Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309916b1006f2d69f89b39ff846e74b101329323107dc2f35283754a6abe6c34
+oid sha256:2958ef7928d42d39f72ee023b6e28ef4769c1b49583d5ff6aab778b434f8d174
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae69ad05cb0b6cc75b7cfa5fb775bfd1adb953043a1ba6eed53f697b432e592
+oid sha256:7ed1481e5abb077d9b40483275d6d09b48248b205ccf6eb7d0e0f30b37264fe8
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6364bb22c9c54e3924593b01d82be5f132212590d147a8728fef20641b8e19f2
+oid sha256:cc836fc73d9e93b435db16205a92787f798fa2d8d53f4ff715f4c6c6f3cc1719
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10d0fa96665f6b4af4824faec3d1d9f4e8b4343723a14d86cab932da6ce3225
+oid sha256:e7e4a8d9505ab5e0891e71b89f41010a5997ec96d8f1c5ec4c12ce973f5bf2fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2385743856430054,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.1305909239307868,
+  "best_metric": 1.2301549911499023,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.16323865491348352,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 61.256,
       "eval_steps_per_second": 15.32,
       "step": 200
+    },
+    {
+      "epoch": 0.13712047012732614,
+      "grad_norm": 0.06139560416340828,
+      "learning_rate": 0.00014845508703326504,
+      "loss": 1.1561,
+      "step": 210
+    },
+    {
+      "epoch": 0.14365001632386548,
+      "grad_norm": 0.07948515564203262,
+      "learning_rate": 0.00014373073204588556,
+      "loss": 1.2563,
+      "step": 220
+    },
+    {
+      "epoch": 0.15017956252040482,
+      "grad_norm": 0.14629638195037842,
+      "learning_rate": 0.00013888241754733208,
+      "loss": 1.3074,
+      "step": 230
+    },
+    {
+      "epoch": 0.15670910871694418,
+      "grad_norm": 0.3273250162601471,
+      "learning_rate": 0.00013392388661180303,
+      "loss": 1.288,
+      "step": 240
+    },
+    {
+      "epoch": 0.16323865491348352,
+      "grad_norm": 1.0025297403335571,
+      "learning_rate": 0.0001288691947339621,
+      "loss": 1.242,
+      "step": 250
+    },
+    {
+      "epoch": 0.16323865491348352,
+      "eval_loss": 1.2301549911499023,
+      "eval_runtime": 41.9764,
+      "eval_samples_per_second": 61.439,
+      "eval_steps_per_second": 15.366,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.250388414024909e+16,
+  "total_flos": 4.066988458927718e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null