Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8bdd240635e6d702e91c24fa1cc2fb7789d173dfa652646bdc170f91ce31cd
+oid sha256:951f6e4ab23949f91b8f2487faee2929460a3205dd251830be65ce842c7c3f96
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766ca4c79762cbe9073aa4eae426cb2da08626f03f23ae6f59cc22f5c65d0b68
+oid sha256:7dfd4469c0d8ae3d5d273311d14dd443c84fe7cbb3ec1f6fbec0caeb14b48f27
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e618610556c457baa244b7459ed2a9d4650ecd586a95f954bf24ff8af916b6a8
+oid sha256:64851e9c36129f8625864b7ce099491fd923dc30e4bb4ff01147957b2db14c10
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6539dacbbf98820267496a523cad83f28ce38fa2fcd81f089e53c1b320328a
+oid sha256:b15f02a63e6695d31fe374761251eafc98dc5022b10dedf665787a6d94b0f855
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063be0b7105f22892e4a855a96cf265c30364f7acb349c9d7ee55393b0711f62
+oid sha256:793dc0326a00c18a538aed955ee6b5bf471565ce5cae82bb7e60849c68770afe
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eaea9939deb0f93d6966d23bd745e2ed92592021905ec64fa280028161fbe58
+oid sha256:b169aed396efaa4fabf11b4c1cbc94d36e4c4294a496eef60e8331d4a71b6989
 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": 0.3589280843734741,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4492753623188406,
+  "best_metric": 0.3467337489128113,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.898550724637681,
   "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": 33.429,
       "eval_steps_per_second": 8.692,
       "step": 25
+    },
+    {
+      "epoch": 1.5072463768115942,
+      "grad_norm": 2.520402193069458,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3542,
+      "step": 26
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 3.979710817337036,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3476,
+      "step": 27
+    },
+    {
+      "epoch": 1.6231884057971016,
+      "grad_norm": 8.150418281555176,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4011,
+      "step": 28
+    },
+    {
+      "epoch": 1.681159420289855,
+      "grad_norm": 10.581029891967773,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4766,
+      "step": 29
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 8.106186866760254,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4171,
+      "step": 30
+    },
+    {
+      "epoch": 1.7971014492753623,
+      "grad_norm": 7.351648807525635,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4171,
+      "step": 31
+    },
+    {
+      "epoch": 1.855072463768116,
+      "grad_norm": 3.3254544734954834,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.3602,
+      "step": 32
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 1.1282237768173218,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3508,
+      "step": 33
+    },
+    {
+      "epoch": 1.971014492753623,
+      "grad_norm": 5.488137722015381,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3692,
+      "step": 34
+    },
+    {
+      "epoch": 2.028985507246377,
+      "grad_norm": 2.6220922470092773,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6257,
+      "step": 35
+    },
+    {
+      "epoch": 2.0869565217391304,
+      "grad_norm": 1.9235265254974365,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3561,
+      "step": 36
+    },
+    {
+      "epoch": 2.1449275362318843,
+      "grad_norm": 4.844725131988525,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3788,
+      "step": 37
+    },
+    {
+      "epoch": 2.2028985507246377,
+      "grad_norm": 1.5539034605026245,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3518,
+      "step": 38
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": 1.0556237697601318,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3472,
+      "step": 39
+    },
+    {
+      "epoch": 2.318840579710145,
+      "grad_norm": 3.2514402866363525,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.361,
+      "step": 40
+    },
+    {
+      "epoch": 2.3768115942028984,
+      "grad_norm": 2.6063075065612793,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3559,
+      "step": 41
+    },
+    {
+      "epoch": 2.4347826086956523,
+      "grad_norm": 1.3320070505142212,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3494,
+      "step": 42
+    },
+    {
+      "epoch": 2.4927536231884058,
+      "grad_norm": 0.5125684142112732,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3484,
+      "step": 43
+    },
+    {
+      "epoch": 2.550724637681159,
+      "grad_norm": 3.3589301109313965,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3541,
+      "step": 44
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 3.3061909675598145,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3586,
+      "step": 45
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.8526839017868042,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3508,
+      "step": 46
+    },
+    {
+      "epoch": 2.7246376811594204,
+      "grad_norm": 0.8163145184516907,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3483,
+      "step": 47
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 2.721081256866455,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3602,
+      "step": 48
+    },
+    {
+      "epoch": 2.8405797101449277,
+      "grad_norm": 1.758621096611023,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.345,
+      "step": 49
+    },
+    {
+      "epoch": 2.898550724637681,
+      "grad_norm": 2.4154114723205566,
+      "learning_rate": 1e-05,
+      "loss": 0.3493,
+      "step": 50
+    },
+    {
+      "epoch": 2.898550724637681,
+      "eval_loss": 0.3467337489128113,
+      "eval_runtime": 1.4944,
+      "eval_samples_per_second": 33.458,
+      "eval_steps_per_second": 8.699,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null