Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ac9246745d38528b72d7f63132fc7ec0015d9588cdb821eafd3af4a24784ed
+oid sha256:00a97f50e7872df438e481ea080064c56a5f9982aea2afef13744f48f0fd2d0e
 size 1252904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce18f2c835d876b5da5f83319d020fb8183137f37da9915d454389f5ba69215
+oid sha256:4170cf0869bd634cd366ba58737d1ab3a419c23b94ab2470a5620642ce46468f
 size 669562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:912547e3439c087a494b30d9f86b186e0f5dd1b1bc4e41596aeb4a26e2e169e9
+oid sha256:116b9be2098e40bb27534c05f40050ba378d5645f092cb52dbca1e194fd5a781
 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": 10.686875343322754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0013450125254291432,
+  "best_metric": 10.674724578857422,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.0026900250508582863,
   "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": 104.457,
       "eval_steps_per_second": 52.23,
       "step": 100
+    },
+    {
+      "epoch": 0.0014795137779720574,
+      "grad_norm": 0.24451228976249695,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.684,
+      "step": 110
+    },
+    {
+      "epoch": 0.0016140150305149717,
+      "grad_norm": 0.2579585313796997,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.6861,
+      "step": 120
+    },
+    {
+      "epoch": 0.001748516283057886,
+      "grad_norm": 0.25077152252197266,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.6829,
+      "step": 130
+    },
+    {
+      "epoch": 0.0018830175356008003,
+      "grad_norm": 0.24820062518119812,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.6845,
+      "step": 140
+    },
+    {
+      "epoch": 0.0020175187881437146,
+      "grad_norm": 0.18705056607723236,
+      "learning_rate": 5e-05,
+      "loss": 10.677,
+      "step": 150
+    },
+    {
+      "epoch": 0.0021520200406866287,
+      "grad_norm": 0.25979742407798767,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.6758,
+      "step": 160
+    },
+    {
+      "epoch": 0.002286521293229543,
+      "grad_norm": 0.26039084792137146,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.6775,
+      "step": 170
+    },
+    {
+      "epoch": 0.0024210225457724577,
+      "grad_norm": 0.22908814251422882,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.6743,
+      "step": 180
+    },
+    {
+      "epoch": 0.002555523798315372,
+      "grad_norm": 0.24866251647472382,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.6781,
+      "step": 190
+    },
+    {
+      "epoch": 0.0026900250508582863,
+      "grad_norm": 0.19731056690216064,
+      "learning_rate": 0.0,
+      "loss": 10.6787,
+      "step": 200
+    },
+    {
+      "epoch": 0.0026900250508582863,
+      "eval_loss": 10.674724578857422,
+      "eval_runtime": 300.6284,
+      "eval_samples_per_second": 104.132,
+      "eval_steps_per_second": 52.068,
+      "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": 35690171596800.0,
+  "total_flos": 71380343193600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null