Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25981f35a4754d971392d994257c3d1221a2307dad4d1a59ef48ed23ee5c6971
+oid sha256:aa23ee59def527a462c9e13004dc094aabf54f235e0dd00e852cff1b327f260f
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:220243e7d356f2d02423336356de64b20b477016d893ca0413017368cf5d6afc
+oid sha256:14a8e3723c2c16ad97ea28e9c4cdb3fa7c114e76d56861324fa38cd7e5e46456
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53857b31065290226097899a29c43817f42b59cc1033072766ec46b6e8e362ce
+oid sha256:98e41df5f771584bb63c4aed1116817e1f4c07c6c2296db725d83962a1293b12
 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": 0.5666860342025757,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010892652905615163,
+  "best_metric": 0.5442796945571899,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0013615816132018952,
   "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": 4.138,
       "eval_steps_per_second": 2.069,
       "step": 20
+    },
+    {
+      "epoch": 0.001143728555089592,
+      "grad_norm": 3.8364763259887695,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.6054,
+      "step": 21
+    },
+    {
+      "epoch": 0.001198191819617668,
+      "grad_norm": 6.406091213226318,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4582,
+      "step": 22
+    },
+    {
+      "epoch": 0.0012526550841457436,
+      "grad_norm": 3.415294885635376,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.4367,
+      "step": 23
+    },
+    {
+      "epoch": 0.0013071183486738195,
+      "grad_norm": 5.632196426391602,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.8343,
+      "step": 24
+    },
+    {
+      "epoch": 0.0013615816132018952,
+      "grad_norm": 4.169218063354492,
+      "learning_rate": 0.0,
+      "loss": 0.3636,
+      "step": 25
+    },
+    {
+      "epoch": 0.0013615816132018952,
+      "eval_loss": 0.5442796945571899,
+      "eval_runtime": 1875.2436,
+      "eval_samples_per_second": 4.123,
+      "eval_steps_per_second": 2.062,
+      "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": 3822182832537600.0,
+  "total_flos": 4777728540672000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null