Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8372413b9b662bd61a319e442b8904bfa1061b536a2b13a49d29100186dc5848
+oid sha256:dfe2cbf9677fb6aa10f1669a2a99f087378cb1ac9d724b57b5f472df00fff23a
 size 9047632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62eecb9ce0927ca9fbeb3440c6d761ff8f559c99a57656179da87db55e5362e1
+oid sha256:62a3ca6703e728c4266299b7f4a719dc8f0e3ebdfab843a9a60e4181a5f21fe3
 size 4628218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c6c8bcdc4bb96578fa463048efa4345f39c02e5304e2fc020bc39e3c8ba334
+oid sha256:bd9e8cf707aa5af47b78871671eda38069f38f45787ed0bbd9ca3e81ded08e0a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f89a0d9cc69b5fdf0cd3ece03dd2869c5ec0e6029575a4496ea2556359539ad
+oid sha256:05d63688a697a579ea602c9246c5261e5aa082fc650a107f52a0a175ef1d7c1f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.534428119659424,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.5905511811023622,
+  "best_metric": 2.432068347930908,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.7874015748031497,
   "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": 264.174,
       "eval_steps_per_second": 66.661,
       "step": 150
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 2.376530647277832,
+      "learning_rate": 9.341239704420797e-05,
+      "loss": 2.5895,
+      "step": 160
+    },
+    {
+      "epoch": 0.6692913385826772,
+      "grad_norm": 2.278172731399536,
+      "learning_rate": 7.735489155732317e-05,
+      "loss": 2.492,
+      "step": 170
+    },
+    {
+      "epoch": 0.7086614173228346,
+      "grad_norm": 3.1601502895355225,
+      "learning_rate": 6.198722326955761e-05,
+      "loss": 2.3795,
+      "step": 180
+    },
+    {
+      "epoch": 0.7480314960629921,
+      "grad_norm": 3.5553319454193115,
+      "learning_rate": 4.767313037970613e-05,
+      "loss": 2.2905,
+      "step": 190
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "grad_norm": 5.693742275238037,
+      "learning_rate": 3.4751413951641655e-05,
+      "loss": 2.2922,
+      "step": 200
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "eval_loss": 2.432068347930908,
+      "eval_runtime": 0.4175,
+      "eval_samples_per_second": 256.306,
+      "eval_steps_per_second": 64.675,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 174703745433600.0,
+  "total_flos": 233125576704000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null