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:de2cf379e9967e7e264037b38f400cabfe7dcd3835666705527c50939d93b103
+oid sha256:a6ce0eea9f45f21028107368855d78e8111648a8d4ea4b98598762f7f629c5ca
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b19f849dc6df0a0a6af5c6b079cca91cc299099beb57e065a576d13a724a61d7
+oid sha256:dbbe45d1e891ed4cbf146fbb98ac2263fa95dfa25f3168b1ff9cb27d86253906
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497bd361322733a81f3b9364d542f94e7e2401a166ba712d717f718c442b196b
+oid sha256:80cccc48703f374476c57386aebd06c3e7052c2af36afb18d445036580fa4684
 size 14244

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": 0.45079493522644043,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.039641246717209255,
+  "best_metric": 0.41836661100387573,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07928249343441851,
   "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": 1.543,
       "eval_steps_per_second": 1.543,
       "step": 25
+    },
+    {
+      "epoch": 0.04122689658589763,
+      "grad_norm": 4.445535182952881,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 15.3734,
+      "step": 26
+    },
+    {
+      "epoch": 0.042812546454585994,
+      "grad_norm": 4.722578525543213,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 15.0681,
+      "step": 27
+    },
+    {
+      "epoch": 0.044398196323274366,
+      "grad_norm": 4.662483215332031,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 12.8593,
+      "step": 28
+    },
+    {
+      "epoch": 0.04598384619196274,
+      "grad_norm": 4.774641036987305,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 14.9759,
+      "step": 29
+    },
+    {
+      "epoch": 0.047569496060651105,
+      "grad_norm": 4.80148458480835,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 14.2648,
+      "step": 30
+    },
+    {
+      "epoch": 0.04915514592933948,
+      "grad_norm": 4.728338718414307,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 13.1279,
+      "step": 31
+    },
+    {
+      "epoch": 0.05074079579802785,
+      "grad_norm": 4.526378631591797,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 12.6951,
+      "step": 32
+    },
+    {
+      "epoch": 0.052326445666716216,
+      "grad_norm": 4.543455600738525,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 12.6935,
+      "step": 33
+    },
+    {
+      "epoch": 0.05391209553540459,
+      "grad_norm": 4.797730922698975,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 12.7275,
+      "step": 34
+    },
+    {
+      "epoch": 0.05549774540409296,
+      "grad_norm": 5.633406162261963,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 15.7208,
+      "step": 35
+    },
+    {
+      "epoch": 0.05708339527278133,
+      "grad_norm": 5.659888744354248,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 15.1841,
+      "step": 36
+    },
+    {
+      "epoch": 0.0586690451414697,
+      "grad_norm": 6.257349967956543,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 18.2712,
+      "step": 37
+    },
+    {
+      "epoch": 0.06025469501015807,
+      "grad_norm": 5.911546230316162,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 15.9163,
+      "step": 38
+    },
+    {
+      "epoch": 0.06184034487884644,
+      "grad_norm": 5.786442756652832,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 15.7632,
+      "step": 39
+    },
+    {
+      "epoch": 0.06342599474753481,
+      "grad_norm": 6.7470879554748535,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 15.5596,
+      "step": 40
+    },
+    {
+      "epoch": 0.06501164461622318,
+      "grad_norm": 6.114599227905273,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 16.4764,
+      "step": 41
+    },
+    {
+      "epoch": 0.06659729448491156,
+      "grad_norm": 7.806087493896484,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 16.9766,
+      "step": 42
+    },
+    {
+      "epoch": 0.06818294435359992,
+      "grad_norm": 7.94345760345459,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 16.4281,
+      "step": 43
+    },
+    {
+      "epoch": 0.06976859422228829,
+      "grad_norm": 7.828482151031494,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 18.5273,
+      "step": 44
+    },
+    {
+      "epoch": 0.07135424409097667,
+      "grad_norm": 8.026106834411621,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 16.7366,
+      "step": 45
+    },
+    {
+      "epoch": 0.07293989395966503,
+      "grad_norm": 8.980546951293945,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 18.6461,
+      "step": 46
+    },
+    {
+      "epoch": 0.0745255438283534,
+      "grad_norm": 9.830076217651367,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 21.7088,
+      "step": 47
+    },
+    {
+      "epoch": 0.07611119369704177,
+      "grad_norm": 13.883023262023926,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 25.3251,
+      "step": 48
+    },
+    {
+      "epoch": 0.07769684356573014,
+      "grad_norm": 17.941938400268555,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 25.1379,
+      "step": 49
+    },
+    {
+      "epoch": 0.07928249343441851,
+      "grad_norm": 19.284452438354492,
+      "learning_rate": 1e-05,
+      "loss": 27.9763,
+      "step": 50
+    },
+    {
+      "epoch": 0.07928249343441851,
+      "eval_loss": 0.41836661100387573,
+      "eval_runtime": 32.3564,
+      "eval_samples_per_second": 1.545,
+      "eval_steps_per_second": 1.545,
+      "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": 1.2820971257856e+17,
+  "total_flos": 2.5578156589056e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null