Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea95e02b53e84297322e25f83b6b42b73cc4df2c178b3683b80aab0b2f576eb
+oid sha256:54ccfc3986b143a4a2f96f549d098aa614f7f7aafd2890657bfdccb267a85f59
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905ccf5ea31257c3d87f2a56f33a2aded5fe7e6a5f48acbe10b90519195deb9b
+oid sha256:b567591f8cd8ea2446a2ceaf481a78303768763a4b7e2bb9a16792754e0908b8
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26af93fa51efe49b9e2140f982834d8563ac9574eccc808ced055984b884ad08
+oid sha256:222b56b9f8df0f0e53f193b41fb7b31d9e4883bc8c3809d0e1455a3588234cfb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1272f8845e0bcdb0442d607d302b013236cd341b15d2f9f81b4b66126029771
+oid sha256:4bf1a6f89c4ccfeb423775f70e378195af348273ade7a1d504b8ad665994fa62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3870110511779785,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.07256894049346879,
+  "best_metric": 2.3372433185577393,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.14513788098693758,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 11.789,
       "eval_steps_per_second": 2.968,
       "step": 50
+    },
+    {
+      "epoch": 0.08708272859216255,
+      "grad_norm": 1.203863263130188,
+      "learning_rate": 0.00021274057135267128,
+      "loss": 2.2284,
+      "step": 60
+    },
+    {
+      "epoch": 0.10159651669085631,
+      "grad_norm": 1.2065693140029907,
+      "learning_rate": 0.00021196354932097723,
+      "loss": 2.1552,
+      "step": 70
+    },
+    {
+      "epoch": 0.11611030478955008,
+      "grad_norm": 1.6284523010253906,
+      "learning_rate": 0.0002106727194781503,
+      "loss": 2.181,
+      "step": 80
+    },
+    {
+      "epoch": 0.13062409288824384,
+      "grad_norm": 1.8947309255599976,
+      "learning_rate": 0.00020887437061743096,
+      "loss": 2.1743,
+      "step": 90
+    },
+    {
+      "epoch": 0.14513788098693758,
+      "grad_norm": 3.7555911540985107,
+      "learning_rate": 0.00020657726411369925,
+      "loss": 2.1284,
+      "step": 100
+    },
+    {
+      "epoch": 0.14513788098693758,
+      "eval_loss": 2.3372433185577393,
+      "eval_runtime": 24.4036,
+      "eval_samples_per_second": 11.884,
+      "eval_steps_per_second": 2.991,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.319949381402624e+16,
+  "total_flos": 2.611614133203763e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null