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:f14b98721fd78d56d91768fa4bbbd66f4cc7fe6b48f2adf6af4db86fc8f7462f
+oid sha256:293c6e9e5a3458f158ad294b524e2a36757e26153a65fecaa1a5f9710c210019
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:416d45d931ecb3d674f2892b483c5831f63400a080814346cb7baf8e8d1536ff
+oid sha256:fd85de5f13f267298eefef66b27173f57d8e3a493aeeac708f87ef77b9bc0b07
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1857c66e6e8d6e11a0747eed5b4017955023dcf6f7964ebdc3cb5802d5c9a1
+oid sha256:2c6035987a59d8e6fd59331c7d2d7c47cb9cce66571a75b6cf75ae999973aa2c
 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": 0.9340419769287109,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0004339194862393283,
+  "best_metric": 0.9151530265808105,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0005423993577991604,
   "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": 11.357,
       "eval_steps_per_second": 5.679,
       "step": 20
+    },
+    {
+      "epoch": 0.0004556154605512947,
+      "grad_norm": 4.069162368774414,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.6392,
+      "step": 21
+    },
+    {
+      "epoch": 0.00047731143486326113,
+      "grad_norm": 4.433424472808838,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.2692,
+      "step": 22
+    },
+    {
+      "epoch": 0.0004990074091752275,
+      "grad_norm": 4.288788318634033,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.7456,
+      "step": 23
+    },
+    {
+      "epoch": 0.000520703383487194,
+      "grad_norm": 5.057470321655273,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.965,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005423993577991604,
+      "grad_norm": 5.0678277015686035,
+      "learning_rate": 0.0,
+      "loss": 3.955,
+      "step": 25
+    },
+    {
+      "epoch": 0.0005423993577991604,
+      "eval_loss": 0.9151530265808105,
+      "eval_runtime": 1779.2107,
+      "eval_samples_per_second": 10.908,
+      "eval_steps_per_second": 5.454,
+      "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": 1305898647552000.0,
+  "total_flos": 1632373309440000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null