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:c8f07c25b525bc099b7af01d942900e8d0b4493d9c375855e8997d633c81f1d5
+oid sha256:58873015c8ce923c1705d303bf1e57ac3d083fc8c8d12d93e0b77f93f40f0fb7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:939b96c1d990cc1cc5705fef699d70c37338ca6a1d6aeac472110a4971816b75
+oid sha256:e35023a7462a83ae6077b4b607e6f9c38f34f483fdb2c1527d74d72ef33ba483
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:c18d7e756a20859618d3fcce0c6bd2efae1a4202114489dc7f99bc851f6958cd
 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": 0.30053460597991943,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.013157894736842105,
+  "best_metric": 0.29195284843444824,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01644736842105263,
   "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": 4.966,
       "eval_steps_per_second": 2.483,
       "step": 20
+    },
+    {
+      "epoch": 0.01381578947368421,
+      "grad_norm": 0.4335065186023712,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.207,
+      "step": 21
+    },
+    {
+      "epoch": 0.014473684210526316,
+      "grad_norm": 0.4096187651157379,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0894,
+      "step": 22
+    },
+    {
+      "epoch": 0.015131578947368421,
+      "grad_norm": 0.3267219066619873,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.3022,
+      "step": 23
+    },
+    {
+      "epoch": 0.015789473684210527,
+      "grad_norm": 0.3841478228569031,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.3776,
+      "step": 24
+    },
+    {
+      "epoch": 0.01644736842105263,
+      "grad_norm": 0.37570875883102417,
+      "learning_rate": 0.0,
+      "loss": 0.2774,
+      "step": 25
+    },
+    {
+      "epoch": 0.01644736842105263,
+      "eval_loss": 0.29195284843444824,
+      "eval_runtime": 125.2988,
+      "eval_samples_per_second": 5.108,
+      "eval_steps_per_second": 2.554,
+      "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": 7398256992583680.0,
+  "total_flos": 9201582134525952.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null