Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057f7e5cd0c2d628d657e16bc352faa48916def65188a5152fbaa1429a97f7c6
+oid sha256:99b80b93b2ba64ba48c12efc737c3a2b030f843a649701512bfe8cdf877b8144
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74fe8c8fda6bdd662d1abca1c9355e02cc89ee369316901751e2e42b0e401417
+oid sha256:03d9cf50e1a9504c55fd2e86ea1a1e80ff687fd3ff14faca8276e84f6c833d48
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b04bdfd79d84239f3e557c988a56cceac113ced60c914ea287bcc8bcb6b4e5c
+oid sha256:60b784d950e6a10d6a604174b4cccce1e6683055119eef214b8eccd3ce3c79fc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bb130d34ca43045c38ca96cbe7149c1ec6ec999a9ea267a50983529254b771
+oid sha256:ba484a3ce5e501cc0d9886cca2e2c5d31c4834b806bd2c9f759b5ba0fb1af0ba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab8185e4b51ef7d817b68136f55aee895f466b351c79aad53359a619c116c8df
+oid sha256:7a19948d42ae4c44a9135a35de3dadc1799db967fd13b9283006ceb40db45de3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91766ccc5e0c5baac210294f191096742c74848dd456ca801c900e04f5a02c31
+oid sha256:ee72b8ea0f96bcf393682310dfae14074c35532ba15f14267fc384c83bc4aace
 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": 0.4834555685520172,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09066183136899365,
+  "best_metric": 0.4731850028038025,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1813236627379873,
   "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": 24.684,
       "eval_steps_per_second": 6.418,
       "step": 25
+    },
+    {
+      "epoch": 0.0942883046237534,
+      "grad_norm": 0.10247881710529327,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5168,
+      "step": 26
+    },
+    {
+      "epoch": 0.09791477787851315,
+      "grad_norm": 0.11820855736732483,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.551,
+      "step": 27
+    },
+    {
+      "epoch": 0.10154125113327289,
+      "grad_norm": 0.11400573700666428,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5089,
+      "step": 28
+    },
+    {
+      "epoch": 0.10516772438803264,
+      "grad_norm": 0.1190500557422638,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5123,
+      "step": 29
+    },
+    {
+      "epoch": 0.10879419764279238,
+      "grad_norm": 0.12067992240190506,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5113,
+      "step": 30
+    },
+    {
+      "epoch": 0.11242067089755213,
+      "grad_norm": 0.12420016527175903,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5039,
+      "step": 31
+    },
+    {
+      "epoch": 0.11604714415231188,
+      "grad_norm": 0.12639960646629333,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.4742,
+      "step": 32
+    },
+    {
+      "epoch": 0.11967361740707162,
+      "grad_norm": 0.12689970433712006,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4927,
+      "step": 33
+    },
+    {
+      "epoch": 0.12330009066183137,
+      "grad_norm": 0.1331597864627838,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5117,
+      "step": 34
+    },
+    {
+      "epoch": 0.12692656391659113,
+      "grad_norm": 0.13654395937919617,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5115,
+      "step": 35
+    },
+    {
+      "epoch": 0.13055303717135086,
+      "grad_norm": 0.14279140532016754,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5082,
+      "step": 36
+    },
+    {
+      "epoch": 0.13417951042611062,
+      "grad_norm": 0.16443079710006714,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.492,
+      "step": 37
+    },
+    {
+      "epoch": 0.13780598368087035,
+      "grad_norm": 0.11059442907571793,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5043,
+      "step": 38
+    },
+    {
+      "epoch": 0.1414324569356301,
+      "grad_norm": 0.10864920914173126,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.5052,
+      "step": 39
+    },
+    {
+      "epoch": 0.14505893019038985,
+      "grad_norm": 0.10561143606901169,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5122,
+      "step": 40
+    },
+    {
+      "epoch": 0.1486854034451496,
+      "grad_norm": 0.11367624253034592,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4875,
+      "step": 41
+    },
+    {
+      "epoch": 0.15231187669990934,
+      "grad_norm": 0.11491914838552475,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5187,
+      "step": 42
+    },
+    {
+      "epoch": 0.1559383499546691,
+      "grad_norm": 0.11767067015171051,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5232,
+      "step": 43
+    },
+    {
+      "epoch": 0.15956482320942883,
+      "grad_norm": 0.12322618812322617,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5039,
+      "step": 44
+    },
+    {
+      "epoch": 0.1631912964641886,
+      "grad_norm": 0.13600581884384155,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.5255,
+      "step": 45
+    },
+    {
+      "epoch": 0.16681776971894832,
+      "grad_norm": 0.12546585500240326,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.505,
+      "step": 46
+    },
+    {
+      "epoch": 0.17044424297370808,
+      "grad_norm": 0.15670840442180634,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5126,
+      "step": 47
+    },
+    {
+      "epoch": 0.17407071622846781,
+      "grad_norm": 0.13949869573116302,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5064,
+      "step": 48
+    },
+    {
+      "epoch": 0.17769718948322757,
+      "grad_norm": 0.13772359490394592,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4811,
+      "step": 49
+    },
+    {
+      "epoch": 0.1813236627379873,
+      "grad_norm": 0.1660703420639038,
+      "learning_rate": 1e-05,
+      "loss": 0.5298,
+      "step": 50
+    },
+    {
+      "epoch": 0.1813236627379873,
+      "eval_loss": 0.4731850028038025,
+      "eval_runtime": 2.0393,
+      "eval_samples_per_second": 24.518,
+      "eval_steps_per_second": 6.375,
+      "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": 2.991501909153546e+17,
+  "total_flos": 5.981138793183314e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null