Training in progress, step 57, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1b0f0b368dbeb07e31566defc95ed109606879308321732694671b31b89124
+oid sha256:62b14eceb1c83043124d981520cb978b6215cecf0ed5824c08210b8a86393249
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a256967de46c83a1028fb71ed6883b7d507057182f4eda522120d8fb24d6d585
+oid sha256:ac76c6de2efa00a7c762518c01ec96b5b2c7c5dcbd16847483f1e2d46309502d
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87843e6917141f7f1e7f12e442b00953ba60bff347078563b062ea5b5c6b6faa
+oid sha256:1184f74cac2f2a79ae0f6351f3ca41df47658fbab85421e4759da7ec9517a489
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c19540610427b7a8e051502a2f9b29e8689f426c64528ae25ca45e698aa73ad
+oid sha256:798c2fb93c2c30432cc6d8a50fd6e334ae2cbcbf55475fcdeccb88eb2c638bd2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.48477548360824585,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.6315789473684212,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 57,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,55 @@
       "eval_samples_per_second": 47.076,
       "eval_steps_per_second": 11.769,
       "step": 50
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.6864362359046936,
+      "learning_rate": 3.967505666178556e-06,
+      "loss": 0.2494,
+      "step": 51
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.6838574409484863,
+      "learning_rate": 2.7665454196040664e-06,
+      "loss": 0.2374,
+      "step": 52
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.830783486366272,
+      "learning_rate": 1.7765412472811771e-06,
+      "loss": 0.2275,
+      "step": 53
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.7984945774078369,
+      "learning_rate": 1.0019147481706625e-06,
+      "loss": 0.1932,
+      "step": 54
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.8175436854362488,
+      "learning_rate": 4.461255922609986e-07,
+      "loss": 0.3245,
+      "step": 55
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.7662434577941895,
+      "learning_rate": 1.1165606884234181e-07,
+      "loss": 0.2508,
+      "step": 56
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8699974417686462,
+      "learning_rate": 0.0,
+      "loss": 0.2183,
+      "step": 57
     }
   ],
   "logging_steps": 1,
@@ -396,12 +445,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9959607883530240.0,
+  "total_flos": 1.133593560612864e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null