3d435c76ec1ef264880534cb7375aacdf43d1
 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": 0.19338418543338776,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.28198801550934083,
+  "best_metric": 0.09648923575878143,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5639760310186817,
   "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": 26.118,
       "eval_steps_per_second": 6.791,
       "step": 25
+    },
+    {
+      "epoch": 0.2932675361297145,
+      "grad_norm": 2.5036373138427734,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7331,
+      "step": 26
+    },
+    {
+      "epoch": 0.30454705675008814,
+      "grad_norm": 0.009689477272331715,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0001,
+      "step": 27
+    },
+    {
+      "epoch": 0.31582657737046177,
+      "grad_norm": 0.0014077340019866824,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.3271060979908354,
+      "grad_norm": 0.03966264799237251,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0002,
+      "step": 29
+    },
+    {
+      "epoch": 0.338385618611209,
+      "grad_norm": 0.08873093873262405,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0007,
+      "step": 30
+    },
+    {
+      "epoch": 0.34966513923158266,
+      "grad_norm": 0.09382674843072891,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0009,
+      "step": 31
+    },
+    {
+      "epoch": 0.3609446598519563,
+      "grad_norm": 0.04602659121155739,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0003,
+      "step": 32
+    },
+    {
+      "epoch": 0.3722241804723299,
+      "grad_norm": 0.29243648052215576,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0044,
+      "step": 33
+    },
+    {
+      "epoch": 0.38350370109270354,
+      "grad_norm": 0.16613152623176575,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0022,
+      "step": 34
+    },
+    {
+      "epoch": 0.39478322171307717,
+      "grad_norm": 0.043631184846162796,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0005,
+      "step": 35
+    },
+    {
+      "epoch": 0.40606274233345085,
+      "grad_norm": 0.002960504963994026,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.4173422629538245,
+      "grad_norm": 0.005832310300320387,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0001,
+      "step": 37
+    },
+    {
+      "epoch": 0.4286217835741981,
+      "grad_norm": 3.135204553604126,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8,
+      "step": 38
+    },
+    {
+      "epoch": 0.43990130419457174,
+      "grad_norm": 0.005184840876609087,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0001,
+      "step": 39
+    },
+    {
+      "epoch": 0.45118082481494537,
+      "grad_norm": 0.00458234827965498,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.462460345435319,
+      "grad_norm": 0.030586376786231995,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0004,
+      "step": 41
+    },
+    {
+      "epoch": 0.4737398660556926,
+      "grad_norm": 0.01800384186208248,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0002,
+      "step": 42
+    },
+    {
+      "epoch": 0.48501938667606626,
+      "grad_norm": 0.009339077398180962,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0002,
+      "step": 43
+    },
+    {
+      "epoch": 0.4962989072964399,
+      "grad_norm": 0.018710706382989883,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0003,
+      "step": 44
+    },
+    {
+      "epoch": 0.5075784279168135,
+      "grad_norm": 0.008345427922904491,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.5188579485371871,
+      "grad_norm": 0.1667875349521637,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0116,
+      "step": 46
+    },
+    {
+      "epoch": 0.5301374691575608,
+      "grad_norm": 0.031969476491212845,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0004,
+      "step": 47
+    },
+    {
+      "epoch": 0.5414169897779344,
+      "grad_norm": 0.006944997701793909,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.552696510398308,
+      "grad_norm": 0.006165571045130491,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0001,
+      "step": 49
+    },
+    {
+      "epoch": 0.5639760310186817,
+      "grad_norm": 0.005968439858406782,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 0.5639760310186817,
+      "eval_loss": 0.09648923575878143,
+      "eval_runtime": 1.9841,
+      "eval_samples_per_second": 25.2,
+      "eval_steps_per_second": 6.552,
+      "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": 5.403635418241434e+16,
+  "total_flos": 1.082548160519209e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null