Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b1c622cd12b90c55172287019ef181c4332a6114488f32bd86b40f9be5e8ea
+oid sha256:705dd5fcaa64b8b68a1e4febae572ebbeaa16d50043da05419c583c6acd3302b
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a65979472be832628979c713c31096a76520f7dd37b27300f4c0c9835ea965d
+oid sha256:62efe57a149f651ed6fb3bda2bc4c9d18b5e2b45527c0151077bfda2aa23b29d
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79df62983deae4765f7042c135e50e041ffc8941ba0a8597c61b474b827b7188
+oid sha256:cc9d1405fd5c198854c6776a5297887ab3399952b3dc702ad0ad257a3906fb36
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ac8840beb7b85abf3938e939b159c1120ca443a0be93aaac8c73b329764510
+oid sha256:ecf9d486c160f555a75d99aeed9b15edad5989578aa47f617f9c603196627bec
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2cd5b4e328e712bfd7f7a5feb637c9edfff5a0d440d157c851e6112cf0afef4
+oid sha256:826afc3c300435fdb0be2b7f38a0170b465d02bf204c24fb55ece633dadee887
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33c0d0290d41cb60946791519a4597ac4fb67d662be33a7165a6437122b4a10
+oid sha256:5278c64e046280f60264e13e6a3526a7a32622e7f6ea46ae53c2631eb3354d02
 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": 11.017281532287598,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.21522733387140167,
+  "best_metric": 10.991680145263672,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.43045466774280333,
   "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": 354.775,
       "eval_steps_per_second": 92.242,
       "step": 25
+    },
+    {
+      "epoch": 0.22383642722625774,
+      "grad_norm": 9.065348625183105,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 353.421,
+      "step": 26
+    },
+    {
+      "epoch": 0.2324455205811138,
+      "grad_norm": 9.961706161499023,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 353.1088,
+      "step": 27
+    },
+    {
+      "epoch": 0.24105461393596986,
+      "grad_norm": 11.364466667175293,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 352.7587,
+      "step": 28
+    },
+    {
+      "epoch": 0.24966370729082593,
+      "grad_norm": 10.180781364440918,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 352.8823,
+      "step": 29
+    },
+    {
+      "epoch": 0.258272800645682,
+      "grad_norm": 10.212959289550781,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 352.8266,
+      "step": 30
+    },
+    {
+      "epoch": 0.2668818940005381,
+      "grad_norm": 9.96835708618164,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 352.8559,
+      "step": 31
+    },
+    {
+      "epoch": 0.2754909873553941,
+      "grad_norm": 10.018963813781738,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 352.8179,
+      "step": 32
+    },
+    {
+      "epoch": 0.2841000807102502,
+      "grad_norm": 10.431824684143066,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 352.711,
+      "step": 33
+    },
+    {
+      "epoch": 0.29270917406510627,
+      "grad_norm": 11.229265213012695,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 352.5165,
+      "step": 34
+    },
+    {
+      "epoch": 0.3013182674199623,
+      "grad_norm": 13.20763111114502,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 351.8922,
+      "step": 35
+    },
+    {
+      "epoch": 0.3099273607748184,
+      "grad_norm": 16.267868041992188,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 351.0787,
+      "step": 36
+    },
+    {
+      "epoch": 0.31853645412967446,
+      "grad_norm": 19.831783294677734,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 350.2882,
+      "step": 37
+    },
+    {
+      "epoch": 0.3271455474845305,
+      "grad_norm": 15.882200241088867,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 351.226,
+      "step": 38
+    },
+    {
+      "epoch": 0.3357546408393866,
+      "grad_norm": 9.732914924621582,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 352.6428,
+      "step": 39
+    },
+    {
+      "epoch": 0.34436373419424265,
+      "grad_norm": 9.99857234954834,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 352.571,
+      "step": 40
+    },
+    {
+      "epoch": 0.35297282754909876,
+      "grad_norm": 9.702710151672363,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 352.5199,
+      "step": 41
+    },
+    {
+      "epoch": 0.3615819209039548,
+      "grad_norm": 9.81837272644043,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 352.5027,
+      "step": 42
+    },
+    {
+      "epoch": 0.37019101425881085,
+      "grad_norm": 9.183221817016602,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 352.661,
+      "step": 43
+    },
+    {
+      "epoch": 0.37880010761366695,
+      "grad_norm": 9.308856964111328,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 352.6186,
+      "step": 44
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": 9.76315975189209,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 352.499,
+      "step": 45
+    },
+    {
+      "epoch": 0.3960182943233791,
+      "grad_norm": 11.07622241973877,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 352.1287,
+      "step": 46
+    },
+    {
+      "epoch": 0.40462738767823514,
+      "grad_norm": 12.31144905090332,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 351.7421,
+      "step": 47
+    },
+    {
+      "epoch": 0.4132364810330912,
+      "grad_norm": 15.077690124511719,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 351.0006,
+      "step": 48
+    },
+    {
+      "epoch": 0.4218455743879473,
+      "grad_norm": 18.245941162109375,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 350.2695,
+      "step": 49
+    },
+    {
+      "epoch": 0.43045466774280333,
+      "grad_norm": 21.990154266357422,
+      "learning_rate": 1e-05,
+      "loss": 349.6386,
+      "step": 50
+    },
+    {
+      "epoch": 0.43045466774280333,
+      "eval_loss": 10.991680145263672,
+      "eval_runtime": 0.1335,
+      "eval_samples_per_second": 374.611,
+      "eval_steps_per_second": 97.399,
+      "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": 2105286328320.0,
+  "total_flos": 4212542668800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null