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:ab1dce242d1dda912fc0deb254529be40ef6ca3d7f68068f80f39474093bb695
+oid sha256:766f7196e45b87387000801f7194bba316a2af8cf1f7d5f8419c0227de63ee93
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ad34551318871b35db8738a06cf061037555a7d91aa7efc922a1c0a84160eeb
+oid sha256:e2b57e67a324092ffb6a31803dabfc6c647a48b270cfeb915e1fe18a882bf0be
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac9ef8a8d750dd06f1b2f32aa7dc4ccd0792acf7e63e2006163d178a7597fee
+oid sha256:07ef33ef8c9bd3eab93359c523362a448c809b01d08be76655d89dddb1772720
 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": 2.391258716583252,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010182392098463731,
+  "best_metric": 2.384981155395508,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0012727990123079665,
   "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": 6.697,
       "eval_steps_per_second": 3.349,
       "step": 20
+    },
+    {
+      "epoch": 0.001069151170338692,
+      "grad_norm": 2.808321475982666,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.5224,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011200631308310104,
+      "grad_norm": 2.304232597351074,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.1882,
+      "step": 22
+    },
+    {
+      "epoch": 0.0011709750913233292,
+      "grad_norm": 2.0349557399749756,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.9905,
+      "step": 23
+    },
+    {
+      "epoch": 0.0012218870518156478,
+      "grad_norm": 2.6865811347961426,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.6934,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012727990123079665,
+      "grad_norm": 2.483696699142456,
+      "learning_rate": 0.0,
+      "loss": 2.3572,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012727990123079665,
+      "eval_loss": 2.384981155395508,
+      "eval_runtime": 1246.0304,
+      "eval_samples_per_second": 6.638,
+      "eval_steps_per_second": 3.319,
+      "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": 178076327608320.0,
+  "total_flos": 222595409510400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null