Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54cba7d4dcf6f8a2d0a77dfa26886585ac6e1adcb74343c827ffcf5b0beb997a
+oid sha256:df9a3f4eb1637f66f05417e60405ab2769165cfa1c4a26be06271371b88b87d1
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843bc4e3bf2c2f53382ab655c79062e25f936d8bdbe17845b4c87e30d1ced136
+oid sha256:76964ddccc428f24eb28ab97e7d75da038179228ede11677fc639a9b03e4ba4a
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6981ac5fbd6e8a6689fc60b6b9306d4ef9d58cbe68dd437ee41e4684379316
+oid sha256:d725e2490628c33ac6b25be77ff848fe77955fb11a631dc6b602dda22c0bc29b
 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": 1.4150354862213135,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04664723032069971,
+  "best_metric": 1.4121884107589722,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.05830903790087463,
   "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": 4.941,
       "eval_steps_per_second": 2.484,
       "step": 20
+    },
+    {
+      "epoch": 0.04897959183673469,
+      "grad_norm": 0.6569919586181641,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.004,
+      "step": 21
+    },
+    {
+      "epoch": 0.05131195335276968,
+      "grad_norm": 0.45704540610313416,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.1221,
+      "step": 22
+    },
+    {
+      "epoch": 0.053644314868804666,
+      "grad_norm": 0.5303517580032349,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.7539,
+      "step": 23
+    },
+    {
+      "epoch": 0.05597667638483965,
+      "grad_norm": 0.5232126116752625,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.5575,
+      "step": 24
+    },
+    {
+      "epoch": 0.05830903790087463,
+      "grad_norm": 0.5050119161605835,
+      "learning_rate": 0.0,
+      "loss": 1.474,
+      "step": 25
+    },
+    {
+      "epoch": 0.05830903790087463,
+      "eval_loss": 1.4121884107589722,
+      "eval_runtime": 36.7496,
+      "eval_samples_per_second": 4.925,
+      "eval_steps_per_second": 2.476,
+      "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": 1987886889566208.0,
+  "total_flos": 2487984220274688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null