Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19abd315ba6325d3c69b88a3523bb893fbeae7c9f11cf8e8a532a7568424f786
+oid sha256:0b2310e7a4d9c2750fd344925fbbcd52393807c51fec3ffbde374ec87616c3d2
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18677bb0c402f4eda66d46ad6d9c4a85fa0a1b070c5b88fc2fa36935f4de1987
+oid sha256:cdb91fd185fac632dac2585a730e399680ba29c5ccad76630b3fc9242e61f98c
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905784641e6ebfaee544262c51ccc7825688f2bd1c5d6d6a9e62061183b37db7
+oid sha256:fd25ac9c099ac6434f24a73d4e310fc4b5eac058814a5ebffab53a9ff7319937
 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": 1.1016162633895874,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0034278858514011482,
+  "best_metric": 1.0927900075912476,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.004284857314251435,
   "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": 5.664,
       "eval_steps_per_second": 2.833,
       "step": 20
+    },
+    {
+      "epoch": 0.003599280143971206,
+      "grad_norm": 1.463152527809143,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.0791,
+      "step": 21
+    },
+    {
+      "epoch": 0.003770674436541263,
+      "grad_norm": 1.4073078632354736,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.4038,
+      "step": 22
+    },
+    {
+      "epoch": 0.003942068729111321,
+      "grad_norm": 1.736242413520813,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 4.8802,
+      "step": 23
+    },
+    {
+      "epoch": 0.004113463021681378,
+      "grad_norm": 1.039347529411316,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 4.1815,
+      "step": 24
+    },
+    {
+      "epoch": 0.004284857314251435,
+      "grad_norm": 1.331517219543457,
+      "learning_rate": 0.0,
+      "loss": 3.8949,
+      "step": 25
+    },
+    {
+      "epoch": 0.004284857314251435,
+      "eval_loss": 1.0927900075912476,
+      "eval_runtime": 454.4525,
+      "eval_samples_per_second": 5.407,
+      "eval_steps_per_second": 2.704,
+      "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": 8238615861657600.0,
+  "total_flos": 1.03619704651776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null