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:e53aac5e53f954bc0960c59ee22170f8ef35fed6aa8965c2713fd944ad0588b0
+oid sha256:be59025c968c972d71ceb98d622a12da2635ff338c1e8257745c173aca947c9a
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6dd289cb460189c6ae4c6cb4e6fb5a2725db51af17722edd7137599c544b9bd
+oid sha256:fb2d3c8091fbc73a01195fb2f8d791d86ec944622672eac6977ef2e3588b65f2
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f82517a071c3b19d2dc0d271e12225bcddf452db6e335b28f02382dec155c72
+oid sha256:d2b4461e6b476ae735475514b3c5d463b3ba5109eef7a03fd5cd01018d73b01d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410e6a8d0b74ef5ecdcdd7473372d77bffddf3f1144c5886c480b38471eff35e
+oid sha256:e7265f470e4dca972edebde25dae8be406f2556fff107a4079f8f650246adca8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7420f25a76aa68d247f2848f373000f473d6c6da346348ec294d975968a2179
+oid sha256:9f5b310e599e59a68a88392f26075322550364ee320f684cf41db29c6601293b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b341d7cc1ed6f23ab94ec058a40e4d76b7f1043b3fa37eef385cdc337fa46642
+oid sha256:b05ad71afcc8fba42ab7e988e081761866a11274085733f228c018c09087afb9
 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": 4.068567795911804e-05,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.441257584114727,
+  "epoch": 0.882515168229454,
   "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": 88.158,
       "eval_steps_per_second": 22.921,
       "step": 25
+    },
+    {
+      "epoch": 0.45890788747931605,
+      "grad_norm": 0.0008449350716546178,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.4765581908439051,
+      "grad_norm": 0.0008811301086097956,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.4942084942084942,
+      "grad_norm": 0.0009417127585038543,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.5118587975730833,
+      "grad_norm": 0.0010093341115862131,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.5295091009376723,
+      "grad_norm": 0.001085045631043613,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.5471594043022614,
+      "grad_norm": 0.0011195273837074637,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.5648097076668506,
+      "grad_norm": 0.001229833927936852,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.5824600110314396,
+      "grad_norm": 0.0019689970649778843,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.6001103143960287,
+      "grad_norm": 0.019161324948072433,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.6177606177606177,
+      "grad_norm": 0.04453014209866524,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0001,
+      "step": 35
+    },
+    {
+      "epoch": 0.6354109211252068,
+      "grad_norm": 1.2612073421478271,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0019,
+      "step": 36
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.002591792494058609,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0001,
+      "step": 37
+    },
+    {
+      "epoch": 0.670711527854385,
+      "grad_norm": 0.0017153579974547029,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.6883618312189741,
+      "grad_norm": 0.0007801396423019469,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.7060121345835632,
+      "grad_norm": 0.0008483222918584943,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.7236624379481522,
+      "grad_norm": 0.0008646952919661999,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.7413127413127413,
+      "grad_norm": 0.0009732348844408989,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.7589630446773304,
+      "grad_norm": 0.0009822549764066935,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.7766133480419195,
+      "grad_norm": 0.0009263743413612247,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.7942636514065086,
+      "grad_norm": 0.0009933272376656532,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.8119139547710976,
+      "grad_norm": 0.0011112219654023647,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.8295642581356867,
+      "grad_norm": 0.001772879739291966,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.8472145615002757,
+      "grad_norm": 0.004433015361428261,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.009279930032789707,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0001,
+      "step": 49
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 0.008922255598008633,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 4.58928661828395e-05,
+      "eval_runtime": 0.5848,
+      "eval_samples_per_second": 85.493,
+      "eval_steps_per_second": 22.228,
+      "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": 1.476965970214912e+16,
+  "total_flos": 2.953470533435392e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null