Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07436ae71f6e1ce8a1d9ba93454af8b9a76a084ddf9ac92f61f5c04b5d97a6ef
+oid sha256:5db2472e054652cac3c6563de0b886752b6af5bf008161559f18d45e2126e816
 size 3443601480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d910564c6085ce3f1a94c2a79b7c69df5c40bb19530f22a6afe32c53273ef0f
+oid sha256:d297881495baea51f2a2d8d52b4c6c9963cc5c9cfc2bf018e5abb3fba0264bdc
 size 682101396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6be1ee61e986469888561dce8de3f492add76f3bf5cc94c3bd31234e25cafc
+oid sha256:161a33e84b4c64fa9febe6f657339b8da5f141eb4edce251ae9e5a98bceac60f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691263e55c7bb34b6e090bd89cf079f362100d7bd758be475bd3e7091c1a4ed6
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8877848386764526,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.025388765471278957,
+  "best_metric": 1.7957185506820679,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.050777530942557915,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 2.425,
       "eval_steps_per_second": 1.213,
       "step": 100
+    },
+    {
+      "epoch": 0.027927642018406855,
+      "grad_norm": 5.097551345825195,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.0565,
+      "step": 110
+    },
+    {
+      "epoch": 0.030466518565534752,
+      "grad_norm": 5.463619709014893,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.8281,
+      "step": 120
+    },
+    {
+      "epoch": 0.03300539511266265,
+      "grad_norm": 6.433900356292725,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.8498,
+      "step": 130
+    },
+    {
+      "epoch": 0.035544271659790544,
+      "grad_norm": 5.998843193054199,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.0344,
+      "step": 140
+    },
+    {
+      "epoch": 0.03808314820691844,
+      "grad_norm": 5.395852088928223,
+      "learning_rate": 5e-05,
+      "loss": 1.9115,
+      "step": 150
+    },
+    {
+      "epoch": 0.04062202475404633,
+      "grad_norm": 4.1980390548706055,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.9682,
+      "step": 160
+    },
+    {
+      "epoch": 0.04316090130117423,
+      "grad_norm": 3.98956561088562,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.8356,
+      "step": 170
+    },
+    {
+      "epoch": 0.04569977784830213,
+      "grad_norm": 4.076719284057617,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8401,
+      "step": 180
+    },
+    {
+      "epoch": 0.04823865439543002,
+      "grad_norm": 4.793858051300049,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.7489,
+      "step": 190
+    },
+    {
+      "epoch": 0.050777530942557915,
+      "grad_norm": 4.629513740539551,
+      "learning_rate": 0.0,
+      "loss": 1.6943,
+      "step": 200
+    },
+    {
+      "epoch": 0.050777530942557915,
+      "eval_loss": 1.7957185506820679,
+      "eval_runtime": 684.0192,
+      "eval_samples_per_second": 2.425,
+      "eval_steps_per_second": 1.213,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.70749866442752e+16,
+  "total_flos": 1.541499732885504e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null