Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7580bea5e2dd5989e3d5b860b453ccaf7991e93a8bf272eeab36433cf7aad3
+oid sha256:fe3d31d3daec405b0931f2159532beaf2d0519e08a194a811e7291790e04df06
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5eba6eba00a92a49125c573803c23f3ddbcd3787382b0e303221f79a5b7882
+oid sha256:9c7184a7ff07c2567cbcf710cc36fd4884d228150e28e08d89e414de3fba0f71
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5016d318ca8e3d6b8ca4b2a60622ca780cb9ab30c6b1c3967b8626d3aa409c3
+oid sha256:cac8f850acca46a552006ff5c648e435d49743086920a562138c2052b8f6ea77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0106983184814453,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 1.9864908456802368,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02577873254564984,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 3.894,
       "eval_steps_per_second": 1.947,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 1.8552119731903076,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.3037,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 1.9844423532485962,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0401,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 1.9918729066848755,
+      "eval_runtime": 124.9077,
+      "eval_samples_per_second": 3.923,
+      "eval_steps_per_second": 1.961,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 1.1682435274124146,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.9047,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 1.5561579465866089,
+      "learning_rate": 0.0,
+      "loss": 1.9895,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 1.9864908456802368,
+      "eval_runtime": 125.3271,
+      "eval_samples_per_second": 3.91,
+      "eval_steps_per_second": 1.955,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.483774567120896e+16,
+  "total_flos": 2.225661850681344e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null