Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c209b7bf72e9a0283cbadfa15442c82a5e4eb9519b9d7364acd840d847689f
+oid sha256:ab8c8dd89fe6080fa7fbcec9ea73e9231a0a82c17ca756a794c22c4555da03ca
 size 67240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69036cb9e8b134c2b1a58619820e6464ce30832ba3994ff33678ebb4607d3d7
+oid sha256:cb1f79bf8cd7bfde47c4b8900225e45de1a79da8b283da85951074d8b1045e0e
 size 138758

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b25434515ff1ffa5ef57e151ef89f031c4dd81c881229710479bc4c6a54e6d
+oid sha256:edbcf2d15803e2421fecb3f78827c12e7e0cfd18cfa9f829993ebbbd3c374be1
 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": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.004233789877008404,
+  "epoch": 0.008467579754016808,
   "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": 98.748,
       "eval_steps_per_second": 49.379,
       "step": 100
+    },
+    {
+      "epoch": 0.004657168864709245,
+      "grad_norm": 0.0001554292975924909,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 46.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.005080547852410085,
+      "grad_norm": 0.00017063747509382665,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 46.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.005503926840110925,
+      "grad_norm": 0.0002251509140478447,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 46.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.005927305827811766,
+      "grad_norm": 0.00025318050757050514,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 46.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.006350684815512606,
+      "grad_norm": 0.00024476656108163297,
+      "learning_rate": 5e-05,
+      "loss": 46.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.006774063803213447,
+      "grad_norm": 0.0004327484348323196,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 46.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.007197442790914287,
+      "grad_norm": 0.00031539108022116125,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 46.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.007620821778615127,
+      "grad_norm": 0.00022764148889109492,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 46.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.008044200766315967,
+      "grad_norm": 0.00025987360277213156,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 46.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.008467579754016808,
+      "grad_norm": 0.00024760179803706706,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.008467579754016808,
+      "eval_loss": 11.5,
+      "eval_runtime": 101.2299,
+      "eval_samples_per_second": 98.242,
+      "eval_steps_per_second": 49.126,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -107,7 +185,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8201347792896.0,
+  "total_flos": 16362094854144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null