Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b5a90cbae015dfc7be5202391501d2928f4f0767384038e1df885dbf47ed45
+oid sha256:750d7d2c026cb4edc0de34edd942498d472ecc7f9ec3e8eb5c04d941861c272e
 size 435773944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8d9363a7dfcef3b000a69e27d77c3b61ff00273a6f2f166771555b98f88230
+oid sha256:cba134d01587202cdf24feca111dfe0825e7bc1c2d3e80daf37fa73e0d0c7ba0
 size 222034900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58a55fcf967a46936d11fd0124d1ff2bd8c83df24764f5a640a993eb06eec71
+oid sha256:897cf9d004a67877002b3d743e6c35021fd74d92777e133acb701e8c64884078
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
+oid sha256:90c455b2a7603e9003556345290fd0185bd6c6017de2b595e3f9c6216f721e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2731058597564697,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.018373346398824104,
+  "best_metric": 1.2610796689987183,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.02449779519843214,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 10.397,
       "eval_steps_per_second": 2.601,
       "step": 150
+    },
+    {
+      "epoch": 0.019598236158745713,
+      "grad_norm": 0.8640761971473694,
+      "learning_rate": 2.2644444444444443e-06,
+      "loss": 0.9152,
+      "step": 160
+    },
+    {
+      "epoch": 0.02082312591866732,
+      "grad_norm": 1.1081897020339966,
+      "learning_rate": 1.6983333333333333e-06,
+      "loss": 1.0269,
+      "step": 170
+    },
+    {
+      "epoch": 0.022048015678588925,
+      "grad_norm": 1.8240900039672852,
+      "learning_rate": 1.1322222222222221e-06,
+      "loss": 1.0471,
+      "step": 180
+    },
+    {
+      "epoch": 0.023272905438510533,
+      "grad_norm": 5.866700649261475,
+      "learning_rate": 5.661111111111111e-07,
+      "loss": 1.4556,
+      "step": 190
+    },
+    {
+      "epoch": 0.02449779519843214,
+      "grad_norm": 24.9132022857666,
+      "learning_rate": 0.0,
+      "loss": 1.7105,
+      "step": 200
+    },
+    {
+      "epoch": 0.02449779519843214,
+      "eval_loss": 1.2610796689987183,
+      "eval_runtime": 247.8876,
+      "eval_samples_per_second": 10.4,
+      "eval_steps_per_second": 2.602,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.82956662496297e+16,
+  "total_flos": 6.42876087163945e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null