Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0781d9226c5e87a761b7b5906e43f7366919836cf593207a1410082f047422
+oid sha256:233d86f9e043afabf4b8b6232a10d25f8076917f650d96b76a6a6151e6df4392
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddde4dddfb48ce92e44d31f4cc08b35b49e611d089eeca59efacd9bbf276989
+oid sha256:fc348c77465d2c6542383a3ac289be87aa66584b8f26daff33d78bab9bbf70d9
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb513f73c05e47ca2c387863211023105d6a3148f4d95cc6e4456de6d486c5d
+oid sha256:ee3d3e3a9dfc905abebb8950ceed47a257408006e3af77a24a02733369cea165
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7fb5f22874147e56941b0c2b0e6e106f9317ff78b343462a5df511f2b8d1e2
+oid sha256:6d3338a58e0bfbbf42753b4e3cd5016702f7cda5f6424a907d04dafd472f305e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.35164520144462585,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.18393623543838136,
+  "best_metric": 0.2690972089767456,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.2145922746781116,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 16.187,
       "eval_steps_per_second": 4.053,
       "step": 300
+    },
+    {
+      "epoch": 0.1900674432863274,
+      "grad_norm": 0.981971800327301,
+      "learning_rate": 7.997724001423507e-05,
+      "loss": 0.3302,
+      "step": 310
+    },
+    {
+      "epoch": 0.19619865113427346,
+      "grad_norm": 1.1474406719207764,
+      "learning_rate": 7.289870709344306e-05,
+      "loss": 0.2733,
+      "step": 320
+    },
+    {
+      "epoch": 0.2023298589822195,
+      "grad_norm": 1.0042413473129272,
+      "learning_rate": 6.597900439462128e-05,
+      "loss": 0.2392,
+      "step": 330
+    },
+    {
+      "epoch": 0.20846106683016555,
+      "grad_norm": 1.0399328470230103,
+      "learning_rate": 5.9251844013752326e-05,
+      "loss": 0.2247,
+      "step": 340
+    },
+    {
+      "epoch": 0.2145922746781116,
+      "grad_norm": 2.1786627769470215,
+      "learning_rate": 5.275000000000002e-05,
+      "loss": 0.326,
+      "step": 350
+    },
+    {
+      "epoch": 0.2145922746781116,
+      "eval_loss": 0.2690972089767456,
+      "eval_runtime": 42.4522,
+      "eval_samples_per_second": 16.183,
+      "eval_steps_per_second": 4.052,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.666354130164122e+16,
+  "total_flos": 6.609175116880282e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null