Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744c6ef8436c08d0b50ef8d854de1e398a0c0d25b6141f5d2599c0b5c431295e
+oid sha256:e30629809685e73412febbb6b0b8b8dc758c944e3c996d3c5d738b636fbd9811
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1627fb9f0b6b149f60b0dc7c8a644212fe349b8a772cfc93a483187f55ae9b5
+oid sha256:11bef36a1353be5c37eb4c93e78306986396f09af750e280b2a32bc96781b568
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54926f81dba356f5ea2c0b8b8fcabfe7cd44c287b39f51ffbb0cc127dfc77c25
+oid sha256:b1613f6035b0a9c6523a952d21262f76e976f696b912bce578ca7d255d20dc78
 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": 1.2051751613616943,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0033819488480236735,
+  "best_metric": 1.1979334354400635,
+  "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": 10.227,
       "eval_steps_per_second": 5.113,
       "step": 20
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 0.4114494323730469,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2128,
+      "step": 21
+    },
+    {
+      "epoch": 0.003720143732826041,
+      "grad_norm": 0.36479702591896057,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.0317,
+      "step": 22
+    },
+    {
+      "epoch": 0.0038892411752272245,
+      "grad_norm": 0.3829120993614197,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.1817,
+      "step": 23
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 0.400522381067276,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.2204,
+      "step": 24
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "grad_norm": 0.39131632447242737,
+      "learning_rate": 0.0,
+      "loss": 1.2579,
+      "step": 25
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "eval_loss": 1.1979334354400635,
+      "eval_runtime": 251.7367,
+      "eval_samples_per_second": 9.891,
+      "eval_steps_per_second": 4.946,
+      "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": 657160837005312.0,
+  "total_flos": 819422772068352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null