Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e4cb4c947d04ef88a42c6127d5367f945eafbdc61cd0f68d97903c6ca41263
+oid sha256:38b03c92ba49b470a1e5020b040ac0b63972771f418a1eef533e94da12da6b7a
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2387c6af54c4bdefa4175f5e5c7f4eab7d11477991c60d638c30f1e38460dc
+oid sha256:594e9ed8b8f8709a7ac5c9f1e92b05af5abd4fe66d359af0c695054dfcdeb59c
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7244258336335226100e60bd225b5d2b07f289e02de5c6aee0039a2bc0a0199
+oid sha256:e6a042e302747ec2957b5700ffc95982dfdc67b5d0112cdecee265f89e62a0fc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91169b622e700271e5c5cb6253fd11b7ce0ee0657b65ea591863c0939d97fdce
+oid sha256:e1f2a80dafb7705ec82d871a684b6aaee7c0e04ee34f1261f3197d5c074a7b06
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f522e834831fad4a1628e4433e0c1987db47991bd50af74c44c62cdc2f3da77
+oid sha256:5c85bc717a890cc887a8bd507234900eca8270b9e31910b8f09c56add5667ce0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c85eb910b310007d45a32a46203c0ec4e446ba15cda02b01d2fda32dfeb59c
+oid sha256:35ca8c65ad76054c769f24e20de04380a4bb752fbdeedb65cebeb5c213877c3e
 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": 11.92894172668457,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.021021099929053787,
+  "best_metric": 11.928580284118652,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04204219985810757,
   "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": 194.021,
       "eval_steps_per_second": 50.445,
       "step": 25
+    },
+    {
+      "epoch": 0.02186194392621594,
+      "grad_norm": 0.013367222622036934,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9316,
+      "step": 26
+    },
+    {
+      "epoch": 0.02270278792337809,
+      "grad_norm": 0.013996853493154049,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9326,
+      "step": 27
+    },
+    {
+      "epoch": 0.023543631920540244,
+      "grad_norm": 0.012285441160202026,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9317,
+      "step": 28
+    },
+    {
+      "epoch": 0.024384475917702392,
+      "grad_norm": 0.014247197657823563,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9301,
+      "step": 29
+    },
+    {
+      "epoch": 0.025225319914864545,
+      "grad_norm": 0.018749596551060677,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9304,
+      "step": 30
+    },
+    {
+      "epoch": 0.026066163912026697,
+      "grad_norm": 0.019898192957043648,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9308,
+      "step": 31
+    },
+    {
+      "epoch": 0.02690700790918885,
+      "grad_norm": 0.015146265737712383,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.93,
+      "step": 32
+    },
+    {
+      "epoch": 0.027747851906350998,
+      "grad_norm": 0.020423298701643944,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9311,
+      "step": 33
+    },
+    {
+      "epoch": 0.02858869590351315,
+      "grad_norm": 0.019463174045085907,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9324,
+      "step": 34
+    },
+    {
+      "epoch": 0.029429539900675303,
+      "grad_norm": 0.020006148144602776,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9315,
+      "step": 35
+    },
+    {
+      "epoch": 0.030270383897837455,
+      "grad_norm": 0.028537606820464134,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.931,
+      "step": 36
+    },
+    {
+      "epoch": 0.031111227894999607,
+      "grad_norm": 0.0409284271299839,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9303,
+      "step": 37
+    },
+    {
+      "epoch": 0.03195207189216176,
+      "grad_norm": 0.016674354672431946,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9318,
+      "step": 38
+    },
+    {
+      "epoch": 0.03279291588932391,
+      "grad_norm": 0.013431726023554802,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9314,
+      "step": 39
+    },
+    {
+      "epoch": 0.03363375988648606,
+      "grad_norm": 0.0123633723706007,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9302,
+      "step": 40
+    },
+    {
+      "epoch": 0.03447460388364821,
+      "grad_norm": 0.019705647602677345,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9306,
+      "step": 41
+    },
+    {
+      "epoch": 0.03531544788081036,
+      "grad_norm": 0.016866084188222885,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9308,
+      "step": 42
+    },
+    {
+      "epoch": 0.036156291877972514,
+      "grad_norm": 0.014826917089521885,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9303,
+      "step": 43
+    },
+    {
+      "epoch": 0.03699713587513467,
+      "grad_norm": 0.01878633163869381,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9312,
+      "step": 44
+    },
+    {
+      "epoch": 0.03783797987229682,
+      "grad_norm": 0.02509169653058052,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9301,
+      "step": 45
+    },
+    {
+      "epoch": 0.03867882386945897,
+      "grad_norm": 0.01745207980275154,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9303,
+      "step": 46
+    },
+    {
+      "epoch": 0.03951966786662112,
+      "grad_norm": 0.01895272359251976,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9298,
+      "step": 47
+    },
+    {
+      "epoch": 0.040360511863783276,
+      "grad_norm": 0.025853751227259636,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9314,
+      "step": 48
+    },
+    {
+      "epoch": 0.04120135586094542,
+      "grad_norm": 0.030947135761380196,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9316,
+      "step": 49
+    },
+    {
+      "epoch": 0.04204219985810757,
+      "grad_norm": 0.05523964390158653,
+      "learning_rate": 1e-05,
+      "loss": 11.9283,
+      "step": 50
+    },
+    {
+      "epoch": 0.04204219985810757,
+      "eval_loss": 11.928580284118652,
+      "eval_runtime": 0.2428,
+      "eval_samples_per_second": 205.889,
+      "eval_steps_per_second": 53.531,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null