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:f489643489a0f7c9f4321a8367ec8ce0150b6aa93df65ccec9d3d6cb01d36f57
+oid sha256:871e52c1b745337abe3009034da2bca20cb3cf4aac3f5b2beb474b06763fdd7c
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb22efe3ab196e56f50880c2d5f0b05d1786fb93688cace7c8560ab4a486031
+oid sha256:4f4614e153cda11c062626e2d45d38989726f059ff4bdb6dee5b58400e793853
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809f732c428dea9f6c29f2aa17020db5eaeae79e98c4d1c135ce72b5dde9516e
+oid sha256:f144139589cfb22818ed7e3cdabde609bb2af88714153eca49ebd5a4a8ab9bbf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5ad005f18ad2c3c460e78d824d33373300bb1b0c9741a994c687b284a694890
+oid sha256:c9b2510d4f3300d86de2c5b705a4b3113b18ea2234bf5e3432bd4dee5175a4db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.6877731084823608,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.09715812484819043,
+  "epoch": 0.12144765606023804,
   "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": 16.748,
       "eval_steps_per_second": 4.192,
       "step": 200
+    },
+    {
+      "epoch": 0.10201603109059995,
+      "grad_norm": 15.680115699768066,
+      "learning_rate": 0.00014599467139909136,
+      "loss": 2.9233,
+      "step": 210
+    },
+    {
+      "epoch": 0.10687393733300947,
+      "grad_norm": 14.90787410736084,
+      "learning_rate": 0.0001395225692317151,
+      "loss": 2.299,
+      "step": 220
+    },
+    {
+      "epoch": 0.11173184357541899,
+      "grad_norm": 24.221662521362305,
+      "learning_rate": 0.00013286522492905717,
+      "loss": 3.2907,
+      "step": 230
+    },
+    {
+      "epoch": 0.11658974981782852,
+      "grad_norm": 21.316699981689453,
+      "learning_rate": 0.00012605507240336626,
+      "loss": 3.3841,
+      "step": 240
+    },
+    {
+      "epoch": 0.12144765606023804,
+      "grad_norm": 24.28824234008789,
+      "learning_rate": 0.00011912529003319345,
+      "loss": 2.8327,
+      "step": 250
+    },
+    {
+      "epoch": 0.12144765606023804,
+      "eval_loss": 1.6964420080184937,
+      "eval_runtime": 51.7608,
+      "eval_samples_per_second": 16.75,
+      "eval_steps_per_second": 4.192,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.57749502246912e+16,
+  "total_flos": 4.4718687780864e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null