Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f0e8b497e0ee74e1d9078f22cb6bab77028f05afb8cc88563b3ae254cd0fdcf
+oid sha256:b2fe03e64cb15768d1cd8948c3b5771f52ceabd68f4929b5086f05322316651a
 size 1279323952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8517fdd165c345c8a0e0ac0123ea52f40affe701d0290dc63c174f76877a5a88
+oid sha256:d4f1e1185d2450118d34023796b27a5efe35be5a94b75ef2e5161a3076274146
 size 2558910034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76dcb566d5a806738709d623034241d7e4801f3e05a1b69ce0e7c24cc89d0804
+oid sha256:cfe0a0399ff6a3ad1379c36f2a12002da56143a1e8b0f97364e7a19a7da0b2ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f011953770dc18a51194e919361544c1e41f047fac26af2e17015642e43c7d
+oid sha256:50d23b4f208a9403528cc4590d75da0ba9842779b9cd25a1b5978ffbe9bcceb1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4104949235916138,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0022755005390091903,
+  "best_metric": 1.217628002166748,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.004551001078018381,
   "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": 5.539,
       "eval_steps_per_second": 5.539,
       "step": 100
+    },
+    {
+      "epoch": 0.002503050592910109,
+      "grad_norm": 1.1351838111877441,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.6866,
+      "step": 110
+    },
+    {
+      "epoch": 0.002730600646811028,
+      "grad_norm": 1.3157535791397095,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.8786,
+      "step": 120
+    },
+    {
+      "epoch": 0.0029581507007119473,
+      "grad_norm": 1.2388049364089966,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 1.1656,
+      "step": 130
+    },
+    {
+      "epoch": 0.003185700754612866,
+      "grad_norm": 1.667664885520935,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.6019,
+      "step": 140
+    },
+    {
+      "epoch": 0.003413250808513785,
+      "grad_norm": 14.491639137268066,
+      "learning_rate": 5e-06,
+      "loss": 2.5697,
+      "step": 150
+    },
+    {
+      "epoch": 0.0036408008624147043,
+      "grad_norm": 1.081459879875183,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.6925,
+      "step": 160
+    },
+    {
+      "epoch": 0.003868350916315623,
+      "grad_norm": 2.302001953125,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.7282,
+      "step": 170
+    },
+    {
+      "epoch": 0.004095900970216542,
+      "grad_norm": 1.375418782234192,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.8401,
+      "step": 180
+    },
+    {
+      "epoch": 0.004323451024117461,
+      "grad_norm": 1.4581494331359863,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.4591,
+      "step": 190
+    },
+    {
+      "epoch": 0.004551001078018381,
+      "grad_norm": 9.276606559753418,
+      "learning_rate": 0.0,
+      "loss": 2.4783,
+      "step": 200
+    },
+    {
+      "epoch": 0.004551001078018381,
+      "eval_loss": 1.217628002166748,
+      "eval_runtime": 3338.5785,
+      "eval_samples_per_second": 5.542,
+      "eval_steps_per_second": 5.542,
+      "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": 6.82669886102569e+16,
+  "total_flos": 1.363637353536553e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null