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:d514c8d5a87b81b2b976c6a7e37cd12763bdc5aeddb43dbecb9a91472ec1123f
+oid sha256:27c51397e58dbd61c1e16a8be67aa5e696117d2eb55b9faadaa1ccba3c0230ce
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946737398482a2560e50e1c3019364872467a3e99db1e072ea4bf6d207ee9b02
+oid sha256:f4b0af96dfa04679f55a822eec4c29e3cd1e39cb3242e8bb4443537e5f40b3fd
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5858c6913a0c513dd539661b5b90f1600b6f7f42004c4d4a5fc14324131143
+oid sha256:dfe151312e5cae6dfed5b42b191fdbe0b957ff75d21fb034158bccae454d0ffb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f55c6743ac23e78ccf3f7cc8a060f2a3871558f05f6451f922c52ae3ca2f74
+oid sha256:e4ccb8212c01ae0e9cee13f5dfe57ebe77126c530bf6f766bf764401be40de0e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b10747cd163f6c1dd89bd7bd6a444d03d9addf1bf1e3cccce5ee2647cb93764b
+oid sha256:b2cabf418cb1204b5bc333cd3b73da75427cc07c09600e93278c5bf0e26a5035
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccfc54b29be8ef33a51481e788259c3acd48c523ec56745108728a1789bf3248
+oid sha256:441c0151b6ac380c6ca1e5b85ec7433d02dc82a418c9d86be07d5c7a89028391
 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": 4.195949554443359,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.34873583260680036,
+  "best_metric": 4.016973972320557,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6974716652136007,
   "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": 39.485,
       "eval_steps_per_second": 10.266,
       "step": 25
+    },
+    {
+      "epoch": 0.36268526591107236,
+      "grad_norm": 3.850996255874634,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.4531,
+      "step": 26
+    },
+    {
+      "epoch": 0.37663469921534437,
+      "grad_norm": 4.408858299255371,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.4775,
+      "step": 27
+    },
+    {
+      "epoch": 0.3905841325196164,
+      "grad_norm": 4.330770015716553,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.6506,
+      "step": 28
+    },
+    {
+      "epoch": 0.4045335658238884,
+      "grad_norm": 3.5484189987182617,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.4924,
+      "step": 29
+    },
+    {
+      "epoch": 0.4184829991281604,
+      "grad_norm": 3.185976028442383,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.5173,
+      "step": 30
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 2.7126657962799072,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.4024,
+      "step": 31
+    },
+    {
+      "epoch": 0.44638186573670446,
+      "grad_norm": 2.2540411949157715,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.1523,
+      "step": 32
+    },
+    {
+      "epoch": 0.46033129904097647,
+      "grad_norm": 1.9622880220413208,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.3448,
+      "step": 33
+    },
+    {
+      "epoch": 0.4742807323452485,
+      "grad_norm": 1.9291648864746094,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.0292,
+      "step": 34
+    },
+    {
+      "epoch": 0.4882301656495205,
+      "grad_norm": 2.3810603618621826,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.1376,
+      "step": 35
+    },
+    {
+      "epoch": 0.5021795989537925,
+      "grad_norm": 3.092702865600586,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.8523,
+      "step": 36
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 3.8603620529174805,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.8096,
+      "step": 37
+    },
+    {
+      "epoch": 0.5300784655623365,
+      "grad_norm": 1.1517781019210815,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.0555,
+      "step": 38
+    },
+    {
+      "epoch": 0.5440278988666085,
+      "grad_norm": 1.121120810508728,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.1753,
+      "step": 39
+    },
+    {
+      "epoch": 0.5579773321708805,
+      "grad_norm": 1.042154312133789,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.1934,
+      "step": 40
+    },
+    {
+      "epoch": 0.5719267654751525,
+      "grad_norm": 1.0696301460266113,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.251,
+      "step": 41
+    },
+    {
+      "epoch": 0.5858761987794245,
+      "grad_norm": 1.123052954673767,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.2678,
+      "step": 42
+    },
+    {
+      "epoch": 0.5998256320836965,
+      "grad_norm": 1.2128586769104004,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.1949,
+      "step": 43
+    },
+    {
+      "epoch": 0.6137750653879687,
+      "grad_norm": 1.271983027458191,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.2028,
+      "step": 44
+    },
+    {
+      "epoch": 0.6277244986922407,
+      "grad_norm": 1.46515691280365,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.1909,
+      "step": 45
+    },
+    {
+      "epoch": 0.6416739319965127,
+      "grad_norm": 1.5033705234527588,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.0259,
+      "step": 46
+    },
+    {
+      "epoch": 0.6556233653007847,
+      "grad_norm": 1.617010474205017,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.0235,
+      "step": 47
+    },
+    {
+      "epoch": 0.6695727986050567,
+      "grad_norm": 1.9543062448501587,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.9517,
+      "step": 48
+    },
+    {
+      "epoch": 0.6835222319093287,
+      "grad_norm": 2.396531581878662,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.7364,
+      "step": 49
+    },
+    {
+      "epoch": 0.6974716652136007,
+      "grad_norm": 4.221222877502441,
+      "learning_rate": 1e-05,
+      "loss": 3.607,
+      "step": 50
+    },
+    {
+      "epoch": 0.6974716652136007,
+      "eval_loss": 4.016973972320557,
+      "eval_runtime": 1.2592,
+      "eval_samples_per_second": 39.709,
+      "eval_steps_per_second": 10.324,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null