Training in progress, step 213, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d948f01888b537049c0b7f4cd265d9772f7c9fce56ca522794956b763856b0
+oid sha256:942f8465cabeb76dcc95e6f1376a7a2bd0f43607b0fd95e02ca0696335823d9e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecb3abc7a79b3f6942aff7a32c9b7f831fa7e66b7e5696c754675ea496a238c
+oid sha256:55b820f6aca64ee05247f1dcfe684e8698516c64a44a9585c856f3f4c25ba1c7
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72c80b8d0207539470b3350fbbb8ff868cabe1e94b611568dbb68ea2a70094f
+oid sha256:84cc23981c65e9e4b36610af3a7f8e0530e00fd931109c8f0f300b8809f05c8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0ecec6be335b6d48527a855a4479db9f3cb677f2a541e8d4da775c12fae434f
+oid sha256:f3089190bafc90731224612761031dd1ac152bc3d675652a9bd05e3a743d0eea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.7617204189300537,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.5432937181663837,
+  "epoch": 0.5786078098471986,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 213,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1447,6 +1447,97 @@
       "eval_samples_per_second": 6.974,
       "eval_steps_per_second": 1.744,
       "step": 200
+    },
+    {
+      "epoch": 0.5460101867572156,
+      "grad_norm": 0.7055419087409973,
+      "learning_rate": 1.7194582631535617e-06,
+      "loss": 2.7168,
+      "step": 201
+    },
+    {
+      "epoch": 0.5487266553480475,
+      "grad_norm": 0.7580511569976807,
+      "learning_rate": 1.4454863088532388e-06,
+      "loss": 2.7299,
+      "step": 202
+    },
+    {
+      "epoch": 0.5514431239388795,
+      "grad_norm": 0.6726568341255188,
+      "learning_rate": 1.19511780643915e-06,
+      "loss": 2.8939,
+      "step": 203
+    },
+    {
+      "epoch": 0.5541595925297114,
+      "grad_norm": 0.6482507586479187,
+      "learning_rate": 9.684127182679526e-07,
+      "loss": 2.7221,
+      "step": 204
+    },
+    {
+      "epoch": 0.5568760611205433,
+      "grad_norm": 0.638670027256012,
+      "learning_rate": 7.654253393936439e-07,
+      "loss": 2.7499,
+      "step": 205
+    },
+    {
+      "epoch": 0.5595925297113752,
+      "grad_norm": 0.7101965546607971,
+      "learning_rate": 5.862042845640403e-07,
+      "loss": 2.7859,
+      "step": 206
+    },
+    {
+      "epoch": 0.5623089983022072,
+      "grad_norm": 0.7514301538467407,
+      "learning_rate": 4.307924765777682e-07,
+      "loss": 2.7718,
+      "step": 207
+    },
+    {
+      "epoch": 0.565025466893039,
+      "grad_norm": 0.7341988682746887,
+      "learning_rate": 2.9922713600439854e-07,
+      "loss": 2.8015,
+      "step": 208
+    },
+    {
+      "epoch": 0.567741935483871,
+      "grad_norm": 0.782926619052887,
+      "learning_rate": 1.915397722702217e-07,
+      "loss": 2.7818,
+      "step": 209
+    },
+    {
+      "epoch": 0.5704584040747029,
+      "grad_norm": 0.7334633469581604,
+      "learning_rate": 1.0775617611189503e-07,
+      "loss": 2.7087,
+      "step": 210
+    },
+    {
+      "epoch": 0.5731748726655348,
+      "grad_norm": 0.7129755020141602,
+      "learning_rate": 4.789641339963957e-08,
+      "loss": 2.7918,
+      "step": 211
+    },
+    {
+      "epoch": 0.5758913412563668,
+      "grad_norm": 0.707548201084137,
+      "learning_rate": 1.1974820331517312e-08,
+      "loss": 2.7835,
+      "step": 212
+    },
+    {
+      "epoch": 0.5786078098471986,
+      "grad_norm": 0.7628645300865173,
+      "learning_rate": 0.0,
+      "loss": 2.9418,
+      "step": 213
     }
   ],
   "logging_steps": 1,
@@ -1470,12 +1561,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.188874371905618e+18,
+  "total_flos": 1.2664015930376847e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null