Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b256205f69c17896f7f9088f79d8fd985882b751e29b2c896974443db092d65
+oid sha256:1df1c0cd5adb3dbbf0f4de7c2dd7828f36c8d194fa89237f17661c8ad9f09563
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a25e6358803c0b24daaad369b1758895f466ad8f6ec14b97259bc4e1a4fba2a
+oid sha256:2fef32cca4a06c03d66a92e2065e8a6eb83bab73c90a34be6ba8434d466a73c9
 size 25986468

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e48a86cb1ec4353aec4ebfc4d9626489ea8f8c134d8c68f77e6325eeca7793e
+oid sha256:712733c7b288bd068efed7c5fab75f847358c6461fa2ae6afefd659a7edea021
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a78bab0e108d3c186898a780257121eba92c7434d580326e33b855003a3757
+oid sha256:7720ce10f85dbd90d92bd34f3d3d0da56a95cd9c569195e83083bdc45d9452b4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2163466215133667,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.047934808660222095,
+  "best_metric": 1.2060250043869019,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.055923943436925784,
   "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": 53.655,
       "eval_steps_per_second": 13.419,
       "step": 300
+    },
+    {
+      "epoch": 0.049532635615562835,
+      "grad_norm": 0.38519808650016785,
+      "learning_rate": 8.035627906643523e-05,
+      "loss": 1.4363,
+      "step": 310
+    },
+    {
+      "epoch": 0.05113046257090357,
+      "grad_norm": 0.4723591208457947,
+      "learning_rate": 7.324419859625559e-05,
+      "loss": 1.3084,
+      "step": 320
+    },
+    {
+      "epoch": 0.05272828952624431,
+      "grad_norm": 0.6243221163749695,
+      "learning_rate": 6.629170109791332e-05,
+      "loss": 1.2501,
+      "step": 330
+    },
+    {
+      "epoch": 0.05432611648158504,
+      "grad_norm": 0.6776363849639893,
+      "learning_rate": 5.9532658440357784e-05,
+      "loss": 1.0853,
+      "step": 340
+    },
+    {
+      "epoch": 0.055923943436925784,
+      "grad_norm": 1.2277010679244995,
+      "learning_rate": 5.300000000000002e-05,
+      "loss": 1.0173,
+      "step": 350
+    },
+    {
+      "epoch": 0.055923943436925784,
+      "eval_loss": 1.2060250043869019,
+      "eval_runtime": 49.0653,
+      "eval_samples_per_second": 53.704,
+      "eval_steps_per_second": 13.431,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8402222601732096.0,
+  "total_flos": 9791870443978752.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null