Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9a60183d6357e9d76e7fb5ed62331597023349752d24d2d06f10ef425f6c61
+oid sha256:2be317fddf501f99980ba3ed251e15202e2d328121e74f70083b8b088c15e043
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9fb69bbe4ff728742c2fac869caae052a239319e5d8e879e1361b6801760d33
+oid sha256:d783fd6b3ed498dc999a1ad5d0e858dec3aec893e3c5a35fe222e6c7b83f7a83
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266ab93c9e14590f1e60d99c86b6237155e03af842fdc723952273962820feed
+oid sha256:60e2baccb756262de6ad99cf7b62b8e4035c6738812e1268d030ed7a22b411e7
 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": 0.1798376888036728,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.021923814743765414,
+  "best_metric": 0.17813163995742798,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02740476842970677,
   "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": 3.259,
       "eval_steps_per_second": 1.634,
       "step": 20
+    },
+    {
+      "epoch": 0.023020005480953686,
+      "grad_norm": 1.0170478820800781,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0845,
+      "step": 21
+    },
+    {
+      "epoch": 0.024116196218141955,
+      "grad_norm": 0.3763718008995056,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0228,
+      "step": 22
+    },
+    {
+      "epoch": 0.025212386955330228,
+      "grad_norm": 0.7820136547088623,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.1405,
+      "step": 23
+    },
+    {
+      "epoch": 0.026308577692518497,
+      "grad_norm": 0.37036749720573425,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0446,
+      "step": 24
+    },
+    {
+      "epoch": 0.02740476842970677,
+      "grad_norm": 1.084715723991394,
+      "learning_rate": 0.0,
+      "loss": 0.1678,
+      "step": 25
+    },
+    {
+      "epoch": 0.02740476842970677,
+      "eval_loss": 0.17813163995742798,
+      "eval_runtime": 121.1805,
+      "eval_samples_per_second": 3.177,
+      "eval_steps_per_second": 1.593,
+      "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": 5363736319623168.0,
+  "total_flos": 6658431293325312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null