Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52bb1d26060239e58164eb03f2386dd1ec2e412097c36c49bba870df9118ad33
+oid sha256:2201ef89579084e6f72b6a89b42bd7057e17dd625179865235a10d9bc38ac79c
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d7e7b25f1d417aa6bf1615e6ed5d21acddb4a4559e62576a2a877b474b198a2
+oid sha256:9f051bf202a58bbceb091d72a4decedc53556fb9b7e5aecad9947a1b132f435c
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ab209838259e7b50cc05a89d606efd726aa97c9f623e208163f65fb13a4757
+oid sha256:3d0b3a9283a118d92a02bc729c5f2c8c48f3775a9284ab2addc546ffea410f49
 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": 2.060356855392456,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07582938388625593,
+  "best_metric": 2.0514931678771973,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0947867298578199,
   "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": 6.97,
       "eval_steps_per_second": 3.516,
       "step": 20
+    },
+    {
+      "epoch": 0.07962085308056872,
+      "grad_norm": 1.7252284288406372,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.8104,
+      "step": 21
+    },
+    {
+      "epoch": 0.08341232227488152,
+      "grad_norm": 1.7847933769226074,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.5733,
+      "step": 22
+    },
+    {
+      "epoch": 0.08720379146919431,
+      "grad_norm": 1.4043855667114258,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.5828,
+      "step": 23
+    },
+    {
+      "epoch": 0.0909952606635071,
+      "grad_norm": 1.2325977087020874,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.0929,
+      "step": 24
+    },
+    {
+      "epoch": 0.0947867298578199,
+      "grad_norm": 1.5775668621063232,
+      "learning_rate": 0.0,
+      "loss": 1.2883,
+      "step": 25
+    },
+    {
+      "epoch": 0.0947867298578199,
+      "eval_loss": 2.0514931678771973,
+      "eval_runtime": 14.9286,
+      "eval_samples_per_second": 7.435,
+      "eval_steps_per_second": 3.751,
+      "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": 1425277392519168.0,
+  "total_flos": 1775345524015104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null