Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006fdc03a4490ea6e19aebd8227fe78d79cd896b2d64209f83adcc2546367baf
+oid sha256:60d5ae60b21dd2e2ebbc7aca0853e94aca3fb0a0a4b25cacada84092c7755c52
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3b8ee5e4a7275e055c83ffa1c9b42439b2ecd17790928fb2c6b701996f18ff2
+oid sha256:14458b34bb9784f1ddc23c5814a50d6e00966e4c23c684368cdf80fcb5079239
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:813842ccb6a5606b7a8ab80f7e71675de76d6f9db7f73c390878b4b9232afa2e
+oid sha256:4a753380d8a37c9bbb214fefa6e93caa8547bf6973381f4f1c49dcc6609cb0d3
 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": 0.4118092954158783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0935672514619883,
+  "best_metric": 0.4004042446613312,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.11695906432748537,
   "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": 7.954,
       "eval_steps_per_second": 3.977,
       "step": 20
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 1.1064636707305908,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.5972,
+      "step": 21
+    },
+    {
+      "epoch": 0.10292397660818714,
+      "grad_norm": 0.8715364933013916,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.5976,
+      "step": 22
+    },
+    {
+      "epoch": 0.10760233918128655,
+      "grad_norm": 0.8745983242988586,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.7106,
+      "step": 23
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 0.9908772110939026,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.6989,
+      "step": 24
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "grad_norm": 0.8052089214324951,
+      "learning_rate": 0.0,
+      "loss": 1.2794,
+      "step": 25
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "eval_loss": 0.4004042446613312,
+      "eval_runtime": 11.3236,
+      "eval_samples_per_second": 7.948,
+      "eval_steps_per_second": 3.974,
+      "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": 2845655470964736.0,
+  "total_flos": 3488222835376128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null