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:de741ef7f34a5eb7de98448fda69402f3b613549cb58dc7303e87f6cde138f8b
+oid sha256:cf35cfe3b9a50e70a0712a415dbd8bd76f50905539fdfdeab73cddbd95d38048
 size 58680

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f7b8a11f097eb57a6b8a9d16d6cf63426a1290306dca39c128a5ba493e953a
+oid sha256:93d5957c71bd06fba1276eafd7e78c4b10c0e4e3cb7afddda0ed8e3da69e4592
 size 127270

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ced3441efbaac8e8068b5e942efb4d6961a89dd8de37cdf9f39574a4495d7e
+oid sha256:2225fbf78fde67ea9a13b91d4f7da0650f3ce0c4ea5108923a96270e9e8151af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e883b7b3f89fde3f0f981a15cfeb8504571510ffa0b99f735bed98a1fe00478
+oid sha256:d5ad005f18ad2c3c460e78d824d33373300bb1b0c9741a994c687b284a694890
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.306268692016602,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.004214726253529834,
+  "best_metric": 10.305092811584473,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.005619635004706444,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 250.492,
       "eval_steps_per_second": 62.635,
       "step": 150
+    },
+    {
+      "epoch": 0.004495708003765155,
+      "grad_norm": 0.18568071722984314,
+      "learning_rate": 0.00017451298973437308,
+      "loss": 20.6288,
+      "step": 160
+    },
+    {
+      "epoch": 0.004776689754000477,
+      "grad_norm": 0.2910362184047699,
+      "learning_rate": 0.0001694167565454241,
+      "loss": 20.611,
+      "step": 170
+    },
+    {
+      "epoch": 0.0050576715042357995,
+      "grad_norm": 0.2217985987663269,
+      "learning_rate": 0.0001639896397455543,
+      "loss": 20.618,
+      "step": 180
+    },
+    {
+      "epoch": 0.005338653254471122,
+      "grad_norm": 0.19911141693592072,
+      "learning_rate": 0.0001582580797022808,
+      "loss": 20.6091,
+      "step": 190
+    },
+    {
+      "epoch": 0.005619635004706444,
+      "grad_norm": 0.28544291853904724,
+      "learning_rate": 0.00015225,
+      "loss": 20.6026,
+      "step": 200
+    },
+    {
+      "epoch": 0.005619635004706444,
+      "eval_loss": 10.305092811584473,
+      "eval_runtime": 60.5578,
+      "eval_samples_per_second": 247.45,
+      "eval_steps_per_second": 61.875,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6381069926400.0,
+  "total_flos": 8551150387200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null