Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01811041baf9879a1b4428b3af49617d177af840ee6b2bbf91d6fa37554662c2
+oid sha256:4b42d53ef16f5d1ed85d7295ee336d192a220e0777ddd4930a439c11fca3efbd
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4444431c9db4ba1d9c345cc867735e3b90d4902bdb366a07b4c94e7dc5f7a747
+oid sha256:241776dbd2aa8067689b507835d8f7265f2e79d5ae73cdbf6c604edbdb5c1667
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a381123eecaabb913d93235f913b897030f39e80af27754b78e572f4d796ede7
+oid sha256:dc6ac83a9e7751c033c0df492a63e6c13b5d92491800841811e504b5a8a22e64
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:667881bb97184284fb76fd280650d87bccfd585d76e881aee75768c96c1c8328
+oid sha256:64b714e4f085052d928ac3d5da8726451a47e90d4d83772a00170fe93d8fee34
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742a9e1dcb6490c845dcef9cb63ff7bc43bf4cd453e36ede6e042628bdd154e5
+oid sha256:c479faff613ae443a780a2d0807d9f89366d23cc6b164beba6c96972d67e08ee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc128de180d0f5fcb388f5eb2d8c76d9e22994be57a229b5f7fd134c7904a5b
+oid sha256:44779017c60d044f18ec4db47b00f84accfa6fa31d58dc7d95801ae76feb3957
 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": 1.04914391040802,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.19627085377821393,
+  "best_metric": 0.8620172142982483,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.39254170755642787,
   "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": 19.475,
       "eval_steps_per_second": 5.064,
       "step": 25
+    },
+    {
+      "epoch": 0.2041216879293425,
+      "grad_norm": 0.97491055727005,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.3922,
+      "step": 26
+    },
+    {
+      "epoch": 0.21197252208047104,
+      "grad_norm": 1.1205915212631226,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7055,
+      "step": 27
+    },
+    {
+      "epoch": 0.2198233562315996,
+      "grad_norm": 0.336657851934433,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7726,
+      "step": 28
+    },
+    {
+      "epoch": 0.22767419038272815,
+      "grad_norm": 0.3204854726791382,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.673,
+      "step": 29
+    },
+    {
+      "epoch": 0.23552502453385674,
+      "grad_norm": 0.19506654143333435,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9861,
+      "step": 30
+    },
+    {
+      "epoch": 0.2433758586849853,
+      "grad_norm": 0.18182063102722168,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0981,
+      "step": 31
+    },
+    {
+      "epoch": 0.2512266928361138,
+      "grad_norm": 0.19906948506832123,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0542,
+      "step": 32
+    },
+    {
+      "epoch": 0.2590775269872424,
+      "grad_norm": 0.2256714254617691,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.1696,
+      "step": 33
+    },
+    {
+      "epoch": 0.26692836113837093,
+      "grad_norm": 0.23073700070381165,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2768,
+      "step": 34
+    },
+    {
+      "epoch": 0.2747791952894995,
+      "grad_norm": 0.2971401810646057,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.5064,
+      "step": 35
+    },
+    {
+      "epoch": 0.2826300294406281,
+      "grad_norm": 0.6672556400299072,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.752,
+      "step": 36
+    },
+    {
+      "epoch": 0.2904808635917566,
+      "grad_norm": 1.4457920789718628,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.7178,
+      "step": 37
+    },
+    {
+      "epoch": 0.2983316977428852,
+      "grad_norm": 1.220274806022644,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.752,
+      "step": 38
+    },
+    {
+      "epoch": 0.30618253189401373,
+      "grad_norm": 0.618290364742279,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6735,
+      "step": 39
+    },
+    {
+      "epoch": 0.3140333660451423,
+      "grad_norm": 0.4673266112804413,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7348,
+      "step": 40
+    },
+    {
+      "epoch": 0.32188420019627084,
+      "grad_norm": 0.35256361961364746,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5991,
+      "step": 41
+    },
+    {
+      "epoch": 0.3297350343473994,
+      "grad_norm": 0.1682473123073578,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.9351,
+      "step": 42
+    },
+    {
+      "epoch": 0.33758586849852795,
+      "grad_norm": 0.15965545177459717,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9283,
+      "step": 43
+    },
+    {
+      "epoch": 0.34543670264965654,
+      "grad_norm": 0.1923704594373703,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0068,
+      "step": 44
+    },
+    {
+      "epoch": 0.35328753680078506,
+      "grad_norm": 0.20349323749542236,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.0288,
+      "step": 45
+    },
+    {
+      "epoch": 0.36113837095191365,
+      "grad_norm": 0.22597980499267578,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.228,
+      "step": 46
+    },
+    {
+      "epoch": 0.3689892051030422,
+      "grad_norm": 0.3004361391067505,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4147,
+      "step": 47
+    },
+    {
+      "epoch": 0.37684003925417076,
+      "grad_norm": 0.4439603388309479,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.5545,
+      "step": 48
+    },
+    {
+      "epoch": 0.38469087340529934,
+      "grad_norm": 0.6833898425102234,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.7517,
+      "step": 49
+    },
+    {
+      "epoch": 0.39254170755642787,
+      "grad_norm": 2.600379228591919,
+      "learning_rate": 1e-05,
+      "loss": 1.1795,
+      "step": 50
+    },
+    {
+      "epoch": 0.39254170755642787,
+      "eval_loss": 0.8620172142982483,
+      "eval_runtime": 2.7207,
+      "eval_samples_per_second": 18.378,
+      "eval_steps_per_second": 4.778,
+      "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": 3.0391597252634214e+17,
+  "total_flos": 6.086632252354068e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null