Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2114d11a3a42e9f9badca32b1b8e285f99e206308af024496580c589749c23db
+oid sha256:7d45da4b43cc712e2c1159b2dc458d6896c62349a6b3ec95d4d7feca906cda72
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f30ff423e9d220d5c3bf536579634e493b692c5eb3c4f9e4ae770cc5b7e683
+oid sha256:b90e8262d927e11b7bb0e5947f818c0a8c992a9c2a42281b44c604e5f0507005
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b5f447fdf5275d96a8aa3fd1a386234c8c0b0a0ddf0d4ee97f8353919167c5
+oid sha256:15591282530628074d1abaa01e0c13f007c06cb685f2583adb40d1a3d629d0e7
 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": 2.1507134437561035,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.019603038470963,
+  "best_metric": 2.1368038654327393,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02450379808870375,
   "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": 14.215,
       "eval_steps_per_second": 7.108,
       "step": 20
+    },
+    {
+      "epoch": 0.02058319039451115,
+      "grad_norm": 0.7433381676673889,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.1337,
+      "step": 21
+    },
+    {
+      "epoch": 0.0215633423180593,
+      "grad_norm": 0.7238690853118896,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.1446,
+      "step": 22
+    },
+    {
+      "epoch": 0.02254349424160745,
+      "grad_norm": 0.54570472240448,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.9859,
+      "step": 23
+    },
+    {
+      "epoch": 0.0235236461651556,
+      "grad_norm": 0.628850519657135,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.2154,
+      "step": 24
+    },
+    {
+      "epoch": 0.02450379808870375,
+      "grad_norm": 0.9672688245773315,
+      "learning_rate": 0.0,
+      "loss": 2.0251,
+      "step": 25
+    },
+    {
+      "epoch": 0.02450379808870375,
+      "eval_loss": 2.1368038654327393,
+      "eval_runtime": 30.5546,
+      "eval_samples_per_second": 14.073,
+      "eval_steps_per_second": 7.037,
+      "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": 68585300951040.0,
+  "total_flos": 85731626188800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null