Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92793f9f091226be518b77d8487a80b1675ecd76c46f67d28bfb7df49209a4cd
+oid sha256:7b3aa88379fe27c01dd99a9cdc328ebd686d9a102349204453b6c2fc86cf03db
 size 406863720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6587a2c71480de48d1fe5d86ee338977784cfe90e20aacbd399528d20916fb49
+oid sha256:e290a699b9e573b0748c95e56da5ead988a0bfb990c7eccdf2e95b3d1146e8e1
 size 207013892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d582d457d208e41de9ebb4b08cb1cea126766e47df048b8aea32ac6f818ce51f
+oid sha256:b3bd27946b5773c5b71527b48c3b2b0338c97a8d2db198a15f08b1ec80417051
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0029016202315688133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.5154639175257731,
+  "best_metric": 0.0021364144049584866,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.6872852233676976,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -389,6 +389,126 @@
       "eval_samples_per_second": 20.886,
       "eval_steps_per_second": 5.243,
       "step": 150
+    },
+    {
+      "epoch": 0.5257731958762887,
+      "grad_norm": 0.0867040827870369,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 0.0131,
+      "step": 153
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 0.009477502666413784,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.0017,
+      "step": 156
+    },
+    {
+      "epoch": 0.5463917525773195,
+      "grad_norm": 0.07320986688137054,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 0.0011,
+      "step": 159
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 0.036945637315511703,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0006,
+      "step": 162
+    },
+    {
+      "epoch": 0.5670103092783505,
+      "grad_norm": 0.020839812234044075,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.0011,
+      "step": 165
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 0.047367069870233536,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.0007,
+      "step": 168
+    },
+    {
+      "epoch": 0.5876288659793815,
+      "grad_norm": 0.12399918586015701,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 0.0022,
+      "step": 171
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 0.0026428853161633015,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 0.0002,
+      "step": 174
+    },
+    {
+      "epoch": 0.6082474226804123,
+      "grad_norm": 0.05488703399896622,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 0.0021,
+      "step": 177
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 0.055584318935871124,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.001,
+      "step": 180
+    },
+    {
+      "epoch": 0.6288659793814433,
+      "grad_norm": 0.003122512251138687,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 0.0003,
+      "step": 183
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 0.0022415139246731997,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 0.0003,
+      "step": 186
+    },
+    {
+      "epoch": 0.6494845360824743,
+      "grad_norm": 0.008853805251419544,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 0.0051,
+      "step": 189
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 0.9864411354064941,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.0016,
+      "step": 192
+    },
+    {
+      "epoch": 0.6701030927835051,
+      "grad_norm": 0.23232021927833557,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.0034,
+      "step": 195
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 0.06562889367341995,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.0006,
+      "step": 198
+    },
+    {
+      "epoch": 0.6872852233676976,
+      "eval_loss": 0.0021364144049584866,
+      "eval_runtime": 23.4535,
+      "eval_samples_per_second": 20.892,
+      "eval_steps_per_second": 5.244,
+      "step": 200
     }
   ],
   "logging_steps": 3,
@@ -412,12 +532,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0759725130973184e+17,
+  "total_flos": 1.439681531609088e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null