Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dbf8c6e0e171848caa7f36a646de50bb478599e6bc2d29a74ba9ac86ab970c0
+oid sha256:046108880ffccb7ed576634bed7dd0b7fbe390816bb7a4111d497023454883f0
 size 14293800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8608e52b83d9f0d6326604696bcb022ac343e6536708f8f48263220d8dd73e6c
+oid sha256:847d2c8bd52f113731e40823ed450ebec785e5a88852519be0e9bdc0c0f6b0c0
 size 7579748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b014975fc6fe01bc747fcabac49eb3b60c5c8a7a3c91657e5b0b4af75e4149
+oid sha256:4bdfdb504078549847ef7ee4375e661b993dec081f4a7f670cbcbccd1d6499a0
 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": 2.962515354156494,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.016687526074259492,
+  "best_metric": 2.866241693496704,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.020859407592824362,
   "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": 8.694,
       "eval_steps_per_second": 4.356,
       "step": 20
+    },
+    {
+      "epoch": 0.017521902377972465,
+      "grad_norm": 25.836143493652344,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 12.1192,
+      "step": 21
+    },
+    {
+      "epoch": 0.01835627868168544,
+      "grad_norm": 28.20415496826172,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 13.863,
+      "step": 22
+    },
+    {
+      "epoch": 0.019190654985398414,
+      "grad_norm": 30.93284034729004,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 8.6966,
+      "step": 23
+    },
+    {
+      "epoch": 0.02002503128911139,
+      "grad_norm": 28.23725128173828,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 16.9035,
+      "step": 24
+    },
+    {
+      "epoch": 0.020859407592824362,
+      "grad_norm": 28.64270782470703,
+      "learning_rate": 0.0,
+      "loss": 11.5796,
+      "step": 25
+    },
+    {
+      "epoch": 0.020859407592824362,
+      "eval_loss": 2.866241693496704,
+      "eval_runtime": 58.167,
+      "eval_samples_per_second": 8.682,
+      "eval_steps_per_second": 4.35,
+      "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": 150858041917440.0,
+  "total_flos": 188572552396800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null