Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9953800334f2ba22eed4657592ff4fbcc8cba6c6faa0091a3607649bf87a47f6
+oid sha256:fe107a8077e6af7ffca89d18173523cf3b08d2b13a943169562be3a1a873e793
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2986c41ec86f32d482d5a928240209347b0dde689eccc9c1862a416f3101e1af
+oid sha256:a7085399c99969fe08fe0f53e79dc115311faeb46c0e84a15ba1b2f6669aa6d0
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a72e01c01e7ad21df9a561405d6f9b71d00677d97a5743a98da7e5be3742e7
+oid sha256:632a0c2881967a9c4b7687cf37b59a1d141ae61f4e67be18447d1df4575b618b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85322d277c15bd9c1f4318a89bcfff6318150817674a9eedcb91f016b47eb72
+oid sha256:e9035fd211cbb7ca908b7852b439e3d98a27639c73f9b2b16aec504f9b4d3010
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa640015a609db2468a174843c5fd351126a61e519da326b4f722f9762cab0a
+oid sha256:7d90e25ca344bf2ea9db2422c2529364419819a7afe2ff66fe50f9f3fe60760f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e3ed25f61324e389dfac0b0ce723accccadc496752f9bfa4a189e680f71659
+oid sha256:d52386804a179f473bab30fec96beb9d228e74633e2b24d5e1d23fb1296771df
 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": 0.17924122512340546,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06897740989825832,
+  "best_metric": 0.1662767380475998,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13795481979651664,
   "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": 11.197,
       "eval_steps_per_second": 2.911,
       "step": 25
+    },
+    {
+      "epoch": 0.07173650629418865,
+      "grad_norm": 0.5671409964561462,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.208,
+      "step": 26
+    },
+    {
+      "epoch": 0.07449560269011898,
+      "grad_norm": 0.20743843913078308,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1561,
+      "step": 27
+    },
+    {
+      "epoch": 0.07725469908604932,
+      "grad_norm": 0.1487397849559784,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1517,
+      "step": 28
+    },
+    {
+      "epoch": 0.08001379548197965,
+      "grad_norm": 0.14751917123794556,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1527,
+      "step": 29
+    },
+    {
+      "epoch": 0.08277289187790998,
+      "grad_norm": 0.1772109568119049,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1572,
+      "step": 30
+    },
+    {
+      "epoch": 0.08553198827384031,
+      "grad_norm": 0.17633143067359924,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1685,
+      "step": 31
+    },
+    {
+      "epoch": 0.08829108466977065,
+      "grad_norm": 0.1450255960226059,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1668,
+      "step": 32
+    },
+    {
+      "epoch": 0.09105018106570098,
+      "grad_norm": 0.12896516919136047,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.162,
+      "step": 33
+    },
+    {
+      "epoch": 0.09380927746163131,
+      "grad_norm": 0.15334802865982056,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1835,
+      "step": 34
+    },
+    {
+      "epoch": 0.09656837385756165,
+      "grad_norm": 0.11007829010486603,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1674,
+      "step": 35
+    },
+    {
+      "epoch": 0.09932747025349198,
+      "grad_norm": 0.10919762402772903,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1785,
+      "step": 36
+    },
+    {
+      "epoch": 0.10208656664942231,
+      "grad_norm": 0.10813508927822113,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1547,
+      "step": 37
+    },
+    {
+      "epoch": 0.10484566304535264,
+      "grad_norm": 0.47470805048942566,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1636,
+      "step": 38
+    },
+    {
+      "epoch": 0.10760475944128298,
+      "grad_norm": 0.12728680670261383,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1483,
+      "step": 39
+    },
+    {
+      "epoch": 0.11036385583721331,
+      "grad_norm": 0.08785061538219452,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1464,
+      "step": 40
+    },
+    {
+      "epoch": 0.11312295223314364,
+      "grad_norm": 0.09421629458665848,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1475,
+      "step": 41
+    },
+    {
+      "epoch": 0.11588204862907397,
+      "grad_norm": 0.12139090150594711,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1508,
+      "step": 42
+    },
+    {
+      "epoch": 0.11864114502500431,
+      "grad_norm": 0.08867090195417404,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1499,
+      "step": 43
+    },
+    {
+      "epoch": 0.12140024142093464,
+      "grad_norm": 0.10524087399244308,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1575,
+      "step": 44
+    },
+    {
+      "epoch": 0.12415933781686497,
+      "grad_norm": 0.08246508240699768,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1558,
+      "step": 45
+    },
+    {
+      "epoch": 0.1269184342127953,
+      "grad_norm": 0.09248940646648407,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.1731,
+      "step": 46
+    },
+    {
+      "epoch": 0.12967753060872564,
+      "grad_norm": 0.08393806219100952,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1703,
+      "step": 47
+    },
+    {
+      "epoch": 0.13243662700465597,
+      "grad_norm": 0.0718834400177002,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1612,
+      "step": 48
+    },
+    {
+      "epoch": 0.1351957234005863,
+      "grad_norm": 0.058842603117227554,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1673,
+      "step": 49
+    },
+    {
+      "epoch": 0.13795481979651664,
+      "grad_norm": 0.0673556998372078,
+      "learning_rate": 1e-05,
+      "loss": 0.1551,
+      "step": 50
+    },
+    {
+      "epoch": 0.13795481979651664,
+      "eval_loss": 0.1662767380475998,
+      "eval_runtime": 4.3764,
+      "eval_samples_per_second": 11.425,
+      "eval_steps_per_second": 2.971,
+      "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": 3.030719813879071e+17,
+  "total_flos": 6.067967323065549e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null