Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a77fed259c972e234ad7bee9eab9b30073eac39bf8792d4165b4bfcbb98a2a0
+oid sha256:00a9561af355a8b156b0cae31a8b6f6bfffe95e4803f0d129cb44f4ab971e6a5
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a17c0e8eee48d21ba31168e602cc5f4e401ac99354655eef6665b9519b1124
+oid sha256:7cedf2b328c0dd109c733c3c9ef28f0c655b4506d982e651a3b9d7d4ae86d0ec
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257ca1b0d3e9dccbf8fc73d0b97408e446cac39effeb3308bb62443170577b4a
+oid sha256:17e2a62a89db7f985c275deb824923c8909e74aefd4f69d4f6625a6157c3c2e4
 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": 1.242295265197754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02476780185758514,
+  "best_metric": 1.1929755210876465,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.030959752321981424,
   "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": 6.482,
       "eval_steps_per_second": 3.241,
       "step": 20
+    },
+    {
+      "epoch": 0.026006191950464396,
+      "grad_norm": 2.0909576416015625,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.9691,
+      "step": 21
+    },
+    {
+      "epoch": 0.027244582043343655,
+      "grad_norm": 1.5691815614700317,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.8792,
+      "step": 22
+    },
+    {
+      "epoch": 0.02848297213622291,
+      "grad_norm": 2.304408550262451,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.231,
+      "step": 23
+    },
+    {
+      "epoch": 0.029721362229102165,
+      "grad_norm": 2.200516700744629,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.39,
+      "step": 24
+    },
+    {
+      "epoch": 0.030959752321981424,
+      "grad_norm": 1.8304818868637085,
+      "learning_rate": 0.0,
+      "loss": 1.0958,
+      "step": 25
+    },
+    {
+      "epoch": 0.030959752321981424,
+      "eval_loss": 1.1929755210876465,
+      "eval_runtime": 51.5945,
+      "eval_samples_per_second": 6.59,
+      "eval_steps_per_second": 3.295,
+      "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": 293468544958464.0,
+  "total_flos": 370192347561984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null