Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64c2f61f74a66c600e28322088e95981f122bc37c023d8243dacf55432859ad5
+oid sha256:e50a1792713b0df34480e6a25ff771ca1cea83f8d63b2bcf5e49dd2191fad987
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60c08b0e3ee857821d164c515feab77ff8c373272221e2e52ed49af0566a5602
+oid sha256:4977fee263b9d27f61476355361c8d782234c8acd56e3387eba1c49fe7f29765
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddab4e52b4f1b65140744ef1ae0b51e35b3371db2c8a3064b5c2dbcda9313a20
+oid sha256:12a4a11d38a0abd0f4348777f368acad8258aec75bf01d9fe5c69b1fd8657e3f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affbb048fb492d39c36cfc0397f648983f998e8de85f0caf89ec796504ae339e
+oid sha256:eebea7e633543ccd0386c34469c0bb65f1cb5f73be6f0d68063c09ffc70aad45
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ba10139c06f1fbcd77e917c36090e8fbefe7fdf23c729f59a307c5729610df
+oid sha256:bb7808ce4a90c77fad02eaced060a5c5e4db250d50572de00c58766988a535bd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9c2117990413bbaeb7fe3673df9305bc463ec4c9253c04aa531851105c3c15
+oid sha256:14f1ef420597dc591e233fd334efc233df9181b9f5124bc79393f14ad165f841
 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": 0.6147421002388,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010276172125883108,
+  "best_metric": 0.607292115688324,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.020552344251766216,
   "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": 27.406,
       "eval_steps_per_second": 7.125,
       "step": 25
+    },
+    {
+      "epoch": 0.010687219010918432,
+      "grad_norm": 0.19442589581012726,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6409,
+      "step": 26
+    },
+    {
+      "epoch": 0.011098265895953757,
+      "grad_norm": 0.1660703718662262,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5457,
+      "step": 27
+    },
+    {
+      "epoch": 0.011509312780989081,
+      "grad_norm": 0.15484054386615753,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5754,
+      "step": 28
+    },
+    {
+      "epoch": 0.011920359666024406,
+      "grad_norm": 0.14865733683109283,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5555,
+      "step": 29
+    },
+    {
+      "epoch": 0.01233140655105973,
+      "grad_norm": 0.15307866036891937,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5482,
+      "step": 30
+    },
+    {
+      "epoch": 0.012742453436095055,
+      "grad_norm": 0.15046963095664978,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.6116,
+      "step": 31
+    },
+    {
+      "epoch": 0.01315350032113038,
+      "grad_norm": 0.1480926275253296,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5848,
+      "step": 32
+    },
+    {
+      "epoch": 0.013564547206165704,
+      "grad_norm": 0.15706178545951843,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5613,
+      "step": 33
+    },
+    {
+      "epoch": 0.013975594091201027,
+      "grad_norm": 0.1832866072654724,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5875,
+      "step": 34
+    },
+    {
+      "epoch": 0.014386640976236351,
+      "grad_norm": 0.19785840809345245,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6325,
+      "step": 35
+    },
+    {
+      "epoch": 0.014797687861271676,
+      "grad_norm": 0.20388038456439972,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.6878,
+      "step": 36
+    },
+    {
+      "epoch": 0.015208734746307,
+      "grad_norm": 0.2478424608707428,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.7105,
+      "step": 37
+    },
+    {
+      "epoch": 0.015619781631342325,
+      "grad_norm": 0.19740141928195953,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5737,
+      "step": 38
+    },
+    {
+      "epoch": 0.01603082851637765,
+      "grad_norm": 0.11153397709131241,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.5391,
+      "step": 39
+    },
+    {
+      "epoch": 0.016441875401412974,
+      "grad_norm": 0.11589927971363068,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5387,
+      "step": 40
+    },
+    {
+      "epoch": 0.0168529222864483,
+      "grad_norm": 0.13013747334480286,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5277,
+      "step": 41
+    },
+    {
+      "epoch": 0.017263969171483623,
+      "grad_norm": 0.1374446004629135,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5472,
+      "step": 42
+    },
+    {
+      "epoch": 0.017675016056518947,
+      "grad_norm": 0.14348241686820984,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5851,
+      "step": 43
+    },
+    {
+      "epoch": 0.018086062941554272,
+      "grad_norm": 0.14722514152526855,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6086,
+      "step": 44
+    },
+    {
+      "epoch": 0.018497109826589597,
+      "grad_norm": 0.14866043627262115,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6056,
+      "step": 45
+    },
+    {
+      "epoch": 0.01890815671162492,
+      "grad_norm": 0.1653967648744583,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6457,
+      "step": 46
+    },
+    {
+      "epoch": 0.019319203596660246,
+      "grad_norm": 0.184136301279068,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6064,
+      "step": 47
+    },
+    {
+      "epoch": 0.01973025048169557,
+      "grad_norm": 0.23449210822582245,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6429,
+      "step": 48
+    },
+    {
+      "epoch": 0.02014129736673089,
+      "grad_norm": 0.2075590044260025,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.6361,
+      "step": 49
+    },
+    {
+      "epoch": 0.020552344251766216,
+      "grad_norm": 0.29820141196250916,
+      "learning_rate": 1e-05,
+      "loss": 0.7007,
+      "step": 50
+    },
+    {
+      "epoch": 0.020552344251766216,
+      "eval_loss": 0.607292115688324,
+      "eval_runtime": 1.8268,
+      "eval_samples_per_second": 27.37,
+      "eval_steps_per_second": 7.116,
+      "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": 3.082888193905787e+17,
+  "total_flos": 6.167641412935352e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null