Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa05723dde4dc9dca4f6a0c08a424f39cacd57447d9d14737804b4088bc33df
+oid sha256:caeda5ffa43f77166c46a0f219e3dbd0f830b3c64000eb0e8c00e062a151f9e7
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4378fe3501dd3fd67195945223e4b4d8c30fa2b5422fb75be13d1096090a1cc6
+oid sha256:39fac0ced71bc444b5a3ec2d0bdf21882b9ffbed59b211752d85204e9c5ab0b6
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546c1f560eab29dbbd8ad3a58f22f38b3f6d7d8801698e62d84517cda04688f4
+oid sha256:34136a898581a12f4f2c35a8f4d06cf0ba5df561b4d6a48b4f4efff4b9e55786
 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": 1.139582872390747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.00865263977618505,
+  "best_metric": 1.135033369064331,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.011536853034913402,
   "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": 58.788,
       "eval_steps_per_second": 14.698,
       "step": 150
+    },
+    {
+      "epoch": 0.008825692571708753,
+      "grad_norm": 0.343904584646225,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 0.9637,
+      "step": 153
+    },
+    {
+      "epoch": 0.008998745367232453,
+      "grad_norm": 0.38003867864608765,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.9447,
+      "step": 156
+    },
+    {
+      "epoch": 0.009171798162756154,
+      "grad_norm": 0.3449487090110779,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 1.0876,
+      "step": 159
+    },
+    {
+      "epoch": 0.009344850958279855,
+      "grad_norm": 0.4446622431278229,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1895,
+      "step": 162
+    },
+    {
+      "epoch": 0.009517903753803555,
+      "grad_norm": 0.4309278428554535,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 1.0161,
+      "step": 165
+    },
+    {
+      "epoch": 0.009690956549327258,
+      "grad_norm": 0.3661138713359833,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 1.1177,
+      "step": 168
+    },
+    {
+      "epoch": 0.009864009344850959,
+      "grad_norm": 0.3448355793952942,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 1.0711,
+      "step": 171
+    },
+    {
+      "epoch": 0.01003706214037466,
+      "grad_norm": 0.35449743270874023,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 1.1541,
+      "step": 174
+    },
+    {
+      "epoch": 0.01021011493589836,
+      "grad_norm": 0.37603992223739624,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 1.1487,
+      "step": 177
+    },
+    {
+      "epoch": 0.01038316773142206,
+      "grad_norm": 0.4178571105003357,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 1.1862,
+      "step": 180
+    },
+    {
+      "epoch": 0.010556220526945763,
+      "grad_norm": 0.5295783281326294,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 1.2777,
+      "step": 183
+    },
+    {
+      "epoch": 0.010729273322469464,
+      "grad_norm": 0.5361846089363098,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 1.1756,
+      "step": 186
+    },
+    {
+      "epoch": 0.010902326117993164,
+      "grad_norm": 0.42806971073150635,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 1.2366,
+      "step": 189
+    },
+    {
+      "epoch": 0.011075378913516865,
+      "grad_norm": 0.45333951711654663,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 1.0958,
+      "step": 192
+    },
+    {
+      "epoch": 0.011248431709040567,
+      "grad_norm": 0.8909216523170471,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 1.1446,
+      "step": 195
+    },
+    {
+      "epoch": 0.011421484504564268,
+      "grad_norm": 0.8104519248008728,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 1.4137,
+      "step": 198
+    },
+    {
+      "epoch": 0.011536853034913402,
+      "eval_loss": 1.135033369064331,
+      "eval_runtime": 500.4661,
+      "eval_samples_per_second": 58.34,
+      "eval_steps_per_second": 14.586,
+      "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": 1.0303319310336e+16,
+  "total_flos": 1.3737759080448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null