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:c6bcc09b5b3e9e916ec3b819021d0a1fce68b961999f6de17f16f1b7bf8a0159
+oid sha256:5ce83b042e9864ab7d94f5fdda79255f2581cc7a73391e35c41333a71cade2d0
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2fc797976b246cea31c54afa6d75d898a7cdc66c01d13af2c49cd16cc74323
+oid sha256:290a891a6691d8b6040a69e5b80b53131d74a68fa958b580c3d1161d919f3781
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b781c8d37a334146c833418a6ac512c73490780c327db4f3e10f03a37acca721
+oid sha256:6ab988d03d242cc0edcbb3e2deef4f6dbdd9d33ed7e6fa89e75a7bf174abd58a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba929c6bbc91332437f4ee9b32b031bf60d457a810cc87c9c6d579f2977aa6a
+oid sha256:eaee71ad656acbea348ea75680aad8a16884301b2ca8ebd678971949311b7bcd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f672c58f1d0716c2eb9626ce17e24f888967f082785d351da04bca711b576aa
+oid sha256:7489090adde32ee7a6ba2d726ee44ff870e015804f7ef4c6a01711dd2aeac74e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487a7ffcec2deb7ee2a5ee6f3422705ee5d55e16bac74b82a5ad1b63905e38bb
+oid sha256:7972881429cb4a28e648e57e86ca2683079875ed93ea401b04157dd465665b04
 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": 3.1355321407318115,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01613228473482557,
+  "best_metric": 3.096146821975708,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03226456946965114,
   "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": 25.516,
       "eval_steps_per_second": 6.634,
       "step": 25
+    },
+    {
+      "epoch": 0.016777576124218593,
+      "grad_norm": 0.24698567390441895,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.0764,
+      "step": 26
+    },
+    {
+      "epoch": 0.017422867513611617,
+      "grad_norm": 0.24421782791614532,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.0893,
+      "step": 27
+    },
+    {
+      "epoch": 0.018068158903004637,
+      "grad_norm": 0.28326475620269775,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.1001,
+      "step": 28
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 0.308344304561615,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.0855,
+      "step": 29
+    },
+    {
+      "epoch": 0.019358741681790685,
+      "grad_norm": 0.3393581807613373,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0941,
+      "step": 30
+    },
+    {
+      "epoch": 0.020004033071183706,
+      "grad_norm": 0.36885160207748413,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.1291,
+      "step": 31
+    },
+    {
+      "epoch": 0.02064932446057673,
+      "grad_norm": 0.40527042746543884,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.1255,
+      "step": 32
+    },
+    {
+      "epoch": 0.021294615849969754,
+      "grad_norm": 0.39910948276519775,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.1406,
+      "step": 33
+    },
+    {
+      "epoch": 0.021939907239362774,
+      "grad_norm": 0.5128020644187927,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.2373,
+      "step": 34
+    },
+    {
+      "epoch": 0.022585198628755798,
+      "grad_norm": 0.5385227203369141,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.3137,
+      "step": 35
+    },
+    {
+      "epoch": 0.02323049001814882,
+      "grad_norm": 0.4920327663421631,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.3304,
+      "step": 36
+    },
+    {
+      "epoch": 0.023875781407541843,
+      "grad_norm": 0.927702009677887,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.3799,
+      "step": 37
+    },
+    {
+      "epoch": 0.024521072796934867,
+      "grad_norm": 0.3272736668586731,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.1169,
+      "step": 38
+    },
+    {
+      "epoch": 0.025166364186327887,
+      "grad_norm": 0.4105949401855469,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.1145,
+      "step": 39
+    },
+    {
+      "epoch": 0.02581165557572091,
+      "grad_norm": 0.4404626786708832,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.0417,
+      "step": 40
+    },
+    {
+      "epoch": 0.026456946965113935,
+      "grad_norm": 0.4399726390838623,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.0397,
+      "step": 41
+    },
+    {
+      "epoch": 0.027102238354506956,
+      "grad_norm": 0.39927875995635986,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.0521,
+      "step": 42
+    },
+    {
+      "epoch": 0.02774752974389998,
+      "grad_norm": 0.4015970528125763,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.0857,
+      "step": 43
+    },
+    {
+      "epoch": 0.028392821133293004,
+      "grad_norm": 0.3402881324291229,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.115,
+      "step": 44
+    },
+    {
+      "epoch": 0.029038112522686024,
+      "grad_norm": 0.330485999584198,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.0711,
+      "step": 45
+    },
+    {
+      "epoch": 0.02968340391207905,
+      "grad_norm": 0.3675265610218048,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.1623,
+      "step": 46
+    },
+    {
+      "epoch": 0.030328695301472072,
+      "grad_norm": 0.5795705318450928,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.3602,
+      "step": 47
+    },
+    {
+      "epoch": 0.030973986690865093,
+      "grad_norm": 0.5248962044715881,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.3047,
+      "step": 48
+    },
+    {
+      "epoch": 0.03161927808025811,
+      "grad_norm": 1.0681005716323853,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.3858,
+      "step": 49
+    },
+    {
+      "epoch": 0.03226456946965114,
+      "grad_norm": 1.1730180978775024,
+      "learning_rate": 1e-05,
+      "loss": 3.455,
+      "step": 50
+    },
+    {
+      "epoch": 0.03226456946965114,
+      "eval_loss": 3.096146821975708,
+      "eval_runtime": 1.9568,
+      "eval_samples_per_second": 25.552,
+      "eval_steps_per_second": 6.644,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null