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:f7b2719e10c21a98d8a45bdf5ede3c0bf22e307a5f83912cb52d772f7fc26e8d
+oid sha256:1402422168e912695b4377d8cc83bc795f0094c008bb57991df3b948a613c590
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:474a8a078862a6bb5d31d769d5ba6c266dc64364ef9c260f4699dd77f63b728e
+oid sha256:ce269430b5d8db859a469c89e04a5525a9ba75fe26a78ae6100833614ed1191c
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f23090f59efc52964004013a078804e5f8142509a8fee9227be409752682a6a
+oid sha256:a5d89c8894ed3141b3804009d635ca819a5e4734d7a8eb477a61f541d547bce6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93d17918a212c59740638acfb88e1da7fdf7e74c275a5f96463db5c3f766309
+oid sha256:5f7b455062c86e3e7e8e779e7b649a51180660b9faa4fa2e0227d3b3c0dfd4fd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98f350156a6e6e008b02c1edcd5dc0d3b7d7924d41f8fe6d3441ec6068dc28d6
+oid sha256:fc243106e6feeb5eb2b5c263149aee39678e38c1c53c5ffe3814b7f489ed370f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c40173b7e7cfbec59321c960387c9b4896f67feca1736aa80dd3083f61128bc
+oid sha256:dbc6a06f12bc6d2ba2f422d3d43635bad4f6b052718bf6844f17a298b0560f36
 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": 6.913173675537109,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011883894352179208,
+  "best_metric": 6.900269031524658,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.023767788704358417,
   "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": 564.04,
       "eval_steps_per_second": 146.65,
       "step": 25
+    },
+    {
+      "epoch": 0.012359250126266378,
+      "grad_norm": 0.3777521550655365,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.8997,
+      "step": 26
+    },
+    {
+      "epoch": 0.012834605900353546,
+      "grad_norm": 0.31511756777763367,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.9013,
+      "step": 27
+    },
+    {
+      "epoch": 0.013309961674440714,
+      "grad_norm": 0.3206568956375122,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.8988,
+      "step": 28
+    },
+    {
+      "epoch": 0.013785317448527883,
+      "grad_norm": 0.3120715618133545,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.8991,
+      "step": 29
+    },
+    {
+      "epoch": 0.014260673222615051,
+      "grad_norm": 0.30434051156044006,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.8997,
+      "step": 30
+    },
+    {
+      "epoch": 0.014736028996702219,
+      "grad_norm": 0.32293179631233215,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.8968,
+      "step": 31
+    },
+    {
+      "epoch": 0.015211384770789387,
+      "grad_norm": 0.3022577166557312,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.9002,
+      "step": 32
+    },
+    {
+      "epoch": 0.015686740544876555,
+      "grad_norm": 0.276790052652359,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.9018,
+      "step": 33
+    },
+    {
+      "epoch": 0.016162096318963724,
+      "grad_norm": 0.27103278040885925,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.9013,
+      "step": 34
+    },
+    {
+      "epoch": 0.016637452093050894,
+      "grad_norm": 0.24876445531845093,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.9043,
+      "step": 35
+    },
+    {
+      "epoch": 0.01711280786713806,
+      "grad_norm": 0.19545753300189972,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.9152,
+      "step": 36
+    },
+    {
+      "epoch": 0.01758816364122523,
+      "grad_norm": 0.1613902449607849,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.9259,
+      "step": 37
+    },
+    {
+      "epoch": 0.0180635194153124,
+      "grad_norm": 0.4136228561401367,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.8879,
+      "step": 38
+    },
+    {
+      "epoch": 0.018538875189399565,
+      "grad_norm": 0.34804272651672363,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.8892,
+      "step": 39
+    },
+    {
+      "epoch": 0.019014230963486735,
+      "grad_norm": 0.3347592353820801,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.8905,
+      "step": 40
+    },
+    {
+      "epoch": 0.019489586737573904,
+      "grad_norm": 0.3388766944408417,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.8902,
+      "step": 41
+    },
+    {
+      "epoch": 0.01996494251166107,
+      "grad_norm": 0.314827024936676,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.8922,
+      "step": 42
+    },
+    {
+      "epoch": 0.02044029828574824,
+      "grad_norm": 0.3265056610107422,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.8902,
+      "step": 43
+    },
+    {
+      "epoch": 0.02091565405983541,
+      "grad_norm": 0.310298353433609,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.8928,
+      "step": 44
+    },
+    {
+      "epoch": 0.021391009833922576,
+      "grad_norm": 0.3022330701351166,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.8925,
+      "step": 45
+    },
+    {
+      "epoch": 0.021866365608009745,
+      "grad_norm": 0.2826597988605499,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.8954,
+      "step": 46
+    },
+    {
+      "epoch": 0.02234172138209691,
+      "grad_norm": 0.26531800627708435,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.8986,
+      "step": 47
+    },
+    {
+      "epoch": 0.02281707715618408,
+      "grad_norm": 0.22228993475437164,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.9088,
+      "step": 48
+    },
+    {
+      "epoch": 0.02329243293027125,
+      "grad_norm": 0.17581987380981445,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.9162,
+      "step": 49
+    },
+    {
+      "epoch": 0.023767788704358417,
+      "grad_norm": 0.2906361222267151,
+      "learning_rate": 1e-05,
+      "loss": 6.9222,
+      "step": 50
+    },
+    {
+      "epoch": 0.023767788704358417,
+      "eval_loss": 6.900269031524658,
+      "eval_runtime": 0.0883,
+      "eval_samples_per_second": 566.131,
+      "eval_steps_per_second": 147.194,
+      "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": 3118662336512.0,
+  "total_flos": 6231975329792.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null