Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266b464db579b1ca3b17bae89f64d07932388924dc33369b5bb923c33509321b
+oid sha256:16e0a4d4c91f7899b419e3fa12a02390a5c8ba5e01b87865bbe14678f8eb1182
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfb340d467daddac8183ff1cb7f9d55d1dd44bf10bf9319597b8841a47c6433
+oid sha256:bebc95ae9ec034d8c9244da06d04922943cd36cb58c148b0304bb8babccec7e6
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
+oid sha256:983baa830df615f6f61b75af5f4b0cf7a694a7d02c96696d0f4804987ec72e0d
 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": 11.084075927734375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0017046302017856001,
+  "best_metric": 11.083807945251465,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.002130787752232,
   "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": 95.824,
       "eval_steps_per_second": 47.922,
       "step": 20
+    },
+    {
+      "epoch": 0.0017898617118748802,
+      "grad_norm": 0.5952379703521729,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 44.3498,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018750932219641601,
+      "grad_norm": 0.48162856698036194,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 44.3237,
+      "step": 22
+    },
+    {
+      "epoch": 0.0019603247320534403,
+      "grad_norm": 0.5268715620040894,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 44.3326,
+      "step": 23
+    },
+    {
+      "epoch": 0.00204555624214272,
+      "grad_norm": 0.4241119623184204,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 44.3351,
+      "step": 24
+    },
+    {
+      "epoch": 0.002130787752232,
+      "grad_norm": 0.5421972274780273,
+      "learning_rate": 0.0,
+      "loss": 44.326,
+      "step": 25
+    },
+    {
+      "epoch": 0.002130787752232,
+      "eval_loss": 11.083807945251465,
+      "eval_runtime": 53.227,
+      "eval_samples_per_second": 92.829,
+      "eval_steps_per_second": 46.424,
+      "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": 17557094400.0,
+  "total_flos": 21852979200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null