Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f19c0209adf85e51c88ccfe69de41ca345598c3b30099a717c388d0e71bddb8
+oid sha256:224f42d8f85d9208a81003f7927c51f3b8516a7ec1553c9c55aea16fa4cb6c08
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc7235cbd47d156793ee982a3a481a3fbc2ddfcaf1d0208e641a517e25699c5f
+oid sha256:28dd83e99c973e0ce19a2bf443cdad30a179aef270962df457b342aaad88ec0a
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ccd5622448d5b4793f7c0320456317dd3c53025e79a98eaa0b1029556f2441
+oid sha256:f80d4352855da85e9983490aa4fdcaeaba5be1ffe56258d0c48d0c25a113bc64
 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": 4.010801315307617,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012053638692180202,
+  "best_metric": 3.977468490600586,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.015067048365225252,
   "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": 8.585,
       "eval_steps_per_second": 4.299,
       "step": 20
+    },
+    {
+      "epoch": 0.012656320626789211,
+      "grad_norm": 3.2454922199249268,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.2878,
+      "step": 21
+    },
+    {
+      "epoch": 0.013259002561398222,
+      "grad_norm": 3.833118438720703,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.5356,
+      "step": 22
+    },
+    {
+      "epoch": 0.013861684496007233,
+      "grad_norm": 3.015711784362793,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.0388,
+      "step": 23
+    },
+    {
+      "epoch": 0.014464366430616242,
+      "grad_norm": 2.6508641242980957,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.9127,
+      "step": 24
+    },
+    {
+      "epoch": 0.015067048365225252,
+      "grad_norm": 4.65998649597168,
+      "learning_rate": 0.0,
+      "loss": 4.1332,
+      "step": 25
+    },
+    {
+      "epoch": 0.015067048365225252,
+      "eval_loss": 3.977468490600586,
+      "eval_runtime": 77.4804,
+      "eval_samples_per_second": 9.022,
+      "eval_steps_per_second": 4.517,
+      "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": 180302281703424.0,
+  "total_flos": 224821363605504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null