Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce65fe5efb6992c37767cc647a3c029a01aea16ffea7857be16a9901fd52044
+oid sha256:d04616e6c9686651e05f84b2adc3fb90f7d6e048cf74d21563c6d943bcf92852
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b53f159ef1f9c4e7bd20a321ce56f1c9f0351711488fab70880cd2e72e306f
+oid sha256:01321ee8817ba8cbfc6b83e36bb9e16d95f16224618253ce7a07e38446310da7
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c84a67128ae6918b79c3715f16531616a7fd438c0472b14975d8be4f346d1720
+oid sha256:eb645e3b6031e469fc3dcf414b1ef1eace69472cb72bdef1b342fb8a8df199b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1164ae497156bc73ad6aea2c09c8b9bf103d80abc111b82a8d3df6753edffe06
+oid sha256:eb9254c45787266aeb2f2d77203ac5705f2dafc0eddb0332e9ac78a896bc3b27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7171608209609985,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.05684240443370755,
+  "best_metric": 1.7082891464233398,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.07105300554213444,
   "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": 9.067,
       "eval_steps_per_second": 2.276,
       "step": 200
+    },
+    {
+      "epoch": 0.05968452465539292,
+      "grad_norm": 1.718658208847046,
+      "learning_rate": 0.00014815222811927496,
+      "loss": 1.7286,
+      "step": 210
+    },
+    {
+      "epoch": 0.0625266448770783,
+      "grad_norm": 2.2495739459991455,
+      "learning_rate": 0.00014158447912183896,
+      "loss": 1.5474,
+      "step": 220
+    },
+    {
+      "epoch": 0.06536876509876367,
+      "grad_norm": 2.8208131790161133,
+      "learning_rate": 0.00013482875042061958,
+      "loss": 1.3549,
+      "step": 230
+    },
+    {
+      "epoch": 0.06821088532044906,
+      "grad_norm": 1.70619535446167,
+      "learning_rate": 0.00012791795524676576,
+      "loss": 1.8743,
+      "step": 240
+    },
+    {
+      "epoch": 0.07105300554213444,
+      "grad_norm": 2.3366291522979736,
+      "learning_rate": 0.00012088576229969385,
+      "loss": 1.9315,
+      "step": 250
+    },
+    {
+      "epoch": 0.07105300554213444,
+      "eval_loss": 1.7082891464233398,
+      "eval_runtime": 81.785,
+      "eval_samples_per_second": 9.06,
+      "eval_steps_per_second": 2.274,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.482539204490035e+16,
+  "total_flos": 4.390310087177011e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null