Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71781d42ace147cda31792e9710c64ccef5ad279e057874d2fdb5c05cdd77a94
+oid sha256:3723a70af12c174850207bb910958eba19f87198a60ef977d34166068e898234
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:349e35314591f8d9888214f58d7087ae5eb21b817e819f2371e55c747e036769
+oid sha256:c5b349172a7af37c717da35c6a6bb53db643f5b092e677db78d7f07b8023a808
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc92e301fbaafcc2948b746381205b7802002ef36f94213e5f939ff71a55bd8
+oid sha256:0605594bde2f8468c4639d0a7dc6c86249c33b3ad2186b79d3154bcb254910d7
 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": 0.15883538126945496,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.014202023788389846,
+  "best_metric": 0.15553146600723267,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.017752529735487306,
   "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": 3.429,
       "eval_steps_per_second": 1.717,
       "step": 20
+    },
+    {
+      "epoch": 0.014912124977809338,
+      "grad_norm": 0.29583197832107544,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.1597,
+      "step": 21
+    },
+    {
+      "epoch": 0.015622226167228831,
+      "grad_norm": 0.20675452053546906,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.1089,
+      "step": 22
+    },
+    {
+      "epoch": 0.016332327356648323,
+      "grad_norm": 0.2454639971256256,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.1296,
+      "step": 23
+    },
+    {
+      "epoch": 0.017042428546067814,
+      "grad_norm": 0.2648043930530548,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.1249,
+      "step": 24
+    },
+    {
+      "epoch": 0.017752529735487306,
+      "grad_norm": 0.22896485030651093,
+      "learning_rate": 0.0,
+      "loss": 0.1387,
+      "step": 25
+    },
+    {
+      "epoch": 0.017752529735487306,
+      "eval_loss": 0.15553146600723267,
+      "eval_runtime": 172.9969,
+      "eval_samples_per_second": 3.428,
+      "eval_steps_per_second": 1.717,
+      "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": 7234687501074432.0,
+  "total_flos": 8876602394935296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null