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:c49eca6f0e15050bbf85e7bdcee025bf385fa39adb9ceb30813cd32b23a5cdad
+oid sha256:fccb2ba22b5b6dfa991a413189b90560425f4111aa5ce1364f396c248a1f28b6
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b39ecfdf33409025f4b60db0fba2c848eb0dd2f9ac9c92ec7946ef2eef2394
+oid sha256:573648a468af742a07a6a14344cffe2bff51546a70328b7c583a6d1a9a0552e1
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f51136095b7fc6d10a6bb7fc123482a16d9870f2a5453d8d83fc637dd1ee7e
+oid sha256:b709956ff6cbda6fd110c175a6bf0de5821f4a3bd4f0fc71f5f9a4bdafe0ae45
 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": 1.938501000404358,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008506113769271665,
+  "best_metric": 1.9379709959030151,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01063264221158958,
   "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": 10.284,
       "eval_steps_per_second": 5.142,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": Infinity,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.7604,
+      "step": 21
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "grad_norm": Infinity,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.0637,
+      "step": 22
+    },
+    {
+      "epoch": 0.009782030834662414,
+      "grad_norm": Infinity,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.893,
+      "step": 23
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": Infinity,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.1805,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 1.826,
+      "step": 25
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 1.9379709959030151,
+      "eval_runtime": 93.7663,
+      "eval_samples_per_second": 10.558,
+      "eval_steps_per_second": 5.279,
+      "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": 1003983514632192.0,
+  "total_flos": 1253380693426176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null