Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f565d2f2fb56b975eee1c0fdd2865357f20351125e81f2362872b3319dbdef8
+oid sha256:b0481b5ca8346d348833ce29b2cd1076ec712c490662ad203abe71806f665a16
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0be19ce108370eb9631bb567807d44842275d7f3eb6532a08c3c255ff67c0ac6
+oid sha256:e672a88f3f71ae05fad228290bf3f3080a5852ef4152ea3e0ffb629d70c3042f
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2883b55283aa08466a16415bc71e27a29af0f45f41ed6640488845068b9b5ac7
+oid sha256:b952d5a70a5a965e35e81bb38f20959fc2fb4f3a1c60a6d3516d4316cdf76ca0
 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": 0.6037781834602356,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0035234529839242457,
+  "best_metric": 0.5760171413421631,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.004404316229905308,
   "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": 4.318,
       "eval_steps_per_second": 2.16,
       "step": 20
+    },
+    {
+      "epoch": 0.003699625633120458,
+      "grad_norm": 3.4255576133728027,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.5927,
+      "step": 21
+    },
+    {
+      "epoch": 0.0038757982823166702,
+      "grad_norm": 3.003241777420044,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.2529,
+      "step": 22
+    },
+    {
+      "epoch": 0.004051970931512883,
+      "grad_norm": 3.7899880409240723,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.617,
+      "step": 23
+    },
+    {
+      "epoch": 0.004228143580709095,
+      "grad_norm": 3.382770538330078,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.2677,
+      "step": 24
+    },
+    {
+      "epoch": 0.004404316229905308,
+      "grad_norm": 4.07171106338501,
+      "learning_rate": 0.0,
+      "loss": 2.2699,
+      "step": 25
+    },
+    {
+      "epoch": 0.004404316229905308,
+      "eval_loss": 0.5760171413421631,
+      "eval_runtime": 557.4206,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.146,
+      "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": 1.126858116562944e+16,
+  "total_flos": 1.412138652401664e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null