Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6909601fb1b7c1a75b5de25c1d33836eb3b09b919557b3a5a43dc0f3bd6e26bc
+oid sha256:1943e60f1e98e4fa9639f0feb9aec32fddb30abd1414a8d77e96b0fa897e2d4e
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a6d8360de8b13bd7f5af225d07e82bfd170211a119894ed44d36c8dfbd9b39
+oid sha256:754e2f077af90d8fcde36a92f7a567767e37c8e49ba58d5561809f278cd82c7b
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d069854adf6f8c64d237a97cab9bc2f661d3965c931b035054203309642fd6e2
+oid sha256:54532bada871805483c2ea35d983981142f78f0330c768fabeaf4de012cb9c83
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf8eb973ada744b6f4db3d1088729258e18d872e9d8d1a15924f3e5b4ea4a190
+oid sha256:c485262a039ef780cae6ff00f494a67b3cf07ac9504cc2b0bbb6da0d2e6dbbf7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620b2d7357ae5851c3ea38085d59faf8ae0bbf0a34d1ae3b0d913f9c0f19c2c2
+oid sha256:63a30bbf08638b33d9aa7e5b58916f6d22289a467c3dab8efc094a189cac5d79
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1890b49e29aba3e6e303af7110e34c10f01bd29ef462a4cf7d6f3a08f702223f
+oid sha256:99c4d5ea5f4313571d4af345167e8967f18d34ecb12e19254dff64ed7025374b
 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": 0.8075627684593201,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02629935237844768,
+  "epoch": 0.05259870475689536,
   "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": 24.06,
       "eval_steps_per_second": 6.256,
       "step": 25
+    },
+    {
+      "epoch": 0.02735132647358559,
+      "grad_norm": 1.6255582571029663,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8066,
+      "step": 26
+    },
+    {
+      "epoch": 0.028403300568723495,
+      "grad_norm": 0.809135377407074,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.8051,
+      "step": 27
+    },
+    {
+      "epoch": 0.029455274663861403,
+      "grad_norm": 1.7985752820968628,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8179,
+      "step": 28
+    },
+    {
+      "epoch": 0.03050724875899931,
+      "grad_norm": 1.2974883317947388,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.808,
+      "step": 29
+    },
+    {
+      "epoch": 0.03155922285413722,
+      "grad_norm": 1.3518906831741333,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.8031,
+      "step": 30
+    },
+    {
+      "epoch": 0.032611196949275126,
+      "grad_norm": 1.5183818340301514,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.8073,
+      "step": 31
+    },
+    {
+      "epoch": 0.033663171044413034,
+      "grad_norm": 1.6260573863983154,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8144,
+      "step": 32
+    },
+    {
+      "epoch": 0.034715145139550936,
+      "grad_norm": 2.1896719932556152,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8099,
+      "step": 33
+    },
+    {
+      "epoch": 0.035767119234688845,
+      "grad_norm": 1.9014267921447754,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8069,
+      "step": 34
+    },
+    {
+      "epoch": 0.03681909332982675,
+      "grad_norm": 1.9700180292129517,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.8166,
+      "step": 35
+    },
+    {
+      "epoch": 0.03787106742496466,
+      "grad_norm": 1.4387903213500977,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8091,
+      "step": 36
+    },
+    {
+      "epoch": 0.03892304152010257,
+      "grad_norm": 1.0182123184204102,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8039,
+      "step": 37
+    },
+    {
+      "epoch": 0.03997501561524047,
+      "grad_norm": 1.6459559202194214,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8475,
+      "step": 38
+    },
+    {
+      "epoch": 0.04102698971037838,
+      "grad_norm": 1.9654988050460815,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8169,
+      "step": 39
+    },
+    {
+      "epoch": 0.04207896380551629,
+      "grad_norm": 1.2888116836547852,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.8084,
+      "step": 40
+    },
+    {
+      "epoch": 0.0431309379006542,
+      "grad_norm": 1.0997812747955322,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.794,
+      "step": 41
+    },
+    {
+      "epoch": 0.04418291199579211,
+      "grad_norm": 1.8465800285339355,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8217,
+      "step": 42
+    },
+    {
+      "epoch": 0.04523488609093001,
+      "grad_norm": 1.5212135314941406,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8128,
+      "step": 43
+    },
+    {
+      "epoch": 0.04628686018606792,
+      "grad_norm": 1.6653895378112793,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.8139,
+      "step": 44
+    },
+    {
+      "epoch": 0.047338834281205826,
+      "grad_norm": 1.3936947584152222,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7985,
+      "step": 45
+    },
+    {
+      "epoch": 0.048390808376343734,
+      "grad_norm": 2.1122493743896484,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8154,
+      "step": 46
+    },
+    {
+      "epoch": 0.04944278247148164,
+      "grad_norm": 0.8528788685798645,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8162,
+      "step": 47
+    },
+    {
+      "epoch": 0.050494756566619545,
+      "grad_norm": 1.5338293313980103,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.7937,
+      "step": 48
+    },
+    {
+      "epoch": 0.05154673066175745,
+      "grad_norm": 1.9110890626907349,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8225,
+      "step": 49
+    },
+    {
+      "epoch": 0.05259870475689536,
+      "grad_norm": 1.324634313583374,
+      "learning_rate": 1e-05,
+      "loss": 0.8084,
+      "step": 50
+    },
+    {
+      "epoch": 0.05259870475689536,
+      "eval_loss": 0.8132852911949158,
+      "eval_runtime": 2.0735,
+      "eval_samples_per_second": 24.114,
+      "eval_steps_per_second": 6.27,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.26272811885527e+16,
+  "total_flos": 1.6522972753402266e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null