Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719f29ee76f559420eb591897ff5f9c634ce02ae11ea78bda0e8155ffb885da2
+oid sha256:822cbe05eb5d2b7c48eea57f9bcc0604768b02f91fe361a66bd8fcb5d79cad76
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b6a2ca44f804b8750b117ed7a187c1e09a380c456522ba74f2613fda283722
+oid sha256:bad73460f76e9cd71019dcba7d7f1b382123c13fb6650ee4221f1aff8c4611c6
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79d8bb6261ae6f0d6a70b8f218e7f74fad160365eb5f04ccbb70e24782bc98c
+oid sha256:06045bfda977b8c794d21c92a67b76b0c15a955b90c4b3bfcb8761ed94c6587d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a53e373878af8696de39d4b7adb8634138f0e346e89bffc05bcb76c7b6de169
+oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8955165147781372,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.026073069778052994,
+  "best_metric": 0.876220166683197,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.029332203500309618,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 14.461,
       "eval_steps_per_second": 3.615,
       "step": 400
+    },
+    {
+      "epoch": 0.02672489652250432,
+      "grad_norm": 2.0528738498687744,
+      "learning_rate": 1.9862232585005475e-05,
+      "loss": 0.7577,
+      "step": 410
+    },
+    {
+      "epoch": 0.027376723266955644,
+      "grad_norm": 1.3070178031921387,
+      "learning_rate": 1.58029979997317e-05,
+      "loss": 0.7595,
+      "step": 420
+    },
+    {
+      "epoch": 0.02802855001140697,
+      "grad_norm": 2.6197099685668945,
+      "learning_rate": 1.2173450342671593e-05,
+      "loss": 0.7412,
+      "step": 430
+    },
+    {
+      "epoch": 0.028680376755858293,
+      "grad_norm": 2.77477765083313,
+      "learning_rate": 8.991272405169498e-06,
+      "loss": 0.9327,
+      "step": 440
+    },
+    {
+      "epoch": 0.029332203500309618,
+      "grad_norm": 4.5697340965271,
+      "learning_rate": 6.271967438265535e-06,
+      "loss": 1.0734,
+      "step": 450
+    },
+    {
+      "epoch": 0.029332203500309618,
+      "eval_loss": 0.876220166683197,
+      "eval_runtime": 443.5926,
+      "eval_samples_per_second": 14.563,
+      "eval_steps_per_second": 3.641,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.303876499308544e+16,
+  "total_flos": 9.352345754271744e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null