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:dea312c683c66be75416de58d1702bcaee368716233a88b4b1ae682ce0fa2f38
+oid sha256:3a32df4b738bd7dec6bc2d6ce99294138a5b676cb35aa8c534da9f7adebe3060
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51124d0fdb3009fe2f8ac57c9e0159aefdb7b8d2fe75e57acc767200bdaa56f6
+oid sha256:8c3afea5df0d52baac4f11eb90cebced8544dcea441eae9f12302f8dfd0adb26
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff21e0751b3a5cea005fdd4e373110f88946aad70f157d90ebe5ea2842c00ef6
+oid sha256:e926b08d55705d8356636d5ec7ca1ca5847643fe2200800bd149d0e5a1f2f87b
 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": 1.019839882850647,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0935672514619883,
+  "best_metric": 0.9813918471336365,
+  "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": 4.086,
       "eval_steps_per_second": 2.043,
       "step": 20
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 0.6741195917129517,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.0423,
+      "step": 21
+    },
+    {
+      "epoch": 0.10292397660818714,
+      "grad_norm": 0.6320233345031738,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.991,
+      "step": 22
+    },
+    {
+      "epoch": 0.10760233918128655,
+      "grad_norm": 0.5491010546684265,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.063,
+      "step": 23
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 0.5644322037696838,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.8984,
+      "step": 24
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "grad_norm": 0.6533280611038208,
+      "learning_rate": 0.0,
+      "loss": 0.9426,
+      "step": 25
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "eval_loss": 0.9813918471336365,
+      "eval_runtime": 22.0739,
+      "eval_samples_per_second": 4.077,
+      "eval_steps_per_second": 2.039,
+      "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": 1.060678819381248e+16,
+  "total_flos": 1.313975253860352e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null