Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe975f9b7debd0c78a84523c58ddf29def66d77579edeefa33c8fd912dc2c31
+oid sha256:e268913740361921f99a4cf1b60b4894c80112c7142d2c1c0a9bc68549b0a6be
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a169cd5c20c772032249100d163d632e0429fc8136a326ae083a822fda9150d
+oid sha256:6315aa1422c7251110801dfdbc6e8011cad19b41fac2e8347b787d02979db2ce
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b028a07eb9b8df202ab053169b8ccc289be0a99adacfd2f2461d86813bbc7e0a
+oid sha256:9cb142c662972fc894b04556cf7d57f95bcc2e88e3c53942c89789a796f594d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.18536759912967682,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0033819488480236735,
+  "best_metric": 0.16695956885814667,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.004227436060029592,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 8.898,
       "eval_steps_per_second": 4.449,
       "step": 20
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 6.975110054016113,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.6873,
+      "step": 21
+    },
+    {
+      "epoch": 0.003720143732826041,
+      "grad_norm": 5.249928951263428,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4136,
+      "step": 22
+    },
+    {
+      "epoch": 0.0038892411752272245,
+      "grad_norm": 4.379932403564453,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.3382,
+      "step": 23
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 0.7862380146980286,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0129,
+      "step": 24
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "grad_norm": 2.2497642040252686,
+      "learning_rate": 0.0,
+      "loss": 0.0801,
+      "step": 25
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "eval_loss": 0.16695956885814667,
+      "eval_runtime": 281.9052,
+      "eval_samples_per_second": 8.833,
+      "eval_steps_per_second": 4.416,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 202561822654464.0,
+  "total_flos": 258210675032064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null