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:ef982679675501a02a84d942f1d90031076372874f6a8cc77d6393c7a897c593
+oid sha256:73a83f252d8b04c895504cee3f39d4a6c7d40cd3483a744d3a7954ca84999412
 size 1101095848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df287fc806d35c0fcf5b33ee6f529bcabbc5144c1f3111ab8bd9069f13f2bbae
+oid sha256:a00fa2c762f46a03f70372606e2f4f04477e09b2cc534bbdd0a6fb979be86e68
 size 559894228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98bbc5f0b528b79b46837ea53d9f093e9c34dc2503b0e2dce8ac4efe9607bf26
+oid sha256:efe8c2076c072af0d24cf5322844d1bdd0c354d93ecb584ce4f7a7db8e2d52b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126a95bf1277ff34f610ecef71ab3da4221c5fdf57145767d775e04c91223794
+oid sha256:180579b18c9e708a5cf9b411c96230bb3cb8d2c4c87c23004deaa70e5c990f72
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8360850811004639,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.004776974980593539,
+  "best_metric": 1.812909483909607,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.0059712187257419235,
   "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": 4.961,
       "eval_steps_per_second": 1.24,
       "step": 200
+    },
+    {
+      "epoch": 0.005015823729623216,
+      "grad_norm": 0.5694807171821594,
+      "learning_rate": 0.00015174815598624768,
+      "loss": 1.7452,
+      "step": 210
+    },
+    {
+      "epoch": 0.005254672478652893,
+      "grad_norm": 0.5760820508003235,
+      "learning_rate": 0.00014502099560537873,
+      "loss": 1.8861,
+      "step": 220
+    },
+    {
+      "epoch": 0.00549352122768257,
+      "grad_norm": 0.5834171772003174,
+      "learning_rate": 0.00013810129290655696,
+      "loss": 1.7734,
+      "step": 230
+    },
+    {
+      "epoch": 0.005732369976712247,
+      "grad_norm": 0.5962727069854736,
+      "learning_rate": 0.00013102275998576495,
+      "loss": 1.8497,
+      "step": 240
+    },
+    {
+      "epoch": 0.0059712187257419235,
+      "grad_norm": 0.572326123714447,
+      "learning_rate": 0.00012381988274386116,
+      "loss": 1.8388,
+      "step": 250
+    },
+    {
+      "epoch": 0.0059712187257419235,
+      "eval_loss": 1.812909483909607,
+      "eval_runtime": 1791.0601,
+      "eval_samples_per_second": 4.922,
+      "eval_steps_per_second": 1.231,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.00361135924183e+16,
+  "total_flos": 8.75670556681175e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null