Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bafa5ff1af4b67df238b235d97e93870cddbaa757335e8be9567992fc93d200
+oid sha256:1304561f6becfb7035c3c1e1ca67cea1cb1ecc1b8156d35cde46db6534c75cb4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ac5b1d2e6fd90a8000a0555b788667d5d6c473963782009169b55a4a1c460b
+oid sha256:dcd8e964078b86e4253b3121ac6d099fb0311b5c4254394a7ae52074ee22f272
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 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": 1.4961340427398682,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.044370493621741544,
+  "best_metric": 1.4826573133468628,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.05546311702717693,
   "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": 6.938,
       "eval_steps_per_second": 3.469,
       "step": 20
+    },
+    {
+      "epoch": 0.04658901830282862,
+      "grad_norm": 7.893642902374268,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.248,
+      "step": 21
+    },
+    {
+      "epoch": 0.048807542983915694,
+      "grad_norm": 4.949916839599609,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.6591,
+      "step": 22
+    },
+    {
+      "epoch": 0.051026067665002776,
+      "grad_norm": 3.629110097885132,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.6903,
+      "step": 23
+    },
+    {
+      "epoch": 0.05324459234608985,
+      "grad_norm": 3.409166097640991,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.4897,
+      "step": 24
+    },
+    {
+      "epoch": 0.05546311702717693,
+      "grad_norm": 3.813494920730591,
+      "learning_rate": 0.0,
+      "loss": 1.2999,
+      "step": 25
+    },
+    {
+      "epoch": 0.05546311702717693,
+      "eval_loss": 1.4826573133468628,
+      "eval_runtime": 27.6629,
+      "eval_samples_per_second": 6.868,
+      "eval_steps_per_second": 3.434,
+      "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": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null