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:f5abf21cfab48dd3925d4ec5a166b7f55914349d9850978c53b268e3e112c702
+oid sha256:09119648709aaca99aeac019654cb19b6aaf44fdf0a43040a262fa8d248fc7e6
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4252abb5398e8d90f8b250957c93777aadd7d391b06d22581496fb853312f3aa
+oid sha256:f2ee9c5e3d5591799bed352bcf6761c5ae824a2352f49bcacba87ca5ca5afd68
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a345a09bb686cac75cb2496fa891d6f1b56e65517e790e016904dc972ee23ae
+oid sha256:2affdcfce18cd416c944a033b88ff813db8c77a9afe89cef3e21c09a80cdff40
 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": 0.4108954071998596,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0935672514619883,
+  "best_metric": 0.4004054665565491,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.11695906432748537,
   "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": 7.83,
       "eval_steps_per_second": 3.915,
       "step": 20
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 1.1456410884857178,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.5951,
+      "step": 21
+    },
+    {
+      "epoch": 0.10292397660818714,
+      "grad_norm": 0.8460454344749451,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.6078,
+      "step": 22
+    },
+    {
+      "epoch": 0.10760233918128655,
+      "grad_norm": 0.872773289680481,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.71,
+      "step": 23
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 0.9382916688919067,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.7091,
+      "step": 24
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "grad_norm": 0.804826557636261,
+      "learning_rate": 0.0,
+      "loss": 1.2807,
+      "step": 25
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "eval_loss": 0.4004054665565491,
+      "eval_runtime": 11.4784,
+      "eval_samples_per_second": 7.841,
+      "eval_steps_per_second": 3.92,
+      "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": 2845655470964736.0,
+  "total_flos": 3488222835376128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null