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:ff7f87035abaf57ce5aba2f3ab915b6a1e69546732c52c324c159441d6f30338
+oid sha256:99614a17327f5e4d97580289064c90a824501c86b43b5f059d947ab8bdc49385
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f562c286459684f707dc17e1ed168e0da0d8ea16b7b77dd5f08cf0a4447142c
+oid sha256:c3c6538f67bcf9e76374c5a3291835d26b7f06a4cc7e0ad7a9cad5f818360b3a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07f20432918f2c0a240b6df3a8b7310f0636d9fb94885fb0dcc33d01079c2dfb
+oid sha256:57b5271d8ea64f1f0e6309f3fdacc09a98bb435dbb4059ba320af5a702febfc1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270f501ab89a5c8017e0cda738b0167fd906c37461dfe3f11df2c348fba732d7
+oid sha256:a7473e890b6c0cd1da1226d4a2b860a673c3d52c85466b5fc9d4a220f974cbec
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a28aa4f867dc02a9fb37a3e1afb505aef71861060f809ddb887a31cdc9cdf4ed
+oid sha256:917961ecd4a4b36252df248de7bf6814bdeae7e6a5c25ea14083bd9eab257f01
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76610edfe4f863751b608c0576fe6ebf2b3ba77a8d98821edf0cc993aa0d8243
+oid sha256:33a9306f2539a35ae28e8aea439a87bba0031e3535799eb1995fb9213350bc37
 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": 3.5562896728515625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004573153303531617,
+  "best_metric": 3.432676315307617,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009146306607063235,
   "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": 24.518,
       "eval_steps_per_second": 6.375,
       "step": 25
+    },
+    {
+      "epoch": 0.004756079435672882,
+      "grad_norm": 1.803903341293335,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.0202,
+      "step": 26
+    },
+    {
+      "epoch": 0.004939005567814147,
+      "grad_norm": 1.4035038948059082,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.1542,
+      "step": 27
+    },
+    {
+      "epoch": 0.005121931699955412,
+      "grad_norm": 1.3655030727386475,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.2782,
+      "step": 28
+    },
+    {
+      "epoch": 0.005304857832096677,
+      "grad_norm": 1.1467270851135254,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.396,
+      "step": 29
+    },
+    {
+      "epoch": 0.005487783964237941,
+      "grad_norm": 1.1027382612228394,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.4175,
+      "step": 30
+    },
+    {
+      "epoch": 0.005670710096379206,
+      "grad_norm": 1.5248521566390991,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.4381,
+      "step": 31
+    },
+    {
+      "epoch": 0.0058536362285204705,
+      "grad_norm": 1.9056307077407837,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.4771,
+      "step": 32
+    },
+    {
+      "epoch": 0.006036562360661735,
+      "grad_norm": 1.7207236289978027,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.5574,
+      "step": 33
+    },
+    {
+      "epoch": 0.006219488492803,
+      "grad_norm": 1.2745652198791504,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.6236,
+      "step": 34
+    },
+    {
+      "epoch": 0.006402414624944265,
+      "grad_norm": 1.5298084020614624,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.5052,
+      "step": 35
+    },
+    {
+      "epoch": 0.006585340757085529,
+      "grad_norm": 1.6400824785232544,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.5871,
+      "step": 36
+    },
+    {
+      "epoch": 0.006768266889226794,
+      "grad_norm": 2.165523052215576,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.7025,
+      "step": 37
+    },
+    {
+      "epoch": 0.006951193021368059,
+      "grad_norm": 1.51387619972229,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.0254,
+      "step": 38
+    },
+    {
+      "epoch": 0.007134119153509324,
+      "grad_norm": 1.3941786289215088,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.1322,
+      "step": 39
+    },
+    {
+      "epoch": 0.007317045285650589,
+      "grad_norm": 1.2476261854171753,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.1812,
+      "step": 40
+    },
+    {
+      "epoch": 0.007499971417791853,
+      "grad_norm": 1.377185344696045,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.4018,
+      "step": 41
+    },
+    {
+      "epoch": 0.0076828975499331174,
+      "grad_norm": 1.416702389717102,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.2872,
+      "step": 42
+    },
+    {
+      "epoch": 0.007865823682074382,
+      "grad_norm": 1.2533056735992432,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.4308,
+      "step": 43
+    },
+    {
+      "epoch": 0.008048749814215647,
+      "grad_norm": 1.3103725910186768,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.4037,
+      "step": 44
+    },
+    {
+      "epoch": 0.008231675946356912,
+      "grad_norm": 1.1992508172988892,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.5168,
+      "step": 45
+    },
+    {
+      "epoch": 0.008414602078498177,
+      "grad_norm": 1.243343710899353,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.4219,
+      "step": 46
+    },
+    {
+      "epoch": 0.008597528210639442,
+      "grad_norm": 1.248721718788147,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.3442,
+      "step": 47
+    },
+    {
+      "epoch": 0.008780454342780707,
+      "grad_norm": 1.4735393524169922,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.6574,
+      "step": 48
+    },
+    {
+      "epoch": 0.00896338047492197,
+      "grad_norm": 1.8419065475463867,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.504,
+      "step": 49
+    },
+    {
+      "epoch": 0.009146306607063235,
+      "grad_norm": 3.8599138259887695,
+      "learning_rate": 1e-05,
+      "loss": 3.868,
+      "step": 50
+    },
+    {
+      "epoch": 0.009146306607063235,
+      "eval_loss": 3.432676315307617,
+      "eval_runtime": 2.0429,
+      "eval_samples_per_second": 24.475,
+      "eval_steps_per_second": 6.363,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null