Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3413bb852d3f9c69759913ff1076b77ba36a5ec4a0ad8ad69d68604a66c4f181
+oid sha256:141f7091203cb770317fc79e1960b770a26609e578a49f778ecc21d4ad7618fe
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da45b4ee29c8b70b56d351b44006233a3dbecf9991e2e1ae84a60053ad095b73
+oid sha256:989a29f7e09b714bdcb0db863d38a1467b320418ee3d878b317fef2b0994eb50
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1e75550467bdce903818aa67d91dcfb4935ee2a62140d5762c3edc6bc01908d
+oid sha256:46b12ebbd2881d8ba677d76b515131b9cfadfbea8e49f9e25937c5ca307e97c1
 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": 0.004581085871905088,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.02294630564479119,
+  "epoch": 0.028682882055988984,
   "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": 16.701,
       "eval_steps_per_second": 4.178,
       "step": 200
+    },
+    {
+      "epoch": 0.024093620927030747,
+      "grad_norm": 0.02351466752588749,
+      "learning_rate": 0.00014815222811927496,
+      "loss": 0.0411,
+      "step": 210
+    },
+    {
+      "epoch": 0.025240936209270308,
+      "grad_norm": 0.11702999472618103,
+      "learning_rate": 0.00014158447912183896,
+      "loss": 0.0032,
+      "step": 220
+    },
+    {
+      "epoch": 0.026388251491509866,
+      "grad_norm": 0.01888689026236534,
+      "learning_rate": 0.00013482875042061958,
+      "loss": 0.0005,
+      "step": 230
+    },
+    {
+      "epoch": 0.027535566773749427,
+      "grad_norm": 0.08518572896718979,
+      "learning_rate": 0.00012791795524676576,
+      "loss": 0.0039,
+      "step": 240
+    },
+    {
+      "epoch": 0.028682882055988984,
+      "grad_norm": 0.021077927201986313,
+      "learning_rate": 0.00012088576229969385,
+      "loss": 0.0005,
+      "step": 250
+    },
+    {
+      "epoch": 0.028682882055988984,
+      "eval_loss": 0.007498083636164665,
+      "eval_runtime": 219.6624,
+      "eval_samples_per_second": 16.707,
+      "eval_steps_per_second": 4.179,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.759118211874816e+16,
+  "total_flos": 4.701119465914368e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null