Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9780cd9fd17d34b215bd36bd9703f810abbb1444351ee0c8888d1123900b1d2d
+oid sha256:6f2d615f87b08f8e8f1a1ec8bc9d0119f3debd37647c9f74a50401ab62fb1dc7
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c17a76ee31c5f7653f58e7216514baafb46d1007dfa727a27d3ceece4a96745a
+oid sha256:b95380f19d8c7479944c49a9258f0ba601397c3f38234b9e6a16ba8ce4e0f673
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf355fd48ca7fbf33eb7fc35115a0613a7bff5e1759da5fa0cb1ec53729b7e7
+oid sha256:0f961351929a5df16fd6f95a46d2cc68ae8eb220a0a4dcd52e4105e45b02d8ec
 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": 1.4640228748321533,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 1.4572163820266724,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.021482277121374866,
   "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": 11.008,
       "eval_steps_per_second": 5.504,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 0.1899358034133911,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.3502,
+      "step": 21
+    },
+    {
+      "epoch": 0.01890440386680988,
+      "grad_norm": 0.18288901448249817,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.4681,
+      "step": 22
+    },
+    {
+      "epoch": 0.019763694951664877,
+      "grad_norm": 0.18912482261657715,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.4683,
+      "step": 23
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 0.21653838455677032,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.4228,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "grad_norm": 0.20494642853736877,
+      "learning_rate": 0.0,
+      "loss": 1.4457,
+      "step": 25
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 1.4572163820266724,
+      "eval_runtime": 44.5699,
+      "eval_samples_per_second": 10.994,
+      "eval_steps_per_second": 5.497,
+      "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": 1023167913000960.0,
+  "total_flos": 1278959891251200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null